diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,114065 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9999693053807668, + "eval_steps": 500, + "global_step": 16289, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 6.138923846649683e-05, + "grad_norm": 5.419731382643109, + "learning_rate": 4.08997955010225e-08, + "loss": 1.6778, + "step": 1 + }, + { + "epoch": 0.00012277847693299365, + "grad_norm": 6.088084298360978, + "learning_rate": 8.1799591002045e-08, + "loss": 1.6697, + "step": 2 + }, + { + "epoch": 0.00018416771539949046, + "grad_norm": 5.992567488457631, + "learning_rate": 1.226993865030675e-07, + "loss": 1.7223, + "step": 3 + }, + { + "epoch": 0.0002455569538659873, + "grad_norm": 6.041118260097492, + "learning_rate": 1.6359918200409e-07, + "loss": 1.6739, + "step": 4 + }, + { + "epoch": 0.00030694619233248414, + "grad_norm": 5.555813179881878, + "learning_rate": 2.0449897750511251e-07, + "loss": 1.7091, + "step": 5 + }, + { + "epoch": 0.0003683354307989809, + "grad_norm": 5.474330677779886, + "learning_rate": 2.45398773006135e-07, + "loss": 1.717, + "step": 6 + }, + { + "epoch": 0.00042972466926547776, + "grad_norm": 5.470606816616102, + "learning_rate": 2.862985685071575e-07, + "loss": 1.6591, + "step": 7 + }, + { + "epoch": 0.0004911139077319746, + "grad_norm": 5.413902671919053, + "learning_rate": 3.2719836400818e-07, + "loss": 1.5951, + "step": 8 + }, + { + "epoch": 0.0005525031461984714, + "grad_norm": 5.129594963808689, + "learning_rate": 3.680981595092025e-07, + "loss": 1.6217, + "step": 9 + }, + { + "epoch": 0.0006138923846649683, + "grad_norm": 5.427275108676571, + "learning_rate": 4.0899795501022503e-07, + "loss": 1.6719, + "step": 10 + }, + { + "epoch": 0.0006752816231314651, + "grad_norm": 5.471144058866722, + "learning_rate": 4.498977505112475e-07, + "loss": 1.6865, + "step": 11 + }, + { + "epoch": 0.0007366708615979618, + "grad_norm": 5.825101029676583, + "learning_rate": 4.9079754601227e-07, + "loss": 1.6633, + "step": 12 + }, + { + "epoch": 0.0007980601000644587, + "grad_norm": 6.261871018703678, + "learning_rate": 5.316973415132925e-07, + "loss": 1.6951, + "step": 13 + }, + { + "epoch": 0.0008594493385309555, + "grad_norm": 5.7149695394135245, + "learning_rate": 5.72597137014315e-07, + "loss": 1.7412, + "step": 14 + }, + { + "epoch": 0.0009208385769974523, + "grad_norm": 5.055757884950573, + "learning_rate": 6.134969325153375e-07, + "loss": 1.619, + "step": 15 + }, + { + "epoch": 0.0009822278154639492, + "grad_norm": 4.589612950195362, + "learning_rate": 6.5439672801636e-07, + "loss": 1.6729, + "step": 16 + }, + { + "epoch": 0.001043617053930446, + "grad_norm": 5.154877864119565, + "learning_rate": 6.952965235173826e-07, + "loss": 1.6051, + "step": 17 + }, + { + "epoch": 0.0011050062923969428, + "grad_norm": 4.790962910083796, + "learning_rate": 7.36196319018405e-07, + "loss": 1.6424, + "step": 18 + }, + { + "epoch": 0.0011663955308634396, + "grad_norm": 4.061899551124692, + "learning_rate": 7.770961145194275e-07, + "loss": 1.6471, + "step": 19 + }, + { + "epoch": 0.0012277847693299366, + "grad_norm": 4.180974810647579, + "learning_rate": 8.179959100204501e-07, + "loss": 1.6453, + "step": 20 + }, + { + "epoch": 0.0012891740077964333, + "grad_norm": 4.196394111136924, + "learning_rate": 8.588957055214725e-07, + "loss": 1.6173, + "step": 21 + }, + { + "epoch": 0.0013505632462629301, + "grad_norm": 2.3630192015891573, + "learning_rate": 8.99795501022495e-07, + "loss": 1.5609, + "step": 22 + }, + { + "epoch": 0.001411952484729427, + "grad_norm": 2.289404102868081, + "learning_rate": 9.406952965235175e-07, + "loss": 1.6068, + "step": 23 + }, + { + "epoch": 0.0014733417231959237, + "grad_norm": 2.122560044928578, + "learning_rate": 9.8159509202454e-07, + "loss": 1.5356, + "step": 24 + }, + { + "epoch": 0.0015347309616624205, + "grad_norm": 2.1356886583888617, + "learning_rate": 1.0224948875255625e-06, + "loss": 1.6425, + "step": 25 + }, + { + "epoch": 0.0015961202001289175, + "grad_norm": 1.9799173052629913, + "learning_rate": 1.063394683026585e-06, + "loss": 1.5471, + "step": 26 + }, + { + "epoch": 0.0016575094385954143, + "grad_norm": 1.9068186914296608, + "learning_rate": 1.1042944785276075e-06, + "loss": 1.6339, + "step": 27 + }, + { + "epoch": 0.001718898677061911, + "grad_norm": 1.9934928749546574, + "learning_rate": 1.14519427402863e-06, + "loss": 1.5512, + "step": 28 + }, + { + "epoch": 0.0017802879155284078, + "grad_norm": 1.7262822175013637, + "learning_rate": 1.1860940695296524e-06, + "loss": 1.5419, + "step": 29 + }, + { + "epoch": 0.0018416771539949046, + "grad_norm": 1.829661240041745, + "learning_rate": 1.226993865030675e-06, + "loss": 1.5467, + "step": 30 + }, + { + "epoch": 0.0019030663924614016, + "grad_norm": 1.6046616343720403, + "learning_rate": 1.2678936605316975e-06, + "loss": 1.609, + "step": 31 + }, + { + "epoch": 0.0019644556309278984, + "grad_norm": 1.5769640431836995, + "learning_rate": 1.30879345603272e-06, + "loss": 1.5313, + "step": 32 + }, + { + "epoch": 0.002025844869394395, + "grad_norm": 1.5850922133770804, + "learning_rate": 1.3496932515337425e-06, + "loss": 1.5575, + "step": 33 + }, + { + "epoch": 0.002087234107860892, + "grad_norm": 1.7487083132403785, + "learning_rate": 1.3905930470347651e-06, + "loss": 1.5068, + "step": 34 + }, + { + "epoch": 0.0021486233463273888, + "grad_norm": 1.6715946212491897, + "learning_rate": 1.4314928425357874e-06, + "loss": 1.5054, + "step": 35 + }, + { + "epoch": 0.0022100125847938855, + "grad_norm": 1.7250077343574728, + "learning_rate": 1.47239263803681e-06, + "loss": 1.4979, + "step": 36 + }, + { + "epoch": 0.0022714018232603823, + "grad_norm": 1.9103604198484807, + "learning_rate": 1.5132924335378324e-06, + "loss": 1.5818, + "step": 37 + }, + { + "epoch": 0.002332791061726879, + "grad_norm": 1.5416903080873583, + "learning_rate": 1.554192229038855e-06, + "loss": 1.4896, + "step": 38 + }, + { + "epoch": 0.002394180300193376, + "grad_norm": 1.3868157950550353, + "learning_rate": 1.5950920245398775e-06, + "loss": 1.5309, + "step": 39 + }, + { + "epoch": 0.002455569538659873, + "grad_norm": 1.4019592173454258, + "learning_rate": 1.6359918200409001e-06, + "loss": 1.4964, + "step": 40 + }, + { + "epoch": 0.00251695877712637, + "grad_norm": 1.3381016691059902, + "learning_rate": 1.6768916155419223e-06, + "loss": 1.5109, + "step": 41 + }, + { + "epoch": 0.0025783480155928667, + "grad_norm": 1.2340130663559845, + "learning_rate": 1.717791411042945e-06, + "loss": 1.5439, + "step": 42 + }, + { + "epoch": 0.0026397372540593635, + "grad_norm": 1.282139302091685, + "learning_rate": 1.7586912065439674e-06, + "loss": 1.527, + "step": 43 + }, + { + "epoch": 0.0027011264925258602, + "grad_norm": 1.4074506916891978, + "learning_rate": 1.79959100204499e-06, + "loss": 1.5234, + "step": 44 + }, + { + "epoch": 0.002762515730992357, + "grad_norm": 1.4385929325724174, + "learning_rate": 1.8404907975460124e-06, + "loss": 1.3999, + "step": 45 + }, + { + "epoch": 0.002823904969458854, + "grad_norm": 1.5536700359327238, + "learning_rate": 1.881390593047035e-06, + "loss": 1.4736, + "step": 46 + }, + { + "epoch": 0.0028852942079253506, + "grad_norm": 1.4753426777403071, + "learning_rate": 1.9222903885480575e-06, + "loss": 1.4692, + "step": 47 + }, + { + "epoch": 0.0029466834463918474, + "grad_norm": 1.3375192883071174, + "learning_rate": 1.96319018404908e-06, + "loss": 1.4065, + "step": 48 + }, + { + "epoch": 0.003008072684858344, + "grad_norm": 1.3666824322629754, + "learning_rate": 2.0040899795501023e-06, + "loss": 1.4618, + "step": 49 + }, + { + "epoch": 0.003069461923324841, + "grad_norm": 1.1325041832851601, + "learning_rate": 2.044989775051125e-06, + "loss": 1.3459, + "step": 50 + }, + { + "epoch": 0.003130851161791338, + "grad_norm": 1.2179370463026602, + "learning_rate": 2.085889570552147e-06, + "loss": 1.4754, + "step": 51 + }, + { + "epoch": 0.003192240400257835, + "grad_norm": 1.8809224945998855, + "learning_rate": 2.12678936605317e-06, + "loss": 0.8324, + "step": 52 + }, + { + "epoch": 0.0032536296387243317, + "grad_norm": 1.111862154211469, + "learning_rate": 2.1676891615541925e-06, + "loss": 1.4465, + "step": 53 + }, + { + "epoch": 0.0033150188771908285, + "grad_norm": 1.0622516874252448, + "learning_rate": 2.208588957055215e-06, + "loss": 1.4981, + "step": 54 + }, + { + "epoch": 0.0033764081156573253, + "grad_norm": 1.1291292309013106, + "learning_rate": 2.2494887525562373e-06, + "loss": 1.4463, + "step": 55 + }, + { + "epoch": 0.003437797354123822, + "grad_norm": 1.2497265527295522, + "learning_rate": 2.29038854805726e-06, + "loss": 1.4244, + "step": 56 + }, + { + "epoch": 0.003499186592590319, + "grad_norm": 1.149934518463357, + "learning_rate": 2.331288343558282e-06, + "loss": 1.3336, + "step": 57 + }, + { + "epoch": 0.0035605758310568157, + "grad_norm": 1.183657094655249, + "learning_rate": 2.3721881390593048e-06, + "loss": 1.4216, + "step": 58 + }, + { + "epoch": 0.0036219650695233124, + "grad_norm": 1.165590516711574, + "learning_rate": 2.4130879345603274e-06, + "loss": 1.4058, + "step": 59 + }, + { + "epoch": 0.0036833543079898092, + "grad_norm": 1.1106754415196056, + "learning_rate": 2.45398773006135e-06, + "loss": 1.3929, + "step": 60 + }, + { + "epoch": 0.003744743546456306, + "grad_norm": 1.0503726505658932, + "learning_rate": 2.4948875255623727e-06, + "loss": 1.4761, + "step": 61 + }, + { + "epoch": 0.0038061327849228032, + "grad_norm": 0.9512009030733303, + "learning_rate": 2.535787321063395e-06, + "loss": 1.3055, + "step": 62 + }, + { + "epoch": 0.0038675220233893, + "grad_norm": 0.9696728967488274, + "learning_rate": 2.5766871165644175e-06, + "loss": 1.3976, + "step": 63 + }, + { + "epoch": 0.003928911261855797, + "grad_norm": 1.0050215774037465, + "learning_rate": 2.61758691206544e-06, + "loss": 1.3994, + "step": 64 + }, + { + "epoch": 0.003990300500322294, + "grad_norm": 1.37105510773757, + "learning_rate": 2.6584867075664624e-06, + "loss": 0.806, + "step": 65 + }, + { + "epoch": 0.00405168973878879, + "grad_norm": 1.11752272952652, + "learning_rate": 2.699386503067485e-06, + "loss": 1.4399, + "step": 66 + }, + { + "epoch": 0.004113078977255287, + "grad_norm": 1.1059760941495282, + "learning_rate": 2.7402862985685077e-06, + "loss": 1.4332, + "step": 67 + }, + { + "epoch": 0.004174468215721784, + "grad_norm": 1.1164050343538612, + "learning_rate": 2.7811860940695303e-06, + "loss": 1.411, + "step": 68 + }, + { + "epoch": 0.004235857454188281, + "grad_norm": 1.026165690855717, + "learning_rate": 2.822085889570552e-06, + "loss": 1.3684, + "step": 69 + }, + { + "epoch": 0.0042972466926547775, + "grad_norm": 1.081728084881368, + "learning_rate": 2.8629856850715747e-06, + "loss": 1.4253, + "step": 70 + }, + { + "epoch": 0.004358635931121274, + "grad_norm": 0.9555988045224345, + "learning_rate": 2.9038854805725973e-06, + "loss": 1.3663, + "step": 71 + }, + { + "epoch": 0.004420025169587771, + "grad_norm": 0.9682739997206177, + "learning_rate": 2.94478527607362e-06, + "loss": 1.3835, + "step": 72 + }, + { + "epoch": 0.004481414408054268, + "grad_norm": 0.9625143319993155, + "learning_rate": 2.985685071574642e-06, + "loss": 1.4134, + "step": 73 + }, + { + "epoch": 0.004542803646520765, + "grad_norm": 0.9175058909462707, + "learning_rate": 3.026584867075665e-06, + "loss": 1.339, + "step": 74 + }, + { + "epoch": 0.004604192884987261, + "grad_norm": 1.0701486061287444, + "learning_rate": 3.0674846625766875e-06, + "loss": 0.8422, + "step": 75 + }, + { + "epoch": 0.004665582123453758, + "grad_norm": 0.9702781684775256, + "learning_rate": 3.10838445807771e-06, + "loss": 1.356, + "step": 76 + }, + { + "epoch": 0.004726971361920255, + "grad_norm": 1.0360150434887103, + "learning_rate": 3.1492842535787323e-06, + "loss": 1.4023, + "step": 77 + }, + { + "epoch": 0.004788360600386752, + "grad_norm": 0.9146945459707857, + "learning_rate": 3.190184049079755e-06, + "loss": 1.2879, + "step": 78 + }, + { + "epoch": 0.0048497498388532494, + "grad_norm": 1.0059059628338427, + "learning_rate": 3.2310838445807776e-06, + "loss": 1.3925, + "step": 79 + }, + { + "epoch": 0.004911139077319746, + "grad_norm": 0.9407272415218308, + "learning_rate": 3.2719836400818002e-06, + "loss": 1.3454, + "step": 80 + }, + { + "epoch": 0.004972528315786243, + "grad_norm": 0.9468927727048108, + "learning_rate": 3.312883435582822e-06, + "loss": 1.3691, + "step": 81 + }, + { + "epoch": 0.00503391755425274, + "grad_norm": 0.9258823699860028, + "learning_rate": 3.3537832310838446e-06, + "loss": 1.3719, + "step": 82 + }, + { + "epoch": 0.005095306792719237, + "grad_norm": 0.9355674345177702, + "learning_rate": 3.3946830265848673e-06, + "loss": 1.3694, + "step": 83 + }, + { + "epoch": 0.005156696031185733, + "grad_norm": 0.9810739843041114, + "learning_rate": 3.43558282208589e-06, + "loss": 1.3596, + "step": 84 + }, + { + "epoch": 0.00521808526965223, + "grad_norm": 1.0296562681745476, + "learning_rate": 3.476482617586912e-06, + "loss": 1.4562, + "step": 85 + }, + { + "epoch": 0.005279474508118727, + "grad_norm": 1.0965078889281514, + "learning_rate": 3.5173824130879348e-06, + "loss": 1.4432, + "step": 86 + }, + { + "epoch": 0.005340863746585224, + "grad_norm": 0.9986550572935614, + "learning_rate": 3.5582822085889574e-06, + "loss": 1.3524, + "step": 87 + }, + { + "epoch": 0.0054022529850517205, + "grad_norm": 0.9294966776929697, + "learning_rate": 3.59918200408998e-06, + "loss": 1.3867, + "step": 88 + }, + { + "epoch": 0.005463642223518217, + "grad_norm": 0.9550344537704868, + "learning_rate": 3.6400817995910027e-06, + "loss": 1.3575, + "step": 89 + }, + { + "epoch": 0.005525031461984714, + "grad_norm": 1.0151328526383596, + "learning_rate": 3.680981595092025e-06, + "loss": 1.4337, + "step": 90 + }, + { + "epoch": 0.005586420700451211, + "grad_norm": 0.9043744733050825, + "learning_rate": 3.7218813905930475e-06, + "loss": 1.3832, + "step": 91 + }, + { + "epoch": 0.005647809938917708, + "grad_norm": 0.938104655837314, + "learning_rate": 3.76278118609407e-06, + "loss": 1.4235, + "step": 92 + }, + { + "epoch": 0.005709199177384204, + "grad_norm": 0.9482335036691907, + "learning_rate": 3.8036809815950928e-06, + "loss": 1.3511, + "step": 93 + }, + { + "epoch": 0.005770588415850701, + "grad_norm": 0.9585112755571599, + "learning_rate": 3.844580777096115e-06, + "loss": 1.335, + "step": 94 + }, + { + "epoch": 0.005831977654317198, + "grad_norm": 0.8867970567430236, + "learning_rate": 3.885480572597138e-06, + "loss": 1.3805, + "step": 95 + }, + { + "epoch": 0.005893366892783695, + "grad_norm": 0.9515576536482325, + "learning_rate": 3.92638036809816e-06, + "loss": 1.3139, + "step": 96 + }, + { + "epoch": 0.0059547561312501916, + "grad_norm": 0.9350752722419858, + "learning_rate": 3.967280163599183e-06, + "loss": 1.3402, + "step": 97 + }, + { + "epoch": 0.006016145369716688, + "grad_norm": 0.9127982682996693, + "learning_rate": 4.008179959100205e-06, + "loss": 1.2927, + "step": 98 + }, + { + "epoch": 0.006077534608183185, + "grad_norm": 0.9863790576398986, + "learning_rate": 4.049079754601227e-06, + "loss": 1.3686, + "step": 99 + }, + { + "epoch": 0.006138923846649682, + "grad_norm": 0.9091736946261958, + "learning_rate": 4.08997955010225e-06, + "loss": 1.3587, + "step": 100 + }, + { + "epoch": 0.0062003130851161796, + "grad_norm": 1.036778815077969, + "learning_rate": 4.130879345603273e-06, + "loss": 1.4177, + "step": 101 + }, + { + "epoch": 0.006261702323582676, + "grad_norm": 0.9289271878174319, + "learning_rate": 4.171779141104294e-06, + "loss": 1.3508, + "step": 102 + }, + { + "epoch": 0.006323091562049173, + "grad_norm": 0.9604407703189597, + "learning_rate": 4.212678936605317e-06, + "loss": 1.3867, + "step": 103 + }, + { + "epoch": 0.00638448080051567, + "grad_norm": 0.9211020060737071, + "learning_rate": 4.25357873210634e-06, + "loss": 1.2711, + "step": 104 + }, + { + "epoch": 0.006445870038982167, + "grad_norm": 0.9019200851503366, + "learning_rate": 4.294478527607362e-06, + "loss": 1.3382, + "step": 105 + }, + { + "epoch": 0.0065072592774486635, + "grad_norm": 0.9132752102701412, + "learning_rate": 4.335378323108385e-06, + "loss": 1.3131, + "step": 106 + }, + { + "epoch": 0.00656864851591516, + "grad_norm": 0.8928423693200058, + "learning_rate": 4.3762781186094076e-06, + "loss": 1.3776, + "step": 107 + }, + { + "epoch": 0.006630037754381657, + "grad_norm": 0.9381955249323793, + "learning_rate": 4.41717791411043e-06, + "loss": 1.4203, + "step": 108 + }, + { + "epoch": 0.006691426992848154, + "grad_norm": 0.9018663175836714, + "learning_rate": 4.458077709611453e-06, + "loss": 1.2718, + "step": 109 + }, + { + "epoch": 0.006752816231314651, + "grad_norm": 0.9044812919187765, + "learning_rate": 4.498977505112475e-06, + "loss": 1.3009, + "step": 110 + }, + { + "epoch": 0.006814205469781147, + "grad_norm": 0.8949443209654904, + "learning_rate": 4.539877300613497e-06, + "loss": 1.2834, + "step": 111 + }, + { + "epoch": 0.006875594708247644, + "grad_norm": 0.9274769267446017, + "learning_rate": 4.58077709611452e-06, + "loss": 1.3221, + "step": 112 + }, + { + "epoch": 0.006936983946714141, + "grad_norm": 0.937587977946187, + "learning_rate": 4.6216768916155425e-06, + "loss": 1.3273, + "step": 113 + }, + { + "epoch": 0.006998373185180638, + "grad_norm": 0.9627959200030355, + "learning_rate": 4.662576687116564e-06, + "loss": 1.295, + "step": 114 + }, + { + "epoch": 0.0070597624236471345, + "grad_norm": 0.8986753139895682, + "learning_rate": 4.703476482617587e-06, + "loss": 1.3132, + "step": 115 + }, + { + "epoch": 0.007121151662113631, + "grad_norm": 0.9270067726244529, + "learning_rate": 4.7443762781186096e-06, + "loss": 1.3358, + "step": 116 + }, + { + "epoch": 0.007182540900580128, + "grad_norm": 0.9128336173056443, + "learning_rate": 4.785276073619632e-06, + "loss": 1.3547, + "step": 117 + }, + { + "epoch": 0.007243930139046625, + "grad_norm": 0.900156835000954, + "learning_rate": 4.826175869120655e-06, + "loss": 1.2843, + "step": 118 + }, + { + "epoch": 0.007305319377513122, + "grad_norm": 0.9082996451148456, + "learning_rate": 4.8670756646216775e-06, + "loss": 1.2634, + "step": 119 + }, + { + "epoch": 0.0073667086159796185, + "grad_norm": 0.9211211774221046, + "learning_rate": 4.9079754601227e-06, + "loss": 1.3289, + "step": 120 + }, + { + "epoch": 0.007428097854446115, + "grad_norm": 0.8890271381321616, + "learning_rate": 4.948875255623723e-06, + "loss": 1.2788, + "step": 121 + }, + { + "epoch": 0.007489487092912612, + "grad_norm": 0.8561358990839021, + "learning_rate": 4.989775051124745e-06, + "loss": 1.2819, + "step": 122 + }, + { + "epoch": 0.007550876331379109, + "grad_norm": 0.8683597147918308, + "learning_rate": 5.030674846625767e-06, + "loss": 1.2832, + "step": 123 + }, + { + "epoch": 0.0076122655698456065, + "grad_norm": 0.9230599813848475, + "learning_rate": 5.07157464212679e-06, + "loss": 1.2767, + "step": 124 + }, + { + "epoch": 0.007673654808312103, + "grad_norm": 0.8992074648819915, + "learning_rate": 5.1124744376278124e-06, + "loss": 1.3186, + "step": 125 + }, + { + "epoch": 0.0077350440467786, + "grad_norm": 0.9143850170541834, + "learning_rate": 5.153374233128835e-06, + "loss": 1.3408, + "step": 126 + }, + { + "epoch": 0.007796433285245097, + "grad_norm": 0.9219411689305363, + "learning_rate": 5.194274028629858e-06, + "loss": 1.3444, + "step": 127 + }, + { + "epoch": 0.007857822523711594, + "grad_norm": 0.9178710519098933, + "learning_rate": 5.23517382413088e-06, + "loss": 1.3489, + "step": 128 + }, + { + "epoch": 0.00791921176217809, + "grad_norm": 0.9476556257513215, + "learning_rate": 5.276073619631902e-06, + "loss": 1.3883, + "step": 129 + }, + { + "epoch": 0.007980601000644587, + "grad_norm": 0.8950014107893959, + "learning_rate": 5.316973415132925e-06, + "loss": 1.3154, + "step": 130 + }, + { + "epoch": 0.008041990239111084, + "grad_norm": 0.9600269216258779, + "learning_rate": 5.357873210633947e-06, + "loss": 1.3302, + "step": 131 + }, + { + "epoch": 0.00810337947757758, + "grad_norm": 0.8859819667839484, + "learning_rate": 5.39877300613497e-06, + "loss": 1.2865, + "step": 132 + }, + { + "epoch": 0.008164768716044078, + "grad_norm": 0.8936358940609402, + "learning_rate": 5.439672801635993e-06, + "loss": 1.2896, + "step": 133 + }, + { + "epoch": 0.008226157954510574, + "grad_norm": 0.9202089938383244, + "learning_rate": 5.480572597137015e-06, + "loss": 1.2697, + "step": 134 + }, + { + "epoch": 0.008287547192977071, + "grad_norm": 0.8744396527413383, + "learning_rate": 5.521472392638038e-06, + "loss": 1.2504, + "step": 135 + }, + { + "epoch": 0.008348936431443568, + "grad_norm": 0.9113140365787075, + "learning_rate": 5.562372188139061e-06, + "loss": 1.296, + "step": 136 + }, + { + "epoch": 0.008410325669910065, + "grad_norm": 0.8821807497511048, + "learning_rate": 5.6032719836400815e-06, + "loss": 1.2798, + "step": 137 + }, + { + "epoch": 0.008471714908376561, + "grad_norm": 0.9098566796035605, + "learning_rate": 5.644171779141104e-06, + "loss": 1.33, + "step": 138 + }, + { + "epoch": 0.008533104146843058, + "grad_norm": 0.9193833002569138, + "learning_rate": 5.685071574642127e-06, + "loss": 1.3586, + "step": 139 + }, + { + "epoch": 0.008594493385309555, + "grad_norm": 0.965682496753043, + "learning_rate": 5.7259713701431494e-06, + "loss": 1.3763, + "step": 140 + }, + { + "epoch": 0.008655882623776052, + "grad_norm": 0.9272414234055115, + "learning_rate": 5.766871165644172e-06, + "loss": 1.2549, + "step": 141 + }, + { + "epoch": 0.008717271862242549, + "grad_norm": 0.9523711322795424, + "learning_rate": 5.807770961145195e-06, + "loss": 1.2807, + "step": 142 + }, + { + "epoch": 0.008778661100709045, + "grad_norm": 0.9470341935499339, + "learning_rate": 5.848670756646217e-06, + "loss": 1.2618, + "step": 143 + }, + { + "epoch": 0.008840050339175542, + "grad_norm": 0.9199109048895818, + "learning_rate": 5.88957055214724e-06, + "loss": 1.2642, + "step": 144 + }, + { + "epoch": 0.008901439577642039, + "grad_norm": 0.9181492413979947, + "learning_rate": 5.930470347648263e-06, + "loss": 1.298, + "step": 145 + }, + { + "epoch": 0.008962828816108536, + "grad_norm": 1.0023545733944235, + "learning_rate": 5.971370143149284e-06, + "loss": 1.3352, + "step": 146 + }, + { + "epoch": 0.009024218054575033, + "grad_norm": 0.9172735742063141, + "learning_rate": 6.012269938650307e-06, + "loss": 1.2631, + "step": 147 + }, + { + "epoch": 0.00908560729304153, + "grad_norm": 0.9054565868180573, + "learning_rate": 6.05316973415133e-06, + "loss": 1.2877, + "step": 148 + }, + { + "epoch": 0.009146996531508026, + "grad_norm": 0.9726695900689754, + "learning_rate": 6.094069529652352e-06, + "loss": 1.2943, + "step": 149 + }, + { + "epoch": 0.009208385769974523, + "grad_norm": 0.9068177536373844, + "learning_rate": 6.134969325153375e-06, + "loss": 1.3316, + "step": 150 + }, + { + "epoch": 0.00926977500844102, + "grad_norm": 0.9601322977515468, + "learning_rate": 6.1758691206543976e-06, + "loss": 1.3029, + "step": 151 + }, + { + "epoch": 0.009331164246907516, + "grad_norm": 0.8833579242803341, + "learning_rate": 6.21676891615542e-06, + "loss": 1.2964, + "step": 152 + }, + { + "epoch": 0.009392553485374013, + "grad_norm": 0.8678477814034519, + "learning_rate": 6.257668711656443e-06, + "loss": 1.2425, + "step": 153 + }, + { + "epoch": 0.00945394272384051, + "grad_norm": 0.9390663897559126, + "learning_rate": 6.298568507157465e-06, + "loss": 1.3244, + "step": 154 + }, + { + "epoch": 0.009515331962307007, + "grad_norm": 0.8688516344702104, + "learning_rate": 6.339468302658487e-06, + "loss": 1.2431, + "step": 155 + }, + { + "epoch": 0.009576721200773504, + "grad_norm": 0.9075196241429163, + "learning_rate": 6.38036809815951e-06, + "loss": 1.2885, + "step": 156 + }, + { + "epoch": 0.009638110439240002, + "grad_norm": 0.9338950888556943, + "learning_rate": 6.4212678936605325e-06, + "loss": 1.3004, + "step": 157 + }, + { + "epoch": 0.009699499677706499, + "grad_norm": 0.9030273270700654, + "learning_rate": 6.462167689161555e-06, + "loss": 1.2568, + "step": 158 + }, + { + "epoch": 0.009760888916172996, + "grad_norm": 0.8980856370608238, + "learning_rate": 6.503067484662578e-06, + "loss": 1.2963, + "step": 159 + }, + { + "epoch": 0.009822278154639492, + "grad_norm": 0.8974008102682139, + "learning_rate": 6.5439672801636004e-06, + "loss": 1.2658, + "step": 160 + }, + { + "epoch": 0.00988366739310599, + "grad_norm": 0.9038974497959962, + "learning_rate": 6.584867075664623e-06, + "loss": 1.2763, + "step": 161 + }, + { + "epoch": 0.009945056631572486, + "grad_norm": 0.8966563549294199, + "learning_rate": 6.625766871165644e-06, + "loss": 1.2469, + "step": 162 + }, + { + "epoch": 0.010006445870038983, + "grad_norm": 0.9846325727694345, + "learning_rate": 6.666666666666667e-06, + "loss": 1.2996, + "step": 163 + }, + { + "epoch": 0.01006783510850548, + "grad_norm": 0.9727600148980952, + "learning_rate": 6.707566462167689e-06, + "loss": 1.3066, + "step": 164 + }, + { + "epoch": 0.010129224346971976, + "grad_norm": 0.9454969490716599, + "learning_rate": 6.748466257668712e-06, + "loss": 1.2878, + "step": 165 + }, + { + "epoch": 0.010190613585438473, + "grad_norm": 0.902773734228336, + "learning_rate": 6.7893660531697346e-06, + "loss": 1.2042, + "step": 166 + }, + { + "epoch": 0.01025200282390497, + "grad_norm": 0.8959704798199241, + "learning_rate": 6.830265848670757e-06, + "loss": 1.2209, + "step": 167 + }, + { + "epoch": 0.010313392062371467, + "grad_norm": 0.9492833272460209, + "learning_rate": 6.87116564417178e-06, + "loss": 1.3159, + "step": 168 + }, + { + "epoch": 0.010374781300837964, + "grad_norm": 0.8636604915335748, + "learning_rate": 6.9120654396728025e-06, + "loss": 1.2297, + "step": 169 + }, + { + "epoch": 0.01043617053930446, + "grad_norm": 0.8792858851541455, + "learning_rate": 6.952965235173824e-06, + "loss": 1.2345, + "step": 170 + }, + { + "epoch": 0.010497559777770957, + "grad_norm": 0.8811876190566337, + "learning_rate": 6.993865030674847e-06, + "loss": 1.2591, + "step": 171 + }, + { + "epoch": 0.010558949016237454, + "grad_norm": 0.8880059649097714, + "learning_rate": 7.0347648261758695e-06, + "loss": 1.2361, + "step": 172 + }, + { + "epoch": 0.01062033825470395, + "grad_norm": 0.9703485407577527, + "learning_rate": 7.075664621676892e-06, + "loss": 1.3157, + "step": 173 + }, + { + "epoch": 0.010681727493170447, + "grad_norm": 0.863691959842333, + "learning_rate": 7.116564417177915e-06, + "loss": 1.1742, + "step": 174 + }, + { + "epoch": 0.010743116731636944, + "grad_norm": 0.8772561919250402, + "learning_rate": 7.157464212678937e-06, + "loss": 1.2703, + "step": 175 + }, + { + "epoch": 0.010804505970103441, + "grad_norm": 0.8902282794257211, + "learning_rate": 7.19836400817996e-06, + "loss": 1.2279, + "step": 176 + }, + { + "epoch": 0.010865895208569938, + "grad_norm": 0.8255348317914312, + "learning_rate": 7.239263803680983e-06, + "loss": 1.2032, + "step": 177 + }, + { + "epoch": 0.010927284447036435, + "grad_norm": 0.8655986373759768, + "learning_rate": 7.280163599182005e-06, + "loss": 1.2429, + "step": 178 + }, + { + "epoch": 0.010988673685502931, + "grad_norm": 0.9163616226028534, + "learning_rate": 7.321063394683027e-06, + "loss": 1.2501, + "step": 179 + }, + { + "epoch": 0.011050062923969428, + "grad_norm": 0.9388189634167472, + "learning_rate": 7.36196319018405e-06, + "loss": 1.3244, + "step": 180 + }, + { + "epoch": 0.011111452162435925, + "grad_norm": 0.9090625627207395, + "learning_rate": 7.402862985685072e-06, + "loss": 1.2691, + "step": 181 + }, + { + "epoch": 0.011172841400902422, + "grad_norm": 0.8904395929951838, + "learning_rate": 7.443762781186095e-06, + "loss": 1.261, + "step": 182 + }, + { + "epoch": 0.011234230639368918, + "grad_norm": 0.8486868606653925, + "learning_rate": 7.484662576687118e-06, + "loss": 1.2141, + "step": 183 + }, + { + "epoch": 0.011295619877835415, + "grad_norm": 0.8948808182560015, + "learning_rate": 7.52556237218814e-06, + "loss": 1.2577, + "step": 184 + }, + { + "epoch": 0.011357009116301912, + "grad_norm": 0.9360825770750187, + "learning_rate": 7.566462167689163e-06, + "loss": 1.3503, + "step": 185 + }, + { + "epoch": 0.011418398354768409, + "grad_norm": 0.8872891758397956, + "learning_rate": 7.6073619631901856e-06, + "loss": 1.2544, + "step": 186 + }, + { + "epoch": 0.011479787593234906, + "grad_norm": 0.9318179579325592, + "learning_rate": 7.648261758691207e-06, + "loss": 1.2633, + "step": 187 + }, + { + "epoch": 0.011541176831701402, + "grad_norm": 0.9396032303982791, + "learning_rate": 7.68916155419223e-06, + "loss": 1.385, + "step": 188 + }, + { + "epoch": 0.0116025660701679, + "grad_norm": 0.8855494288576685, + "learning_rate": 7.730061349693252e-06, + "loss": 1.3073, + "step": 189 + }, + { + "epoch": 0.011663955308634396, + "grad_norm": 0.8981367369414004, + "learning_rate": 7.770961145194275e-06, + "loss": 1.2807, + "step": 190 + }, + { + "epoch": 0.011725344547100893, + "grad_norm": 0.857773026649229, + "learning_rate": 7.811860940695297e-06, + "loss": 1.2526, + "step": 191 + }, + { + "epoch": 0.01178673378556739, + "grad_norm": 0.9885937388090081, + "learning_rate": 7.85276073619632e-06, + "loss": 1.2942, + "step": 192 + }, + { + "epoch": 0.011848123024033886, + "grad_norm": 0.9356016666858499, + "learning_rate": 7.893660531697342e-06, + "loss": 1.2712, + "step": 193 + }, + { + "epoch": 0.011909512262500383, + "grad_norm": 0.8936203603861913, + "learning_rate": 7.934560327198366e-06, + "loss": 1.1965, + "step": 194 + }, + { + "epoch": 0.01197090150096688, + "grad_norm": 0.8763376979175331, + "learning_rate": 7.975460122699386e-06, + "loss": 1.1691, + "step": 195 + }, + { + "epoch": 0.012032290739433377, + "grad_norm": 1.0004836806199355, + "learning_rate": 8.01635991820041e-06, + "loss": 1.3284, + "step": 196 + }, + { + "epoch": 0.012093679977899873, + "grad_norm": 0.9508868824674875, + "learning_rate": 8.057259713701431e-06, + "loss": 1.2386, + "step": 197 + }, + { + "epoch": 0.01215506921636637, + "grad_norm": 0.936486486183284, + "learning_rate": 8.098159509202455e-06, + "loss": 1.2129, + "step": 198 + }, + { + "epoch": 0.012216458454832867, + "grad_norm": 0.8974132797370455, + "learning_rate": 8.139059304703476e-06, + "loss": 1.3184, + "step": 199 + }, + { + "epoch": 0.012277847693299364, + "grad_norm": 0.8882097835097548, + "learning_rate": 8.1799591002045e-06, + "loss": 1.2414, + "step": 200 + }, + { + "epoch": 0.01233923693176586, + "grad_norm": 0.8121652361742757, + "learning_rate": 8.220858895705522e-06, + "loss": 1.1955, + "step": 201 + }, + { + "epoch": 0.012400626170232359, + "grad_norm": 0.9209965225415554, + "learning_rate": 8.261758691206545e-06, + "loss": 1.2604, + "step": 202 + }, + { + "epoch": 0.012462015408698856, + "grad_norm": 0.9101558576208457, + "learning_rate": 8.302658486707567e-06, + "loss": 1.2682, + "step": 203 + }, + { + "epoch": 0.012523404647165353, + "grad_norm": 0.9245098785530109, + "learning_rate": 8.343558282208589e-06, + "loss": 1.2433, + "step": 204 + }, + { + "epoch": 0.01258479388563185, + "grad_norm": 0.8709644052921381, + "learning_rate": 8.384458077709612e-06, + "loss": 1.2523, + "step": 205 + }, + { + "epoch": 0.012646183124098346, + "grad_norm": 0.9235882250331198, + "learning_rate": 8.425357873210634e-06, + "loss": 1.2466, + "step": 206 + }, + { + "epoch": 0.012707572362564843, + "grad_norm": 0.9151927765343967, + "learning_rate": 8.466257668711658e-06, + "loss": 1.2569, + "step": 207 + }, + { + "epoch": 0.01276896160103134, + "grad_norm": 0.9317121626769984, + "learning_rate": 8.50715746421268e-06, + "loss": 1.2775, + "step": 208 + }, + { + "epoch": 0.012830350839497837, + "grad_norm": 0.8932411598195014, + "learning_rate": 8.548057259713703e-06, + "loss": 1.2363, + "step": 209 + }, + { + "epoch": 0.012891740077964333, + "grad_norm": 0.8826815207502858, + "learning_rate": 8.588957055214725e-06, + "loss": 1.2478, + "step": 210 + }, + { + "epoch": 0.01295312931643083, + "grad_norm": 0.9141157091802387, + "learning_rate": 8.629856850715748e-06, + "loss": 1.1909, + "step": 211 + }, + { + "epoch": 0.013014518554897327, + "grad_norm": 0.9460799227638723, + "learning_rate": 8.67075664621677e-06, + "loss": 1.2639, + "step": 212 + }, + { + "epoch": 0.013075907793363824, + "grad_norm": 0.9357147394013448, + "learning_rate": 8.711656441717792e-06, + "loss": 1.2073, + "step": 213 + }, + { + "epoch": 0.01313729703183032, + "grad_norm": 1.353422872602618, + "learning_rate": 8.752556237218815e-06, + "loss": 0.8287, + "step": 214 + }, + { + "epoch": 0.013198686270296817, + "grad_norm": 0.8747892092960756, + "learning_rate": 8.793456032719837e-06, + "loss": 1.2258, + "step": 215 + }, + { + "epoch": 0.013260075508763314, + "grad_norm": 0.8884398919791618, + "learning_rate": 8.83435582822086e-06, + "loss": 1.2302, + "step": 216 + }, + { + "epoch": 0.013321464747229811, + "grad_norm": 0.8449276666995246, + "learning_rate": 8.875255623721882e-06, + "loss": 1.1287, + "step": 217 + }, + { + "epoch": 0.013382853985696308, + "grad_norm": 0.9177524608170432, + "learning_rate": 8.916155419222906e-06, + "loss": 1.2256, + "step": 218 + }, + { + "epoch": 0.013444243224162804, + "grad_norm": 0.9294659376563408, + "learning_rate": 8.957055214723927e-06, + "loss": 1.2215, + "step": 219 + }, + { + "epoch": 0.013505632462629301, + "grad_norm": 0.8699498066404835, + "learning_rate": 8.99795501022495e-06, + "loss": 1.2693, + "step": 220 + }, + { + "epoch": 0.013567021701095798, + "grad_norm": 0.9269998743357923, + "learning_rate": 9.038854805725971e-06, + "loss": 1.2651, + "step": 221 + }, + { + "epoch": 0.013628410939562295, + "grad_norm": 0.9034515701168728, + "learning_rate": 9.079754601226994e-06, + "loss": 1.265, + "step": 222 + }, + { + "epoch": 0.013689800178028792, + "grad_norm": 0.8503384224219481, + "learning_rate": 9.120654396728016e-06, + "loss": 1.2645, + "step": 223 + }, + { + "epoch": 0.013751189416495288, + "grad_norm": 0.8465846045183726, + "learning_rate": 9.16155419222904e-06, + "loss": 1.1953, + "step": 224 + }, + { + "epoch": 0.013812578654961785, + "grad_norm": 0.9023240815720838, + "learning_rate": 9.202453987730062e-06, + "loss": 1.2335, + "step": 225 + }, + { + "epoch": 0.013873967893428282, + "grad_norm": 0.9526578053342919, + "learning_rate": 9.243353783231085e-06, + "loss": 1.2614, + "step": 226 + }, + { + "epoch": 0.013935357131894779, + "grad_norm": 0.8998090085389139, + "learning_rate": 9.284253578732107e-06, + "loss": 1.2002, + "step": 227 + }, + { + "epoch": 0.013996746370361276, + "grad_norm": 0.8686910613385985, + "learning_rate": 9.325153374233129e-06, + "loss": 1.1845, + "step": 228 + }, + { + "epoch": 0.014058135608827772, + "grad_norm": 0.970587452754685, + "learning_rate": 9.366053169734152e-06, + "loss": 1.2627, + "step": 229 + }, + { + "epoch": 0.014119524847294269, + "grad_norm": 0.8988839653579763, + "learning_rate": 9.406952965235174e-06, + "loss": 1.2673, + "step": 230 + }, + { + "epoch": 0.014180914085760766, + "grad_norm": 0.8062676672890478, + "learning_rate": 9.447852760736197e-06, + "loss": 1.2094, + "step": 231 + }, + { + "epoch": 0.014242303324227263, + "grad_norm": 0.8388172834661318, + "learning_rate": 9.488752556237219e-06, + "loss": 1.1993, + "step": 232 + }, + { + "epoch": 0.01430369256269376, + "grad_norm": 0.8733832050235577, + "learning_rate": 9.529652351738243e-06, + "loss": 1.2207, + "step": 233 + }, + { + "epoch": 0.014365081801160256, + "grad_norm": 0.874952551594984, + "learning_rate": 9.570552147239264e-06, + "loss": 1.2138, + "step": 234 + }, + { + "epoch": 0.014426471039626753, + "grad_norm": 0.8445276012472485, + "learning_rate": 9.611451942740288e-06, + "loss": 1.1832, + "step": 235 + }, + { + "epoch": 0.01448786027809325, + "grad_norm": 0.918600890799935, + "learning_rate": 9.65235173824131e-06, + "loss": 1.2596, + "step": 236 + }, + { + "epoch": 0.014549249516559747, + "grad_norm": 0.8791499632343465, + "learning_rate": 9.693251533742331e-06, + "loss": 1.239, + "step": 237 + }, + { + "epoch": 0.014610638755026243, + "grad_norm": 0.8931984974433442, + "learning_rate": 9.734151329243355e-06, + "loss": 1.2335, + "step": 238 + }, + { + "epoch": 0.01467202799349274, + "grad_norm": 0.9427783770086312, + "learning_rate": 9.775051124744377e-06, + "loss": 1.2355, + "step": 239 + }, + { + "epoch": 0.014733417231959237, + "grad_norm": 0.8541402043705444, + "learning_rate": 9.8159509202454e-06, + "loss": 1.2341, + "step": 240 + }, + { + "epoch": 0.014794806470425734, + "grad_norm": 0.897371063040283, + "learning_rate": 9.856850715746422e-06, + "loss": 1.2694, + "step": 241 + }, + { + "epoch": 0.01485619570889223, + "grad_norm": 0.9411009053605871, + "learning_rate": 9.897750511247446e-06, + "loss": 1.235, + "step": 242 + }, + { + "epoch": 0.014917584947358727, + "grad_norm": 0.8408186302454851, + "learning_rate": 9.938650306748467e-06, + "loss": 1.1796, + "step": 243 + }, + { + "epoch": 0.014978974185825224, + "grad_norm": 0.920276063873812, + "learning_rate": 9.97955010224949e-06, + "loss": 1.212, + "step": 244 + }, + { + "epoch": 0.01504036342429172, + "grad_norm": 0.9466011803822727, + "learning_rate": 1.0020449897750513e-05, + "loss": 1.2667, + "step": 245 + }, + { + "epoch": 0.015101752662758218, + "grad_norm": 0.9220814681559567, + "learning_rate": 1.0061349693251534e-05, + "loss": 1.2734, + "step": 246 + }, + { + "epoch": 0.015163141901224716, + "grad_norm": 0.894837202840137, + "learning_rate": 1.0102249488752558e-05, + "loss": 1.2844, + "step": 247 + }, + { + "epoch": 0.015224531139691213, + "grad_norm": 0.9155178228132693, + "learning_rate": 1.014314928425358e-05, + "loss": 1.2481, + "step": 248 + }, + { + "epoch": 0.01528592037815771, + "grad_norm": 0.8944111659887758, + "learning_rate": 1.0184049079754601e-05, + "loss": 1.2085, + "step": 249 + }, + { + "epoch": 0.015347309616624207, + "grad_norm": 0.8609865071776917, + "learning_rate": 1.0224948875255625e-05, + "loss": 1.2359, + "step": 250 + }, + { + "epoch": 0.015408698855090703, + "grad_norm": 0.9056144887186771, + "learning_rate": 1.0265848670756647e-05, + "loss": 1.2935, + "step": 251 + }, + { + "epoch": 0.0154700880935572, + "grad_norm": 0.940474388247613, + "learning_rate": 1.030674846625767e-05, + "loss": 1.3087, + "step": 252 + }, + { + "epoch": 0.015531477332023697, + "grad_norm": 0.8855615263080374, + "learning_rate": 1.0347648261758692e-05, + "loss": 1.2256, + "step": 253 + }, + { + "epoch": 0.015592866570490194, + "grad_norm": 0.8849558016034238, + "learning_rate": 1.0388548057259715e-05, + "loss": 1.1653, + "step": 254 + }, + { + "epoch": 0.01565425580895669, + "grad_norm": 0.8601167960169848, + "learning_rate": 1.0429447852760737e-05, + "loss": 1.2618, + "step": 255 + }, + { + "epoch": 0.015715645047423187, + "grad_norm": 0.8886227336896101, + "learning_rate": 1.047034764826176e-05, + "loss": 1.2446, + "step": 256 + }, + { + "epoch": 0.015777034285889682, + "grad_norm": 0.8319043765206774, + "learning_rate": 1.0511247443762782e-05, + "loss": 1.1959, + "step": 257 + }, + { + "epoch": 0.01583842352435618, + "grad_norm": 0.9050375133322529, + "learning_rate": 1.0552147239263804e-05, + "loss": 1.2499, + "step": 258 + }, + { + "epoch": 0.015899812762822676, + "grad_norm": 0.8687657819158461, + "learning_rate": 1.0593047034764828e-05, + "loss": 1.2225, + "step": 259 + }, + { + "epoch": 0.015961202001289174, + "grad_norm": 0.9147963612785399, + "learning_rate": 1.063394683026585e-05, + "loss": 1.3208, + "step": 260 + }, + { + "epoch": 0.01602259123975567, + "grad_norm": 0.8621046269953997, + "learning_rate": 1.0674846625766873e-05, + "loss": 1.1804, + "step": 261 + }, + { + "epoch": 0.016083980478222168, + "grad_norm": 0.8406150442371855, + "learning_rate": 1.0715746421267895e-05, + "loss": 1.2084, + "step": 262 + }, + { + "epoch": 0.016145369716688663, + "grad_norm": 0.9039460075622624, + "learning_rate": 1.0756646216768918e-05, + "loss": 1.2183, + "step": 263 + }, + { + "epoch": 0.01620675895515516, + "grad_norm": 0.869689663421716, + "learning_rate": 1.079754601226994e-05, + "loss": 1.2206, + "step": 264 + }, + { + "epoch": 0.016268148193621657, + "grad_norm": 0.9424684952723243, + "learning_rate": 1.0838445807770964e-05, + "loss": 1.2067, + "step": 265 + }, + { + "epoch": 0.016329537432088155, + "grad_norm": 0.8245668361011314, + "learning_rate": 1.0879345603271985e-05, + "loss": 1.1432, + "step": 266 + }, + { + "epoch": 0.01639092667055465, + "grad_norm": 0.8343656994292982, + "learning_rate": 1.0920245398773005e-05, + "loss": 1.2191, + "step": 267 + }, + { + "epoch": 0.01645231590902115, + "grad_norm": 0.8705599969736126, + "learning_rate": 1.096114519427403e-05, + "loss": 1.2274, + "step": 268 + }, + { + "epoch": 0.016513705147487647, + "grad_norm": 0.9404281115762353, + "learning_rate": 1.100204498977505e-05, + "loss": 1.3076, + "step": 269 + }, + { + "epoch": 0.016575094385954142, + "grad_norm": 0.9017813602393329, + "learning_rate": 1.1042944785276076e-05, + "loss": 1.2261, + "step": 270 + }, + { + "epoch": 0.01663648362442064, + "grad_norm": 0.9174718832089009, + "learning_rate": 1.1083844580777096e-05, + "loss": 1.212, + "step": 271 + }, + { + "epoch": 0.016697872862887136, + "grad_norm": 0.8767515281361006, + "learning_rate": 1.1124744376278121e-05, + "loss": 1.2326, + "step": 272 + }, + { + "epoch": 0.016759262101353634, + "grad_norm": 0.831719367941329, + "learning_rate": 1.1165644171779141e-05, + "loss": 1.1528, + "step": 273 + }, + { + "epoch": 0.01682065133982013, + "grad_norm": 0.8924988882215402, + "learning_rate": 1.1206543967280163e-05, + "loss": 1.2776, + "step": 274 + }, + { + "epoch": 0.016882040578286628, + "grad_norm": 0.8358171208439977, + "learning_rate": 1.1247443762781187e-05, + "loss": 1.1941, + "step": 275 + }, + { + "epoch": 0.016943429816753123, + "grad_norm": 0.8620610106751827, + "learning_rate": 1.1288343558282208e-05, + "loss": 1.2482, + "step": 276 + }, + { + "epoch": 0.01700481905521962, + "grad_norm": 0.8898586029900778, + "learning_rate": 1.1329243353783232e-05, + "loss": 1.2135, + "step": 277 + }, + { + "epoch": 0.017066208293686116, + "grad_norm": 0.8587422936229843, + "learning_rate": 1.1370143149284254e-05, + "loss": 1.2398, + "step": 278 + }, + { + "epoch": 0.017127597532152615, + "grad_norm": 0.9070155644616447, + "learning_rate": 1.1411042944785277e-05, + "loss": 1.2224, + "step": 279 + }, + { + "epoch": 0.01718898677061911, + "grad_norm": 0.8494583427131507, + "learning_rate": 1.1451942740286299e-05, + "loss": 1.2382, + "step": 280 + }, + { + "epoch": 0.01725037600908561, + "grad_norm": 0.8228500792639477, + "learning_rate": 1.1492842535787322e-05, + "loss": 1.1488, + "step": 281 + }, + { + "epoch": 0.017311765247552104, + "grad_norm": 0.8720139555861608, + "learning_rate": 1.1533742331288344e-05, + "loss": 1.2098, + "step": 282 + }, + { + "epoch": 0.017373154486018602, + "grad_norm": 0.9517942093298918, + "learning_rate": 1.1574642126789366e-05, + "loss": 1.2324, + "step": 283 + }, + { + "epoch": 0.017434543724485097, + "grad_norm": 0.9032252331654993, + "learning_rate": 1.161554192229039e-05, + "loss": 1.2321, + "step": 284 + }, + { + "epoch": 0.017495932962951596, + "grad_norm": 0.8486068095885002, + "learning_rate": 1.1656441717791411e-05, + "loss": 1.284, + "step": 285 + }, + { + "epoch": 0.01755732220141809, + "grad_norm": 0.8480521731405525, + "learning_rate": 1.1697341513292435e-05, + "loss": 1.2346, + "step": 286 + }, + { + "epoch": 0.01761871143988459, + "grad_norm": 0.8765195646993937, + "learning_rate": 1.1738241308793456e-05, + "loss": 1.2437, + "step": 287 + }, + { + "epoch": 0.017680100678351084, + "grad_norm": 0.8409558558951864, + "learning_rate": 1.177914110429448e-05, + "loss": 1.1643, + "step": 288 + }, + { + "epoch": 0.017741489916817583, + "grad_norm": 0.9294002303958651, + "learning_rate": 1.1820040899795502e-05, + "loss": 1.2143, + "step": 289 + }, + { + "epoch": 0.017802879155284078, + "grad_norm": 0.8778896032163639, + "learning_rate": 1.1860940695296525e-05, + "loss": 1.2536, + "step": 290 + }, + { + "epoch": 0.017864268393750576, + "grad_norm": 0.8513093611780121, + "learning_rate": 1.1901840490797547e-05, + "loss": 1.1462, + "step": 291 + }, + { + "epoch": 0.01792565763221707, + "grad_norm": 0.8604064233545102, + "learning_rate": 1.1942740286298569e-05, + "loss": 1.248, + "step": 292 + }, + { + "epoch": 0.01798704687068357, + "grad_norm": 0.9017163611977864, + "learning_rate": 1.1983640081799592e-05, + "loss": 1.2149, + "step": 293 + }, + { + "epoch": 0.018048436109150065, + "grad_norm": 0.8230898774484232, + "learning_rate": 1.2024539877300614e-05, + "loss": 1.183, + "step": 294 + }, + { + "epoch": 0.018109825347616564, + "grad_norm": 0.8128401673011836, + "learning_rate": 1.2065439672801638e-05, + "loss": 1.2038, + "step": 295 + }, + { + "epoch": 0.01817121458608306, + "grad_norm": 0.9104437509012364, + "learning_rate": 1.210633946830266e-05, + "loss": 1.2495, + "step": 296 + }, + { + "epoch": 0.018232603824549557, + "grad_norm": 0.8731653118774719, + "learning_rate": 1.2147239263803683e-05, + "loss": 1.2358, + "step": 297 + }, + { + "epoch": 0.018293993063016052, + "grad_norm": 0.8467863429796066, + "learning_rate": 1.2188139059304705e-05, + "loss": 1.1727, + "step": 298 + }, + { + "epoch": 0.01835538230148255, + "grad_norm": 0.891847816920403, + "learning_rate": 1.2229038854805726e-05, + "loss": 1.2367, + "step": 299 + }, + { + "epoch": 0.018416771539949046, + "grad_norm": 0.8138250671729387, + "learning_rate": 1.226993865030675e-05, + "loss": 1.1553, + "step": 300 + }, + { + "epoch": 0.018478160778415544, + "grad_norm": 0.797391442870826, + "learning_rate": 1.2310838445807772e-05, + "loss": 1.1434, + "step": 301 + }, + { + "epoch": 0.01853955001688204, + "grad_norm": 0.8681815390417232, + "learning_rate": 1.2351738241308795e-05, + "loss": 1.3009, + "step": 302 + }, + { + "epoch": 0.018600939255348538, + "grad_norm": 0.8730224416563475, + "learning_rate": 1.2392638036809817e-05, + "loss": 1.2798, + "step": 303 + }, + { + "epoch": 0.018662328493815033, + "grad_norm": 0.815170397513993, + "learning_rate": 1.243353783231084e-05, + "loss": 1.1532, + "step": 304 + }, + { + "epoch": 0.01872371773228153, + "grad_norm": 0.8368990911976751, + "learning_rate": 1.2474437627811862e-05, + "loss": 1.1778, + "step": 305 + }, + { + "epoch": 0.018785106970748026, + "grad_norm": 0.8750915124517663, + "learning_rate": 1.2515337423312886e-05, + "loss": 1.2007, + "step": 306 + }, + { + "epoch": 0.018846496209214525, + "grad_norm": 0.8812375608841377, + "learning_rate": 1.2556237218813907e-05, + "loss": 1.2495, + "step": 307 + }, + { + "epoch": 0.01890788544768102, + "grad_norm": 0.8162530203943192, + "learning_rate": 1.259713701431493e-05, + "loss": 1.1231, + "step": 308 + }, + { + "epoch": 0.01896927468614752, + "grad_norm": 0.8510052960701708, + "learning_rate": 1.2638036809815953e-05, + "loss": 1.2427, + "step": 309 + }, + { + "epoch": 0.019030663924614014, + "grad_norm": 0.8334382739588359, + "learning_rate": 1.2678936605316975e-05, + "loss": 1.2096, + "step": 310 + }, + { + "epoch": 0.019092053163080512, + "grad_norm": 0.9141204604764559, + "learning_rate": 1.2719836400817998e-05, + "loss": 1.2494, + "step": 311 + }, + { + "epoch": 0.019153442401547007, + "grad_norm": 0.8742906771831217, + "learning_rate": 1.276073619631902e-05, + "loss": 1.209, + "step": 312 + }, + { + "epoch": 0.019214831640013506, + "grad_norm": 0.8284805404098343, + "learning_rate": 1.2801635991820043e-05, + "loss": 1.1875, + "step": 313 + }, + { + "epoch": 0.019276220878480004, + "grad_norm": 0.8841166783784936, + "learning_rate": 1.2842535787321065e-05, + "loss": 1.2182, + "step": 314 + }, + { + "epoch": 0.0193376101169465, + "grad_norm": 0.8468138511776635, + "learning_rate": 1.2883435582822085e-05, + "loss": 1.2157, + "step": 315 + }, + { + "epoch": 0.019398999355412998, + "grad_norm": 0.7791877155196608, + "learning_rate": 1.292433537832311e-05, + "loss": 1.1334, + "step": 316 + }, + { + "epoch": 0.019460388593879493, + "grad_norm": 0.8514987978368462, + "learning_rate": 1.296523517382413e-05, + "loss": 1.1919, + "step": 317 + }, + { + "epoch": 0.01952177783234599, + "grad_norm": 0.8019334077702545, + "learning_rate": 1.3006134969325156e-05, + "loss": 1.119, + "step": 318 + }, + { + "epoch": 0.019583167070812486, + "grad_norm": 0.8133062604033454, + "learning_rate": 1.3047034764826176e-05, + "loss": 1.1485, + "step": 319 + }, + { + "epoch": 0.019644556309278985, + "grad_norm": 0.8960798828297384, + "learning_rate": 1.3087934560327201e-05, + "loss": 1.2891, + "step": 320 + }, + { + "epoch": 0.01970594554774548, + "grad_norm": 0.779624313971041, + "learning_rate": 1.3128834355828221e-05, + "loss": 1.1765, + "step": 321 + }, + { + "epoch": 0.01976733478621198, + "grad_norm": 0.8822680604560392, + "learning_rate": 1.3169734151329246e-05, + "loss": 1.2185, + "step": 322 + }, + { + "epoch": 0.019828724024678474, + "grad_norm": 0.8384201648655251, + "learning_rate": 1.3210633946830266e-05, + "loss": 1.1993, + "step": 323 + }, + { + "epoch": 0.019890113263144972, + "grad_norm": 0.8443913175021177, + "learning_rate": 1.3251533742331288e-05, + "loss": 1.2205, + "step": 324 + }, + { + "epoch": 0.019951502501611467, + "grad_norm": 0.8883750333646179, + "learning_rate": 1.3292433537832312e-05, + "loss": 1.1609, + "step": 325 + }, + { + "epoch": 0.020012891740077966, + "grad_norm": 0.8595477498614564, + "learning_rate": 1.3333333333333333e-05, + "loss": 1.2224, + "step": 326 + }, + { + "epoch": 0.02007428097854446, + "grad_norm": 0.7690140860043272, + "learning_rate": 1.3374233128834357e-05, + "loss": 1.1603, + "step": 327 + }, + { + "epoch": 0.02013567021701096, + "grad_norm": 0.8409877024253466, + "learning_rate": 1.3415132924335379e-05, + "loss": 1.2505, + "step": 328 + }, + { + "epoch": 0.020197059455477454, + "grad_norm": 0.8488158411558923, + "learning_rate": 1.3456032719836402e-05, + "loss": 1.2652, + "step": 329 + }, + { + "epoch": 0.020258448693943953, + "grad_norm": 0.8641348652981327, + "learning_rate": 1.3496932515337424e-05, + "loss": 1.2039, + "step": 330 + }, + { + "epoch": 0.020319837932410448, + "grad_norm": 0.8310800626621245, + "learning_rate": 1.3537832310838447e-05, + "loss": 1.1482, + "step": 331 + }, + { + "epoch": 0.020381227170876946, + "grad_norm": 0.8829024398415868, + "learning_rate": 1.3578732106339469e-05, + "loss": 0.804, + "step": 332 + }, + { + "epoch": 0.02044261640934344, + "grad_norm": 0.9708274135958446, + "learning_rate": 1.3619631901840491e-05, + "loss": 1.2251, + "step": 333 + }, + { + "epoch": 0.02050400564780994, + "grad_norm": 0.839984097536665, + "learning_rate": 1.3660531697341514e-05, + "loss": 1.1857, + "step": 334 + }, + { + "epoch": 0.020565394886276435, + "grad_norm": 0.9050744427511135, + "learning_rate": 1.3701431492842536e-05, + "loss": 1.2254, + "step": 335 + }, + { + "epoch": 0.020626784124742933, + "grad_norm": 0.8424436567728738, + "learning_rate": 1.374233128834356e-05, + "loss": 1.1489, + "step": 336 + }, + { + "epoch": 0.02068817336320943, + "grad_norm": 0.8559675442401181, + "learning_rate": 1.3783231083844581e-05, + "loss": 1.1856, + "step": 337 + }, + { + "epoch": 0.020749562601675927, + "grad_norm": 0.8205714595441423, + "learning_rate": 1.3824130879345605e-05, + "loss": 1.1866, + "step": 338 + }, + { + "epoch": 0.020810951840142422, + "grad_norm": 0.8884183143864305, + "learning_rate": 1.3865030674846627e-05, + "loss": 1.2613, + "step": 339 + }, + { + "epoch": 0.02087234107860892, + "grad_norm": 0.8005256198131441, + "learning_rate": 1.3905930470347648e-05, + "loss": 1.2123, + "step": 340 + }, + { + "epoch": 0.020933730317075416, + "grad_norm": 0.8277993062453084, + "learning_rate": 1.3946830265848672e-05, + "loss": 1.1608, + "step": 341 + }, + { + "epoch": 0.020995119555541914, + "grad_norm": 0.8840646635696525, + "learning_rate": 1.3987730061349694e-05, + "loss": 1.2321, + "step": 342 + }, + { + "epoch": 0.02105650879400841, + "grad_norm": 0.8883261922024139, + "learning_rate": 1.4028629856850717e-05, + "loss": 1.2384, + "step": 343 + }, + { + "epoch": 0.021117898032474908, + "grad_norm": 0.9450617927676062, + "learning_rate": 1.4069529652351739e-05, + "loss": 1.2333, + "step": 344 + }, + { + "epoch": 0.021179287270941403, + "grad_norm": 0.811101621824158, + "learning_rate": 1.4110429447852763e-05, + "loss": 1.2372, + "step": 345 + }, + { + "epoch": 0.0212406765094079, + "grad_norm": 0.85069806520605, + "learning_rate": 1.4151329243353784e-05, + "loss": 1.2133, + "step": 346 + }, + { + "epoch": 0.021302065747874396, + "grad_norm": 0.8494879089521378, + "learning_rate": 1.4192229038854808e-05, + "loss": 1.2199, + "step": 347 + }, + { + "epoch": 0.021363454986340895, + "grad_norm": 0.8353418233536639, + "learning_rate": 1.423312883435583e-05, + "loss": 1.1853, + "step": 348 + }, + { + "epoch": 0.02142484422480739, + "grad_norm": 0.8371018762796191, + "learning_rate": 1.4274028629856851e-05, + "loss": 1.2259, + "step": 349 + }, + { + "epoch": 0.02148623346327389, + "grad_norm": 2.147301154327512, + "learning_rate": 1.4314928425357875e-05, + "loss": 0.8418, + "step": 350 + }, + { + "epoch": 0.021547622701740383, + "grad_norm": 0.8389407656463312, + "learning_rate": 1.4355828220858897e-05, + "loss": 1.1719, + "step": 351 + }, + { + "epoch": 0.021609011940206882, + "grad_norm": 0.8918899642550105, + "learning_rate": 1.439672801635992e-05, + "loss": 1.2415, + "step": 352 + }, + { + "epoch": 0.021670401178673377, + "grad_norm": 0.9205182064489833, + "learning_rate": 1.4437627811860942e-05, + "loss": 1.1973, + "step": 353 + }, + { + "epoch": 0.021731790417139876, + "grad_norm": 0.8655022334522159, + "learning_rate": 1.4478527607361965e-05, + "loss": 1.1589, + "step": 354 + }, + { + "epoch": 0.02179317965560637, + "grad_norm": 0.8391981972003733, + "learning_rate": 1.4519427402862987e-05, + "loss": 1.2174, + "step": 355 + }, + { + "epoch": 0.02185456889407287, + "grad_norm": 0.830907270801634, + "learning_rate": 1.456032719836401e-05, + "loss": 1.1372, + "step": 356 + }, + { + "epoch": 0.021915958132539364, + "grad_norm": 0.8695027254179146, + "learning_rate": 1.4601226993865032e-05, + "loss": 1.2091, + "step": 357 + }, + { + "epoch": 0.021977347371005863, + "grad_norm": 0.8654288793733558, + "learning_rate": 1.4642126789366054e-05, + "loss": 1.1838, + "step": 358 + }, + { + "epoch": 0.02203873660947236, + "grad_norm": 0.830466360405704, + "learning_rate": 1.4683026584867078e-05, + "loss": 1.144, + "step": 359 + }, + { + "epoch": 0.022100125847938856, + "grad_norm": 0.8464740622617065, + "learning_rate": 1.47239263803681e-05, + "loss": 1.1898, + "step": 360 + }, + { + "epoch": 0.022161515086405355, + "grad_norm": 0.8979305041679129, + "learning_rate": 1.4764826175869123e-05, + "loss": 1.1844, + "step": 361 + }, + { + "epoch": 0.02222290432487185, + "grad_norm": 0.8286281654472444, + "learning_rate": 1.4805725971370145e-05, + "loss": 1.2018, + "step": 362 + }, + { + "epoch": 0.02228429356333835, + "grad_norm": 0.7913506944330407, + "learning_rate": 1.4846625766871168e-05, + "loss": 1.1766, + "step": 363 + }, + { + "epoch": 0.022345682801804843, + "grad_norm": 0.8215650180308247, + "learning_rate": 1.488752556237219e-05, + "loss": 1.2236, + "step": 364 + }, + { + "epoch": 0.022407072040271342, + "grad_norm": 0.8286552924243976, + "learning_rate": 1.492842535787321e-05, + "loss": 1.1656, + "step": 365 + }, + { + "epoch": 0.022468461278737837, + "grad_norm": 0.8756501976992611, + "learning_rate": 1.4969325153374235e-05, + "loss": 1.2337, + "step": 366 + }, + { + "epoch": 0.022529850517204335, + "grad_norm": 0.8362557626062481, + "learning_rate": 1.5010224948875255e-05, + "loss": 1.2194, + "step": 367 + }, + { + "epoch": 0.02259123975567083, + "grad_norm": 0.8793044525619472, + "learning_rate": 1.505112474437628e-05, + "loss": 1.228, + "step": 368 + }, + { + "epoch": 0.02265262899413733, + "grad_norm": 0.8153760019222073, + "learning_rate": 1.50920245398773e-05, + "loss": 1.2116, + "step": 369 + }, + { + "epoch": 0.022714018232603824, + "grad_norm": 0.8197976202139433, + "learning_rate": 1.5132924335378326e-05, + "loss": 1.1926, + "step": 370 + }, + { + "epoch": 0.022775407471070323, + "grad_norm": 0.8514284177265541, + "learning_rate": 1.5173824130879346e-05, + "loss": 1.1786, + "step": 371 + }, + { + "epoch": 0.022836796709536818, + "grad_norm": 0.8668213052155469, + "learning_rate": 1.5214723926380371e-05, + "loss": 1.2224, + "step": 372 + }, + { + "epoch": 0.022898185948003316, + "grad_norm": 0.8546984925122584, + "learning_rate": 1.5255623721881391e-05, + "loss": 1.2152, + "step": 373 + }, + { + "epoch": 0.02295957518646981, + "grad_norm": 0.7667577465629799, + "learning_rate": 1.5296523517382413e-05, + "loss": 1.1691, + "step": 374 + }, + { + "epoch": 0.02302096442493631, + "grad_norm": 0.8756681508135885, + "learning_rate": 1.5337423312883436e-05, + "loss": 1.2185, + "step": 375 + }, + { + "epoch": 0.023082353663402805, + "grad_norm": 0.8560867968496353, + "learning_rate": 1.537832310838446e-05, + "loss": 1.1952, + "step": 376 + }, + { + "epoch": 0.023143742901869303, + "grad_norm": 0.7878677853596922, + "learning_rate": 1.5419222903885483e-05, + "loss": 1.2091, + "step": 377 + }, + { + "epoch": 0.0232051321403358, + "grad_norm": 0.8319344434557406, + "learning_rate": 1.5460122699386504e-05, + "loss": 1.2324, + "step": 378 + }, + { + "epoch": 0.023266521378802297, + "grad_norm": 0.8506728732599913, + "learning_rate": 1.5501022494887527e-05, + "loss": 1.2596, + "step": 379 + }, + { + "epoch": 0.023327910617268792, + "grad_norm": 0.827374152766755, + "learning_rate": 1.554192229038855e-05, + "loss": 1.2255, + "step": 380 + }, + { + "epoch": 0.02338929985573529, + "grad_norm": 0.8267812530244129, + "learning_rate": 1.5582822085889574e-05, + "loss": 1.2442, + "step": 381 + }, + { + "epoch": 0.023450689094201786, + "grad_norm": 0.8459890697885701, + "learning_rate": 1.5623721881390594e-05, + "loss": 1.211, + "step": 382 + }, + { + "epoch": 0.023512078332668284, + "grad_norm": 0.8443367231109451, + "learning_rate": 1.5664621676891618e-05, + "loss": 1.1976, + "step": 383 + }, + { + "epoch": 0.02357346757113478, + "grad_norm": 0.7317122482131433, + "learning_rate": 1.570552147239264e-05, + "loss": 1.0836, + "step": 384 + }, + { + "epoch": 0.023634856809601278, + "grad_norm": 0.8823447645961097, + "learning_rate": 1.574642126789366e-05, + "loss": 1.2245, + "step": 385 + }, + { + "epoch": 0.023696246048067773, + "grad_norm": 0.8196939815954067, + "learning_rate": 1.5787321063394685e-05, + "loss": 1.1702, + "step": 386 + }, + { + "epoch": 0.02375763528653427, + "grad_norm": 0.9161041167046815, + "learning_rate": 1.5828220858895708e-05, + "loss": 1.2884, + "step": 387 + }, + { + "epoch": 0.023819024525000766, + "grad_norm": 0.8476867162254936, + "learning_rate": 1.586912065439673e-05, + "loss": 1.2021, + "step": 388 + }, + { + "epoch": 0.023880413763467265, + "grad_norm": 0.845458473572594, + "learning_rate": 1.591002044989775e-05, + "loss": 1.2015, + "step": 389 + }, + { + "epoch": 0.02394180300193376, + "grad_norm": 0.7989195397958314, + "learning_rate": 1.5950920245398772e-05, + "loss": 1.1472, + "step": 390 + }, + { + "epoch": 0.02400319224040026, + "grad_norm": 2.1133742579666257, + "learning_rate": 1.59918200408998e-05, + "loss": 0.8498, + "step": 391 + }, + { + "epoch": 0.024064581478866753, + "grad_norm": 0.9574974228127204, + "learning_rate": 1.603271983640082e-05, + "loss": 1.2101, + "step": 392 + }, + { + "epoch": 0.024125970717333252, + "grad_norm": 0.9869075732456787, + "learning_rate": 1.6073619631901842e-05, + "loss": 1.1904, + "step": 393 + }, + { + "epoch": 0.024187359955799747, + "grad_norm": 0.9573120455011499, + "learning_rate": 1.6114519427402862e-05, + "loss": 1.1493, + "step": 394 + }, + { + "epoch": 0.024248749194266245, + "grad_norm": 0.978700590287899, + "learning_rate": 1.615541922290389e-05, + "loss": 1.2044, + "step": 395 + }, + { + "epoch": 0.02431013843273274, + "grad_norm": 0.8859489903145291, + "learning_rate": 1.619631901840491e-05, + "loss": 1.2405, + "step": 396 + }, + { + "epoch": 0.02437152767119924, + "grad_norm": 0.8290133306526156, + "learning_rate": 1.6237218813905933e-05, + "loss": 1.1968, + "step": 397 + }, + { + "epoch": 0.024432916909665734, + "grad_norm": 0.873257014033557, + "learning_rate": 1.6278118609406953e-05, + "loss": 1.1782, + "step": 398 + }, + { + "epoch": 0.024494306148132233, + "grad_norm": 0.7918183931666951, + "learning_rate": 1.6319018404907976e-05, + "loss": 1.2011, + "step": 399 + }, + { + "epoch": 0.024555695386598728, + "grad_norm": 0.8561210213808951, + "learning_rate": 1.6359918200409e-05, + "loss": 1.2338, + "step": 400 + }, + { + "epoch": 0.024617084625065226, + "grad_norm": 0.7792957918963211, + "learning_rate": 1.640081799591002e-05, + "loss": 1.1689, + "step": 401 + }, + { + "epoch": 0.02467847386353172, + "grad_norm": 0.8339615368284344, + "learning_rate": 1.6441717791411043e-05, + "loss": 1.22, + "step": 402 + }, + { + "epoch": 0.02473986310199822, + "grad_norm": 0.8636269783563201, + "learning_rate": 1.6482617586912067e-05, + "loss": 1.2568, + "step": 403 + }, + { + "epoch": 0.024801252340464718, + "grad_norm": 0.7512973709664957, + "learning_rate": 1.652351738241309e-05, + "loss": 1.1216, + "step": 404 + }, + { + "epoch": 0.024862641578931213, + "grad_norm": 0.8289624641623327, + "learning_rate": 1.656441717791411e-05, + "loss": 1.1566, + "step": 405 + }, + { + "epoch": 0.024924030817397712, + "grad_norm": 0.8779813565045463, + "learning_rate": 1.6605316973415134e-05, + "loss": 1.2431, + "step": 406 + }, + { + "epoch": 0.024985420055864207, + "grad_norm": 0.8221452944685408, + "learning_rate": 1.6646216768916157e-05, + "loss": 1.1992, + "step": 407 + }, + { + "epoch": 0.025046809294330705, + "grad_norm": 0.8699029993016624, + "learning_rate": 1.6687116564417178e-05, + "loss": 1.202, + "step": 408 + }, + { + "epoch": 0.0251081985327972, + "grad_norm": 0.8441894825273473, + "learning_rate": 1.67280163599182e-05, + "loss": 1.2544, + "step": 409 + }, + { + "epoch": 0.0251695877712637, + "grad_norm": 0.801628671020808, + "learning_rate": 1.6768916155419224e-05, + "loss": 1.1668, + "step": 410 + }, + { + "epoch": 0.025230977009730194, + "grad_norm": 0.8406000298284504, + "learning_rate": 1.6809815950920248e-05, + "loss": 1.2074, + "step": 411 + }, + { + "epoch": 0.025292366248196693, + "grad_norm": 0.8202374223401271, + "learning_rate": 1.6850715746421268e-05, + "loss": 1.1787, + "step": 412 + }, + { + "epoch": 0.025353755486663188, + "grad_norm": 0.7777730016769869, + "learning_rate": 1.689161554192229e-05, + "loss": 1.1405, + "step": 413 + }, + { + "epoch": 0.025415144725129686, + "grad_norm": 0.7774414464792573, + "learning_rate": 1.6932515337423315e-05, + "loss": 1.1637, + "step": 414 + }, + { + "epoch": 0.02547653396359618, + "grad_norm": 0.8055812763659518, + "learning_rate": 1.6973415132924335e-05, + "loss": 1.1777, + "step": 415 + }, + { + "epoch": 0.02553792320206268, + "grad_norm": 0.8324697293345281, + "learning_rate": 1.701431492842536e-05, + "loss": 1.2341, + "step": 416 + }, + { + "epoch": 0.025599312440529175, + "grad_norm": 0.8743983142196127, + "learning_rate": 1.7055214723926382e-05, + "loss": 1.2516, + "step": 417 + }, + { + "epoch": 0.025660701678995673, + "grad_norm": 0.8130872802405766, + "learning_rate": 1.7096114519427406e-05, + "loss": 1.1323, + "step": 418 + }, + { + "epoch": 0.02572209091746217, + "grad_norm": 0.789991308976025, + "learning_rate": 1.7137014314928426e-05, + "loss": 1.1663, + "step": 419 + }, + { + "epoch": 0.025783480155928667, + "grad_norm": 0.7905300929863343, + "learning_rate": 1.717791411042945e-05, + "loss": 1.2055, + "step": 420 + }, + { + "epoch": 0.025844869394395162, + "grad_norm": 0.8104096117387555, + "learning_rate": 1.7218813905930473e-05, + "loss": 1.1762, + "step": 421 + }, + { + "epoch": 0.02590625863286166, + "grad_norm": 0.7962736928904254, + "learning_rate": 1.7259713701431496e-05, + "loss": 1.1694, + "step": 422 + }, + { + "epoch": 0.025967647871328155, + "grad_norm": 0.7890257267253764, + "learning_rate": 1.7300613496932516e-05, + "loss": 1.1567, + "step": 423 + }, + { + "epoch": 0.026029037109794654, + "grad_norm": 0.8858206460343886, + "learning_rate": 1.734151329243354e-05, + "loss": 1.2857, + "step": 424 + }, + { + "epoch": 0.02609042634826115, + "grad_norm": 0.8200639006937106, + "learning_rate": 1.7382413087934563e-05, + "loss": 1.1665, + "step": 425 + }, + { + "epoch": 0.026151815586727648, + "grad_norm": 0.8268367192927448, + "learning_rate": 1.7423312883435583e-05, + "loss": 1.1716, + "step": 426 + }, + { + "epoch": 0.026213204825194143, + "grad_norm": 0.7920515250328882, + "learning_rate": 1.7464212678936607e-05, + "loss": 1.2295, + "step": 427 + }, + { + "epoch": 0.02627459406366064, + "grad_norm": 0.86443683589795, + "learning_rate": 1.750511247443763e-05, + "loss": 1.2511, + "step": 428 + }, + { + "epoch": 0.026335983302127136, + "grad_norm": 0.8814496384900139, + "learning_rate": 1.7546012269938654e-05, + "loss": 1.2583, + "step": 429 + }, + { + "epoch": 0.026397372540593635, + "grad_norm": 0.7791324839019005, + "learning_rate": 1.7586912065439674e-05, + "loss": 1.1372, + "step": 430 + }, + { + "epoch": 0.02645876177906013, + "grad_norm": 0.8283034622412645, + "learning_rate": 1.7627811860940697e-05, + "loss": 1.1484, + "step": 431 + }, + { + "epoch": 0.026520151017526628, + "grad_norm": 0.7632817238523816, + "learning_rate": 1.766871165644172e-05, + "loss": 1.1445, + "step": 432 + }, + { + "epoch": 0.026581540255993123, + "grad_norm": 0.8287252027218102, + "learning_rate": 1.770961145194274e-05, + "loss": 1.2048, + "step": 433 + }, + { + "epoch": 0.026642929494459622, + "grad_norm": 0.8277530076903813, + "learning_rate": 1.7750511247443764e-05, + "loss": 1.1504, + "step": 434 + }, + { + "epoch": 0.026704318732926117, + "grad_norm": 0.8328745435209625, + "learning_rate": 1.7791411042944788e-05, + "loss": 1.2185, + "step": 435 + }, + { + "epoch": 0.026765707971392615, + "grad_norm": 0.8278157142608409, + "learning_rate": 1.783231083844581e-05, + "loss": 1.23, + "step": 436 + }, + { + "epoch": 0.02682709720985911, + "grad_norm": 0.8105829247693117, + "learning_rate": 1.787321063394683e-05, + "loss": 1.1761, + "step": 437 + }, + { + "epoch": 0.02688848644832561, + "grad_norm": 0.7338440382037114, + "learning_rate": 1.7914110429447855e-05, + "loss": 1.097, + "step": 438 + }, + { + "epoch": 0.026949875686792104, + "grad_norm": 0.7975043191741912, + "learning_rate": 1.795501022494888e-05, + "loss": 1.1893, + "step": 439 + }, + { + "epoch": 0.027011264925258602, + "grad_norm": 0.8264906031744635, + "learning_rate": 1.79959100204499e-05, + "loss": 1.2418, + "step": 440 + }, + { + "epoch": 0.027072654163725098, + "grad_norm": 0.8425408006359938, + "learning_rate": 1.8036809815950922e-05, + "loss": 1.2654, + "step": 441 + }, + { + "epoch": 0.027134043402191596, + "grad_norm": 0.8553549685128431, + "learning_rate": 1.8077709611451942e-05, + "loss": 1.1778, + "step": 442 + }, + { + "epoch": 0.02719543264065809, + "grad_norm": 0.7913396595869623, + "learning_rate": 1.811860940695297e-05, + "loss": 1.1639, + "step": 443 + }, + { + "epoch": 0.02725682187912459, + "grad_norm": 0.7764739330760835, + "learning_rate": 1.815950920245399e-05, + "loss": 1.1598, + "step": 444 + }, + { + "epoch": 0.027318211117591085, + "grad_norm": 0.7871174733192688, + "learning_rate": 1.8200408997955012e-05, + "loss": 1.2255, + "step": 445 + }, + { + "epoch": 0.027379600356057583, + "grad_norm": 0.7954431113661323, + "learning_rate": 1.8241308793456033e-05, + "loss": 1.196, + "step": 446 + }, + { + "epoch": 0.027440989594524078, + "grad_norm": 0.7548485757636636, + "learning_rate": 1.828220858895706e-05, + "loss": 1.1653, + "step": 447 + }, + { + "epoch": 0.027502378832990577, + "grad_norm": 0.7866390070127494, + "learning_rate": 1.832310838445808e-05, + "loss": 1.1617, + "step": 448 + }, + { + "epoch": 0.027563768071457075, + "grad_norm": 0.8231119774693763, + "learning_rate": 1.83640081799591e-05, + "loss": 1.2162, + "step": 449 + }, + { + "epoch": 0.02762515730992357, + "grad_norm": 0.7972489552337322, + "learning_rate": 1.8404907975460123e-05, + "loss": 1.1824, + "step": 450 + }, + { + "epoch": 0.02768654654839007, + "grad_norm": 0.8049131517507562, + "learning_rate": 1.8445807770961147e-05, + "loss": 1.1856, + "step": 451 + }, + { + "epoch": 0.027747935786856564, + "grad_norm": 0.7960940530596916, + "learning_rate": 1.848670756646217e-05, + "loss": 1.24, + "step": 452 + }, + { + "epoch": 0.027809325025323062, + "grad_norm": 0.7858422997082436, + "learning_rate": 1.852760736196319e-05, + "loss": 1.1347, + "step": 453 + }, + { + "epoch": 0.027870714263789557, + "grad_norm": 0.8277525439116892, + "learning_rate": 1.8568507157464214e-05, + "loss": 1.2234, + "step": 454 + }, + { + "epoch": 0.027932103502256056, + "grad_norm": 0.789221429837857, + "learning_rate": 1.8609406952965237e-05, + "loss": 1.1927, + "step": 455 + }, + { + "epoch": 0.02799349274072255, + "grad_norm": 0.805365388997287, + "learning_rate": 1.8650306748466257e-05, + "loss": 1.1951, + "step": 456 + }, + { + "epoch": 0.02805488197918905, + "grad_norm": 0.7920452509045837, + "learning_rate": 1.869120654396728e-05, + "loss": 1.1993, + "step": 457 + }, + { + "epoch": 0.028116271217655545, + "grad_norm": 0.782376837216006, + "learning_rate": 1.8732106339468304e-05, + "loss": 1.1459, + "step": 458 + }, + { + "epoch": 0.028177660456122043, + "grad_norm": 0.8469691551927405, + "learning_rate": 1.8773006134969328e-05, + "loss": 1.2111, + "step": 459 + }, + { + "epoch": 0.028239049694588538, + "grad_norm": 0.8448072862016627, + "learning_rate": 1.8813905930470348e-05, + "loss": 1.2562, + "step": 460 + }, + { + "epoch": 0.028300438933055037, + "grad_norm": 0.7812444865331837, + "learning_rate": 1.885480572597137e-05, + "loss": 1.1136, + "step": 461 + }, + { + "epoch": 0.028361828171521532, + "grad_norm": 0.8370843664752747, + "learning_rate": 1.8895705521472395e-05, + "loss": 1.205, + "step": 462 + }, + { + "epoch": 0.02842321740998803, + "grad_norm": 0.8381248579094686, + "learning_rate": 1.8936605316973418e-05, + "loss": 1.2516, + "step": 463 + }, + { + "epoch": 0.028484606648454525, + "grad_norm": 0.7974951132149466, + "learning_rate": 1.8977505112474438e-05, + "loss": 1.1906, + "step": 464 + }, + { + "epoch": 0.028545995886921024, + "grad_norm": 0.8186989160058334, + "learning_rate": 1.9018404907975462e-05, + "loss": 1.1925, + "step": 465 + }, + { + "epoch": 0.02860738512538752, + "grad_norm": 0.7801635045653744, + "learning_rate": 1.9059304703476485e-05, + "loss": 1.1937, + "step": 466 + }, + { + "epoch": 0.028668774363854017, + "grad_norm": 0.7649071660981295, + "learning_rate": 1.9100204498977505e-05, + "loss": 1.1648, + "step": 467 + }, + { + "epoch": 0.028730163602320512, + "grad_norm": 0.837636149421935, + "learning_rate": 1.914110429447853e-05, + "loss": 1.1829, + "step": 468 + }, + { + "epoch": 0.02879155284078701, + "grad_norm": 0.7533319399575084, + "learning_rate": 1.9182004089979552e-05, + "loss": 1.1608, + "step": 469 + }, + { + "epoch": 0.028852942079253506, + "grad_norm": 0.836676130334936, + "learning_rate": 1.9222903885480576e-05, + "loss": 1.1905, + "step": 470 + }, + { + "epoch": 0.028914331317720005, + "grad_norm": 0.8290817879145083, + "learning_rate": 1.9263803680981596e-05, + "loss": 1.1555, + "step": 471 + }, + { + "epoch": 0.0289757205561865, + "grad_norm": 0.853495044462067, + "learning_rate": 1.930470347648262e-05, + "loss": 1.184, + "step": 472 + }, + { + "epoch": 0.029037109794652998, + "grad_norm": 0.8593914533379913, + "learning_rate": 1.9345603271983643e-05, + "loss": 1.1511, + "step": 473 + }, + { + "epoch": 0.029098499033119493, + "grad_norm": 0.7980600889056769, + "learning_rate": 1.9386503067484663e-05, + "loss": 1.196, + "step": 474 + }, + { + "epoch": 0.02915988827158599, + "grad_norm": 0.7903613511131234, + "learning_rate": 1.9427402862985686e-05, + "loss": 1.1659, + "step": 475 + }, + { + "epoch": 0.029221277510052487, + "grad_norm": 0.8501764868346416, + "learning_rate": 1.946830265848671e-05, + "loss": 1.2248, + "step": 476 + }, + { + "epoch": 0.029282666748518985, + "grad_norm": 0.7600458440365832, + "learning_rate": 1.9509202453987733e-05, + "loss": 1.1619, + "step": 477 + }, + { + "epoch": 0.02934405598698548, + "grad_norm": 0.802046913745942, + "learning_rate": 1.9550102249488753e-05, + "loss": 1.174, + "step": 478 + }, + { + "epoch": 0.02940544522545198, + "grad_norm": 0.772666934578416, + "learning_rate": 1.9591002044989777e-05, + "loss": 1.1584, + "step": 479 + }, + { + "epoch": 0.029466834463918474, + "grad_norm": 0.7882842761115904, + "learning_rate": 1.96319018404908e-05, + "loss": 1.187, + "step": 480 + }, + { + "epoch": 0.029528223702384972, + "grad_norm": 0.829670103261857, + "learning_rate": 1.967280163599182e-05, + "loss": 1.1974, + "step": 481 + }, + { + "epoch": 0.029589612940851467, + "grad_norm": 0.7832045130151868, + "learning_rate": 1.9713701431492844e-05, + "loss": 1.1912, + "step": 482 + }, + { + "epoch": 0.029651002179317966, + "grad_norm": 0.8065090126713159, + "learning_rate": 1.9754601226993868e-05, + "loss": 1.1815, + "step": 483 + }, + { + "epoch": 0.02971239141778446, + "grad_norm": 0.7927486997450159, + "learning_rate": 1.979550102249489e-05, + "loss": 1.1591, + "step": 484 + }, + { + "epoch": 0.02977378065625096, + "grad_norm": 0.7874089706416224, + "learning_rate": 1.983640081799591e-05, + "loss": 1.1939, + "step": 485 + }, + { + "epoch": 0.029835169894717455, + "grad_norm": 0.7589995682730937, + "learning_rate": 1.9877300613496935e-05, + "loss": 1.1032, + "step": 486 + }, + { + "epoch": 0.029896559133183953, + "grad_norm": 0.7723707855142388, + "learning_rate": 1.9918200408997958e-05, + "loss": 1.1798, + "step": 487 + }, + { + "epoch": 0.029957948371650448, + "grad_norm": 0.7416023467357451, + "learning_rate": 1.995910020449898e-05, + "loss": 1.1317, + "step": 488 + }, + { + "epoch": 0.030019337610116947, + "grad_norm": 0.7717719533038341, + "learning_rate": 2e-05, + "loss": 1.1465, + "step": 489 + }, + { + "epoch": 0.03008072684858344, + "grad_norm": 0.8414649155466306, + "learning_rate": 1.999999980232326e-05, + "loss": 1.1812, + "step": 490 + }, + { + "epoch": 0.03014211608704994, + "grad_norm": 0.7966449467979996, + "learning_rate": 1.999999920929304e-05, + "loss": 1.2282, + "step": 491 + }, + { + "epoch": 0.030203505325516435, + "grad_norm": 0.7715489843481121, + "learning_rate": 1.999999822090937e-05, + "loss": 1.1392, + "step": 492 + }, + { + "epoch": 0.030264894563982934, + "grad_norm": 0.7712110961717288, + "learning_rate": 1.9999996837172285e-05, + "loss": 1.1402, + "step": 493 + }, + { + "epoch": 0.030326283802449432, + "grad_norm": 0.7522840368177419, + "learning_rate": 1.9999995058081847e-05, + "loss": 1.2134, + "step": 494 + }, + { + "epoch": 0.030387673040915927, + "grad_norm": 0.8116540616173141, + "learning_rate": 1.9999992883638116e-05, + "loss": 1.1805, + "step": 495 + }, + { + "epoch": 0.030449062279382426, + "grad_norm": 0.7136555782495311, + "learning_rate": 1.999999031384118e-05, + "loss": 1.1667, + "step": 496 + }, + { + "epoch": 0.03051045151784892, + "grad_norm": 0.7588798276322625, + "learning_rate": 1.9999987348691148e-05, + "loss": 1.1233, + "step": 497 + }, + { + "epoch": 0.03057184075631542, + "grad_norm": 0.819457292666737, + "learning_rate": 1.999998398818813e-05, + "loss": 1.1866, + "step": 498 + }, + { + "epoch": 0.030633229994781914, + "grad_norm": 0.8583207822768066, + "learning_rate": 1.999998023233226e-05, + "loss": 1.2129, + "step": 499 + }, + { + "epoch": 0.030694619233248413, + "grad_norm": 0.7766556730015548, + "learning_rate": 1.9999976081123692e-05, + "loss": 1.1467, + "step": 500 + }, + { + "epoch": 0.030756008471714908, + "grad_norm": 0.7665340507140211, + "learning_rate": 1.999997153456258e-05, + "loss": 1.192, + "step": 501 + }, + { + "epoch": 0.030817397710181407, + "grad_norm": 0.8519514024349921, + "learning_rate": 1.9999966592649118e-05, + "loss": 1.2239, + "step": 502 + }, + { + "epoch": 0.0308787869486479, + "grad_norm": 0.7846944218613637, + "learning_rate": 1.9999961255383485e-05, + "loss": 1.1407, + "step": 503 + }, + { + "epoch": 0.0309401761871144, + "grad_norm": 0.8513725432607374, + "learning_rate": 1.99999555227659e-05, + "loss": 1.207, + "step": 504 + }, + { + "epoch": 0.031001565425580895, + "grad_norm": 0.7621796826238002, + "learning_rate": 1.9999949394796597e-05, + "loss": 1.1624, + "step": 505 + }, + { + "epoch": 0.031062954664047394, + "grad_norm": 0.7523755417465795, + "learning_rate": 1.9999942871475807e-05, + "loss": 1.1535, + "step": 506 + }, + { + "epoch": 0.03112434390251389, + "grad_norm": 0.76819616675726, + "learning_rate": 1.9999935952803788e-05, + "loss": 1.1703, + "step": 507 + }, + { + "epoch": 0.031185733140980387, + "grad_norm": 0.7764474456781972, + "learning_rate": 1.9999928638780822e-05, + "loss": 1.1649, + "step": 508 + }, + { + "epoch": 0.031247122379446882, + "grad_norm": 0.71954962542189, + "learning_rate": 1.9999920929407192e-05, + "loss": 1.0998, + "step": 509 + }, + { + "epoch": 0.03130851161791338, + "grad_norm": 0.8085372605357346, + "learning_rate": 1.9999912824683205e-05, + "loss": 1.1921, + "step": 510 + }, + { + "epoch": 0.031369900856379876, + "grad_norm": 0.854721482946347, + "learning_rate": 1.9999904324609177e-05, + "loss": 1.2426, + "step": 511 + }, + { + "epoch": 0.031431290094846374, + "grad_norm": 0.7981261907347532, + "learning_rate": 1.9999895429185453e-05, + "loss": 1.1545, + "step": 512 + }, + { + "epoch": 0.03149267933331287, + "grad_norm": 0.7902739760514762, + "learning_rate": 1.999988613841238e-05, + "loss": 1.1635, + "step": 513 + }, + { + "epoch": 0.031554068571779365, + "grad_norm": 0.806963298502301, + "learning_rate": 1.999987645229032e-05, + "loss": 1.1935, + "step": 514 + }, + { + "epoch": 0.03161545781024586, + "grad_norm": 0.7908212161442938, + "learning_rate": 1.9999866370819662e-05, + "loss": 1.2125, + "step": 515 + }, + { + "epoch": 0.03167684704871236, + "grad_norm": 0.7784013436596409, + "learning_rate": 1.9999855894000807e-05, + "loss": 1.196, + "step": 516 + }, + { + "epoch": 0.03173823628717886, + "grad_norm": 0.8200966914867415, + "learning_rate": 1.9999845021834162e-05, + "loss": 1.2714, + "step": 517 + }, + { + "epoch": 0.03179962552564535, + "grad_norm": 0.7359192391111786, + "learning_rate": 1.999983375432016e-05, + "loss": 1.1438, + "step": 518 + }, + { + "epoch": 0.03186101476411185, + "grad_norm": 0.7658677336856671, + "learning_rate": 1.9999822091459248e-05, + "loss": 1.1439, + "step": 519 + }, + { + "epoch": 0.03192240400257835, + "grad_norm": 0.8394212896368244, + "learning_rate": 1.9999810033251886e-05, + "loss": 1.2652, + "step": 520 + }, + { + "epoch": 0.03198379324104485, + "grad_norm": 0.7507314169898879, + "learning_rate": 1.999979757969855e-05, + "loss": 1.1682, + "step": 521 + }, + { + "epoch": 0.03204518247951134, + "grad_norm": 0.8237155897849922, + "learning_rate": 1.9999784730799736e-05, + "loss": 1.2294, + "step": 522 + }, + { + "epoch": 0.03210657171797784, + "grad_norm": 0.7896724222137275, + "learning_rate": 1.9999771486555947e-05, + "loss": 1.1893, + "step": 523 + }, + { + "epoch": 0.032167960956444336, + "grad_norm": 0.7957047882221367, + "learning_rate": 1.999975784696771e-05, + "loss": 1.2313, + "step": 524 + }, + { + "epoch": 0.032229350194910834, + "grad_norm": 0.7764034212584963, + "learning_rate": 1.999974381203556e-05, + "loss": 1.2051, + "step": 525 + }, + { + "epoch": 0.032290739433377326, + "grad_norm": 0.7851827757856666, + "learning_rate": 1.9999729381760057e-05, + "loss": 1.1698, + "step": 526 + }, + { + "epoch": 0.032352128671843824, + "grad_norm": 0.7934368314415116, + "learning_rate": 1.9999714556141768e-05, + "loss": 1.2099, + "step": 527 + }, + { + "epoch": 0.03241351791031032, + "grad_norm": 0.8120343957691896, + "learning_rate": 1.999969933518128e-05, + "loss": 1.2065, + "step": 528 + }, + { + "epoch": 0.03247490714877682, + "grad_norm": 0.8244403371570975, + "learning_rate": 1.9999683718879195e-05, + "loss": 1.2084, + "step": 529 + }, + { + "epoch": 0.03253629638724331, + "grad_norm": 0.8108730896292196, + "learning_rate": 1.9999667707236133e-05, + "loss": 1.2184, + "step": 530 + }, + { + "epoch": 0.03259768562570981, + "grad_norm": 0.7861424333150167, + "learning_rate": 1.999965130025272e-05, + "loss": 1.1972, + "step": 531 + }, + { + "epoch": 0.03265907486417631, + "grad_norm": 0.7666301683160879, + "learning_rate": 1.9999634497929613e-05, + "loss": 1.1807, + "step": 532 + }, + { + "epoch": 0.03272046410264281, + "grad_norm": 0.7194382265152288, + "learning_rate": 1.999961730026747e-05, + "loss": 1.1288, + "step": 533 + }, + { + "epoch": 0.0327818533411093, + "grad_norm": 0.7474831907741142, + "learning_rate": 1.9999599707266976e-05, + "loss": 1.1175, + "step": 534 + }, + { + "epoch": 0.0328432425795758, + "grad_norm": 0.7515291964224213, + "learning_rate": 1.999958171892882e-05, + "loss": 1.1653, + "step": 535 + }, + { + "epoch": 0.0329046318180423, + "grad_norm": 0.7667241880501288, + "learning_rate": 1.9999563335253722e-05, + "loss": 1.1469, + "step": 536 + }, + { + "epoch": 0.032966021056508796, + "grad_norm": 0.80853043141222, + "learning_rate": 1.9999544556242404e-05, + "loss": 1.18, + "step": 537 + }, + { + "epoch": 0.033027410294975294, + "grad_norm": 0.8277058505783432, + "learning_rate": 1.9999525381895605e-05, + "loss": 1.173, + "step": 538 + }, + { + "epoch": 0.033088799533441786, + "grad_norm": 0.7934307667482043, + "learning_rate": 1.9999505812214087e-05, + "loss": 1.2172, + "step": 539 + }, + { + "epoch": 0.033150188771908284, + "grad_norm": 0.7861330968896678, + "learning_rate": 1.9999485847198623e-05, + "loss": 1.1491, + "step": 540 + }, + { + "epoch": 0.03321157801037478, + "grad_norm": 0.7806549759475643, + "learning_rate": 1.9999465486850003e-05, + "loss": 1.1964, + "step": 541 + }, + { + "epoch": 0.03327296724884128, + "grad_norm": 0.826040198062637, + "learning_rate": 1.9999444731169032e-05, + "loss": 1.2229, + "step": 542 + }, + { + "epoch": 0.03333435648730777, + "grad_norm": 0.8257746936261856, + "learning_rate": 1.999942358015653e-05, + "loss": 1.1813, + "step": 543 + }, + { + "epoch": 0.03339574572577427, + "grad_norm": 0.7867494208901982, + "learning_rate": 1.9999402033813334e-05, + "loss": 1.2007, + "step": 544 + }, + { + "epoch": 0.03345713496424077, + "grad_norm": 0.7787271336693975, + "learning_rate": 1.9999380092140294e-05, + "loss": 1.2011, + "step": 545 + }, + { + "epoch": 0.03351852420270727, + "grad_norm": 0.7302797749917745, + "learning_rate": 1.9999357755138278e-05, + "loss": 1.2455, + "step": 546 + }, + { + "epoch": 0.03357991344117376, + "grad_norm": 0.8028854676537812, + "learning_rate": 1.999933502280817e-05, + "loss": 1.1469, + "step": 547 + }, + { + "epoch": 0.03364130267964026, + "grad_norm": 0.7830588022607307, + "learning_rate": 1.9999311895150866e-05, + "loss": 1.2526, + "step": 548 + }, + { + "epoch": 0.03370269191810676, + "grad_norm": 0.7835692405450327, + "learning_rate": 1.9999288372167287e-05, + "loss": 1.1985, + "step": 549 + }, + { + "epoch": 0.033764081156573256, + "grad_norm": 0.7867134362885789, + "learning_rate": 1.9999264453858354e-05, + "loss": 1.1603, + "step": 550 + }, + { + "epoch": 0.03382547039503975, + "grad_norm": 0.7707247532237194, + "learning_rate": 1.9999240140225023e-05, + "loss": 1.1729, + "step": 551 + }, + { + "epoch": 0.033886859633506246, + "grad_norm": 0.7827628969418767, + "learning_rate": 1.9999215431268246e-05, + "loss": 1.1475, + "step": 552 + }, + { + "epoch": 0.033948248871972744, + "grad_norm": 0.7705559820112987, + "learning_rate": 1.9999190326989005e-05, + "loss": 1.1881, + "step": 553 + }, + { + "epoch": 0.03400963811043924, + "grad_norm": 0.764293788307644, + "learning_rate": 1.999916482738829e-05, + "loss": 1.1423, + "step": 554 + }, + { + "epoch": 0.034071027348905734, + "grad_norm": 0.7751465369738654, + "learning_rate": 1.999913893246711e-05, + "loss": 1.1888, + "step": 555 + }, + { + "epoch": 0.03413241658737223, + "grad_norm": 0.758845314079889, + "learning_rate": 1.999911264222649e-05, + "loss": 1.1736, + "step": 556 + }, + { + "epoch": 0.03419380582583873, + "grad_norm": 0.7791035481138368, + "learning_rate": 1.9999085956667463e-05, + "loss": 1.1211, + "step": 557 + }, + { + "epoch": 0.03425519506430523, + "grad_norm": 0.7835322520820835, + "learning_rate": 1.9999058875791096e-05, + "loss": 1.1893, + "step": 558 + }, + { + "epoch": 0.03431658430277172, + "grad_norm": 0.7605369774090915, + "learning_rate": 1.999903139959845e-05, + "loss": 1.1553, + "step": 559 + }, + { + "epoch": 0.03437797354123822, + "grad_norm": 0.7541013928648674, + "learning_rate": 1.9999003528090613e-05, + "loss": 1.1452, + "step": 560 + }, + { + "epoch": 0.03443936277970472, + "grad_norm": 0.7315990574184156, + "learning_rate": 1.9998975261268693e-05, + "loss": 1.1537, + "step": 561 + }, + { + "epoch": 0.03450075201817122, + "grad_norm": 0.7572168353971249, + "learning_rate": 1.9998946599133795e-05, + "loss": 1.0801, + "step": 562 + }, + { + "epoch": 0.03456214125663771, + "grad_norm": 0.8357147548537776, + "learning_rate": 1.9998917541687066e-05, + "loss": 1.2045, + "step": 563 + }, + { + "epoch": 0.03462353049510421, + "grad_norm": 0.7926522524782875, + "learning_rate": 1.9998888088929647e-05, + "loss": 1.1628, + "step": 564 + }, + { + "epoch": 0.034684919733570706, + "grad_norm": 0.8071412815937687, + "learning_rate": 1.9998858240862703e-05, + "loss": 1.219, + "step": 565 + }, + { + "epoch": 0.034746308972037204, + "grad_norm": 0.770975343708381, + "learning_rate": 1.9998827997487415e-05, + "loss": 1.1694, + "step": 566 + }, + { + "epoch": 0.034807698210503696, + "grad_norm": 0.7427851419258489, + "learning_rate": 1.999879735880498e-05, + "loss": 1.1634, + "step": 567 + }, + { + "epoch": 0.034869087448970194, + "grad_norm": 0.7652591936200561, + "learning_rate": 1.9998766324816606e-05, + "loss": 1.1715, + "step": 568 + }, + { + "epoch": 0.03493047668743669, + "grad_norm": 0.7338838321637975, + "learning_rate": 1.9998734895523525e-05, + "loss": 1.1273, + "step": 569 + }, + { + "epoch": 0.03499186592590319, + "grad_norm": 0.8041474697183796, + "learning_rate": 1.999870307092698e-05, + "loss": 1.2043, + "step": 570 + }, + { + "epoch": 0.03505325516436968, + "grad_norm": 0.7937305418273234, + "learning_rate": 1.9998670851028215e-05, + "loss": 1.1873, + "step": 571 + }, + { + "epoch": 0.03511464440283618, + "grad_norm": 0.7120223038036031, + "learning_rate": 1.9998638235828524e-05, + "loss": 1.12, + "step": 572 + }, + { + "epoch": 0.03517603364130268, + "grad_norm": 0.7459446876162098, + "learning_rate": 1.999860522532918e-05, + "loss": 1.1442, + "step": 573 + }, + { + "epoch": 0.03523742287976918, + "grad_norm": 0.7955998612785583, + "learning_rate": 1.99985718195315e-05, + "loss": 1.163, + "step": 574 + }, + { + "epoch": 0.03529881211823567, + "grad_norm": 0.7792623251696111, + "learning_rate": 1.99985380184368e-05, + "loss": 1.1874, + "step": 575 + }, + { + "epoch": 0.03536020135670217, + "grad_norm": 0.7560230763658033, + "learning_rate": 1.9998503822046414e-05, + "loss": 1.1587, + "step": 576 + }, + { + "epoch": 0.03542159059516867, + "grad_norm": 0.752120173270299, + "learning_rate": 1.9998469230361696e-05, + "loss": 1.1831, + "step": 577 + }, + { + "epoch": 0.035482979833635166, + "grad_norm": 0.7347427482925661, + "learning_rate": 1.999843424338402e-05, + "loss": 1.1284, + "step": 578 + }, + { + "epoch": 0.03554436907210166, + "grad_norm": 0.7066631634578345, + "learning_rate": 1.9998398861114754e-05, + "loss": 1.09, + "step": 579 + }, + { + "epoch": 0.035605758310568156, + "grad_norm": 0.7385682397981282, + "learning_rate": 1.9998363083555308e-05, + "loss": 1.194, + "step": 580 + }, + { + "epoch": 0.035667147549034654, + "grad_norm": 0.8005454131589419, + "learning_rate": 1.9998326910707096e-05, + "loss": 1.2024, + "step": 581 + }, + { + "epoch": 0.03572853678750115, + "grad_norm": 0.7572744650987927, + "learning_rate": 1.9998290342571546e-05, + "loss": 1.1504, + "step": 582 + }, + { + "epoch": 0.03578992602596765, + "grad_norm": 0.7116929389292086, + "learning_rate": 1.9998253379150107e-05, + "loss": 1.0786, + "step": 583 + }, + { + "epoch": 0.03585131526443414, + "grad_norm": 0.7726636222672393, + "learning_rate": 1.9998216020444233e-05, + "loss": 1.2405, + "step": 584 + }, + { + "epoch": 0.03591270450290064, + "grad_norm": 0.789365242858962, + "learning_rate": 1.9998178266455407e-05, + "loss": 1.2093, + "step": 585 + }, + { + "epoch": 0.03597409374136714, + "grad_norm": 0.7962166863487127, + "learning_rate": 1.9998140117185125e-05, + "loss": 1.1842, + "step": 586 + }, + { + "epoch": 0.03603548297983364, + "grad_norm": 0.7553573374029694, + "learning_rate": 1.9998101572634883e-05, + "loss": 1.111, + "step": 587 + }, + { + "epoch": 0.03609687221830013, + "grad_norm": 0.8214403966237992, + "learning_rate": 1.9998062632806213e-05, + "loss": 1.2186, + "step": 588 + }, + { + "epoch": 0.03615826145676663, + "grad_norm": 0.796367331925462, + "learning_rate": 1.9998023297700656e-05, + "loss": 1.1835, + "step": 589 + }, + { + "epoch": 0.03621965069523313, + "grad_norm": 0.7389838316181987, + "learning_rate": 1.999798356731977e-05, + "loss": 1.1635, + "step": 590 + }, + { + "epoch": 0.036281039933699626, + "grad_norm": 0.7202362256161474, + "learning_rate": 1.999794344166511e-05, + "loss": 1.1455, + "step": 591 + }, + { + "epoch": 0.03634242917216612, + "grad_norm": 0.8040138166866135, + "learning_rate": 1.999790292073828e-05, + "loss": 1.2291, + "step": 592 + }, + { + "epoch": 0.036403818410632616, + "grad_norm": 0.7803770717736574, + "learning_rate": 1.9997862004540872e-05, + "loss": 1.1862, + "step": 593 + }, + { + "epoch": 0.036465207649099114, + "grad_norm": 0.7733265108879258, + "learning_rate": 1.999782069307451e-05, + "loss": 1.2249, + "step": 594 + }, + { + "epoch": 0.03652659688756561, + "grad_norm": 0.7572884715272582, + "learning_rate": 1.9997778986340817e-05, + "loss": 1.1105, + "step": 595 + }, + { + "epoch": 0.036587986126032104, + "grad_norm": 0.7356037086821875, + "learning_rate": 1.9997736884341457e-05, + "loss": 1.0957, + "step": 596 + }, + { + "epoch": 0.0366493753644986, + "grad_norm": 0.7812730581123835, + "learning_rate": 1.9997694387078082e-05, + "loss": 1.1679, + "step": 597 + }, + { + "epoch": 0.0367107646029651, + "grad_norm": 0.7483661348133198, + "learning_rate": 1.9997651494552376e-05, + "loss": 1.1656, + "step": 598 + }, + { + "epoch": 0.0367721538414316, + "grad_norm": 0.6881302134362874, + "learning_rate": 1.999760820676604e-05, + "loss": 1.057, + "step": 599 + }, + { + "epoch": 0.03683354307989809, + "grad_norm": 1.4579271595256447, + "learning_rate": 1.9997564523720778e-05, + "loss": 0.8077, + "step": 600 + }, + { + "epoch": 0.03689493231836459, + "grad_norm": 0.7783647397304394, + "learning_rate": 1.9997520445418317e-05, + "loss": 1.2754, + "step": 601 + }, + { + "epoch": 0.03695632155683109, + "grad_norm": 0.8007632895108733, + "learning_rate": 1.9997475971860404e-05, + "loss": 1.1775, + "step": 602 + }, + { + "epoch": 0.03701771079529759, + "grad_norm": 0.8758225690709026, + "learning_rate": 1.9997431103048796e-05, + "loss": 1.2348, + "step": 603 + }, + { + "epoch": 0.03707910003376408, + "grad_norm": 0.7525456378167841, + "learning_rate": 1.9997385838985265e-05, + "loss": 1.1838, + "step": 604 + }, + { + "epoch": 0.03714048927223058, + "grad_norm": 0.7889103804369774, + "learning_rate": 1.9997340179671604e-05, + "loss": 1.1229, + "step": 605 + }, + { + "epoch": 0.037201878510697076, + "grad_norm": 0.7845459938105296, + "learning_rate": 1.9997294125109615e-05, + "loss": 1.1938, + "step": 606 + }, + { + "epoch": 0.037263267749163574, + "grad_norm": 0.7508486658253677, + "learning_rate": 1.999724767530112e-05, + "loss": 1.1691, + "step": 607 + }, + { + "epoch": 0.037324656987630066, + "grad_norm": 0.734081576505851, + "learning_rate": 1.9997200830247955e-05, + "loss": 1.1637, + "step": 608 + }, + { + "epoch": 0.037386046226096564, + "grad_norm": 0.796376013226744, + "learning_rate": 1.9997153589951973e-05, + "loss": 1.1976, + "step": 609 + }, + { + "epoch": 0.03744743546456306, + "grad_norm": 0.7315086718739767, + "learning_rate": 1.999710595441504e-05, + "loss": 1.1234, + "step": 610 + }, + { + "epoch": 0.03750882470302956, + "grad_norm": 0.7533116819803349, + "learning_rate": 1.9997057923639045e-05, + "loss": 1.1549, + "step": 611 + }, + { + "epoch": 0.03757021394149605, + "grad_norm": 0.7300541280323689, + "learning_rate": 1.9997009497625876e-05, + "loss": 1.097, + "step": 612 + }, + { + "epoch": 0.03763160317996255, + "grad_norm": 0.747581368800018, + "learning_rate": 1.999696067637746e-05, + "loss": 1.1409, + "step": 613 + }, + { + "epoch": 0.03769299241842905, + "grad_norm": 0.7233951370961962, + "learning_rate": 1.9996911459895717e-05, + "loss": 1.1864, + "step": 614 + }, + { + "epoch": 0.03775438165689555, + "grad_norm": 0.776828312795986, + "learning_rate": 1.9996861848182596e-05, + "loss": 1.1196, + "step": 615 + }, + { + "epoch": 0.03781577089536204, + "grad_norm": 0.7681275417209665, + "learning_rate": 1.999681184124006e-05, + "loss": 1.2464, + "step": 616 + }, + { + "epoch": 0.03787716013382854, + "grad_norm": 0.801825108006464, + "learning_rate": 1.9996761439070087e-05, + "loss": 1.1246, + "step": 617 + }, + { + "epoch": 0.03793854937229504, + "grad_norm": 0.8217285134147737, + "learning_rate": 1.9996710641674666e-05, + "loss": 1.1992, + "step": 618 + }, + { + "epoch": 0.037999938610761536, + "grad_norm": 0.771677068460579, + "learning_rate": 1.999665944905581e-05, + "loss": 1.1619, + "step": 619 + }, + { + "epoch": 0.03806132784922803, + "grad_norm": 0.7412790352819754, + "learning_rate": 1.9996607861215535e-05, + "loss": 1.1282, + "step": 620 + }, + { + "epoch": 0.038122717087694526, + "grad_norm": 0.8363056284681533, + "learning_rate": 1.9996555878155887e-05, + "loss": 1.2313, + "step": 621 + }, + { + "epoch": 0.038184106326161024, + "grad_norm": 0.722485149827105, + "learning_rate": 1.9996503499878922e-05, + "loss": 1.1703, + "step": 622 + }, + { + "epoch": 0.03824549556462752, + "grad_norm": 0.7453484729146794, + "learning_rate": 1.9996450726386708e-05, + "loss": 1.1222, + "step": 623 + }, + { + "epoch": 0.038306884803094014, + "grad_norm": 0.8275971309559446, + "learning_rate": 1.999639755768133e-05, + "loss": 1.2195, + "step": 624 + }, + { + "epoch": 0.03836827404156051, + "grad_norm": 0.7548409920861079, + "learning_rate": 1.9996343993764896e-05, + "loss": 1.1663, + "step": 625 + }, + { + "epoch": 0.03842966328002701, + "grad_norm": 0.7782396289254079, + "learning_rate": 1.9996290034639517e-05, + "loss": 1.1028, + "step": 626 + }, + { + "epoch": 0.03849105251849351, + "grad_norm": 0.778566181460576, + "learning_rate": 1.999623568030733e-05, + "loss": 1.1697, + "step": 627 + }, + { + "epoch": 0.03855244175696001, + "grad_norm": 0.7510053702911115, + "learning_rate": 1.9996180930770484e-05, + "loss": 1.1311, + "step": 628 + }, + { + "epoch": 0.0386138309954265, + "grad_norm": 0.779438699506071, + "learning_rate": 1.999612578603114e-05, + "loss": 1.162, + "step": 629 + }, + { + "epoch": 0.038675220233893, + "grad_norm": 0.7660350027614419, + "learning_rate": 1.999607024609148e-05, + "loss": 1.1548, + "step": 630 + }, + { + "epoch": 0.0387366094723595, + "grad_norm": 0.728512915665705, + "learning_rate": 1.9996014310953704e-05, + "loss": 1.138, + "step": 631 + }, + { + "epoch": 0.038797998710825995, + "grad_norm": 0.7722311296231772, + "learning_rate": 1.9995957980620016e-05, + "loss": 1.1711, + "step": 632 + }, + { + "epoch": 0.03885938794929249, + "grad_norm": 0.7319656154212063, + "learning_rate": 1.9995901255092648e-05, + "loss": 1.1287, + "step": 633 + }, + { + "epoch": 0.038920777187758986, + "grad_norm": 0.8687482786893576, + "learning_rate": 1.999584413437384e-05, + "loss": 1.1939, + "step": 634 + }, + { + "epoch": 0.038982166426225484, + "grad_norm": 0.7348985331888599, + "learning_rate": 1.9995786618465858e-05, + "loss": 1.1705, + "step": 635 + }, + { + "epoch": 0.03904355566469198, + "grad_norm": 0.7011962909676503, + "learning_rate": 1.9995728707370966e-05, + "loss": 1.0874, + "step": 636 + }, + { + "epoch": 0.039104944903158474, + "grad_norm": 0.7221143137598672, + "learning_rate": 1.999567040109146e-05, + "loss": 1.0981, + "step": 637 + }, + { + "epoch": 0.03916633414162497, + "grad_norm": 0.7275476620219322, + "learning_rate": 1.9995611699629637e-05, + "loss": 1.1178, + "step": 638 + }, + { + "epoch": 0.03922772338009147, + "grad_norm": 0.739928514681386, + "learning_rate": 1.9995552602987828e-05, + "loss": 1.1038, + "step": 639 + }, + { + "epoch": 0.03928911261855797, + "grad_norm": 0.7362001667040914, + "learning_rate": 1.999549311116836e-05, + "loss": 1.1083, + "step": 640 + }, + { + "epoch": 0.03935050185702446, + "grad_norm": 0.7175991015572127, + "learning_rate": 1.9995433224173594e-05, + "loss": 1.1033, + "step": 641 + }, + { + "epoch": 0.03941189109549096, + "grad_norm": 0.6968416036609814, + "learning_rate": 1.9995372942005888e-05, + "loss": 1.1233, + "step": 642 + }, + { + "epoch": 0.03947328033395746, + "grad_norm": 0.8122775823454859, + "learning_rate": 1.9995312264667636e-05, + "loss": 1.2069, + "step": 643 + }, + { + "epoch": 0.03953466957242396, + "grad_norm": 0.7413084866172499, + "learning_rate": 1.9995251192161226e-05, + "loss": 1.1367, + "step": 644 + }, + { + "epoch": 0.03959605881089045, + "grad_norm": 0.745615312385089, + "learning_rate": 1.9995189724489084e-05, + "loss": 1.1482, + "step": 645 + }, + { + "epoch": 0.03965744804935695, + "grad_norm": 0.775709089742677, + "learning_rate": 1.9995127861653632e-05, + "loss": 1.174, + "step": 646 + }, + { + "epoch": 0.039718837287823446, + "grad_norm": 0.7396364640305115, + "learning_rate": 1.9995065603657317e-05, + "loss": 1.1206, + "step": 647 + }, + { + "epoch": 0.039780226526289944, + "grad_norm": 0.7599464807604869, + "learning_rate": 1.9995002950502602e-05, + "loss": 1.0993, + "step": 648 + }, + { + "epoch": 0.039841615764756436, + "grad_norm": 0.7293531175257174, + "learning_rate": 1.9994939902191964e-05, + "loss": 1.1508, + "step": 649 + }, + { + "epoch": 0.039903005003222934, + "grad_norm": 0.8166565660139974, + "learning_rate": 1.9994876458727896e-05, + "loss": 1.2308, + "step": 650 + }, + { + "epoch": 0.03996439424168943, + "grad_norm": 0.7649977975163564, + "learning_rate": 1.99948126201129e-05, + "loss": 1.1745, + "step": 651 + }, + { + "epoch": 0.04002578348015593, + "grad_norm": 0.7437024496534809, + "learning_rate": 1.999474838634951e-05, + "loss": 1.16, + "step": 652 + }, + { + "epoch": 0.04008717271862242, + "grad_norm": 0.8193141962551246, + "learning_rate": 1.999468375744026e-05, + "loss": 1.2246, + "step": 653 + }, + { + "epoch": 0.04014856195708892, + "grad_norm": 0.7564800141712472, + "learning_rate": 1.9994618733387705e-05, + "loss": 1.161, + "step": 654 + }, + { + "epoch": 0.04020995119555542, + "grad_norm": 0.7783680840836504, + "learning_rate": 1.9994553314194415e-05, + "loss": 1.1418, + "step": 655 + }, + { + "epoch": 0.04027134043402192, + "grad_norm": 0.7667881789280312, + "learning_rate": 1.999448749986298e-05, + "loss": 1.1415, + "step": 656 + }, + { + "epoch": 0.04033272967248841, + "grad_norm": 0.7554609848362362, + "learning_rate": 1.9994421290395997e-05, + "loss": 1.1253, + "step": 657 + }, + { + "epoch": 0.04039411891095491, + "grad_norm": 0.7802874476711601, + "learning_rate": 1.9994354685796093e-05, + "loss": 1.1806, + "step": 658 + }, + { + "epoch": 0.04045550814942141, + "grad_norm": 0.7503485087794631, + "learning_rate": 1.9994287686065886e-05, + "loss": 1.1705, + "step": 659 + }, + { + "epoch": 0.040516897387887905, + "grad_norm": 0.6729100045595446, + "learning_rate": 1.999422029120804e-05, + "loss": 1.1078, + "step": 660 + }, + { + "epoch": 0.0405782866263544, + "grad_norm": 0.743117831743013, + "learning_rate": 1.999415250122521e-05, + "loss": 1.1405, + "step": 661 + }, + { + "epoch": 0.040639675864820896, + "grad_norm": 0.7589763428448535, + "learning_rate": 1.999408431612008e-05, + "loss": 1.2158, + "step": 662 + }, + { + "epoch": 0.040701065103287394, + "grad_norm": 0.7216954839711865, + "learning_rate": 1.9994015735895343e-05, + "loss": 1.1388, + "step": 663 + }, + { + "epoch": 0.04076245434175389, + "grad_norm": 0.7453862763157447, + "learning_rate": 1.9993946760553717e-05, + "loss": 1.1628, + "step": 664 + }, + { + "epoch": 0.040823843580220384, + "grad_norm": 0.7158106447018608, + "learning_rate": 1.999387739009792e-05, + "loss": 1.1695, + "step": 665 + }, + { + "epoch": 0.04088523281868688, + "grad_norm": 0.7193536275848171, + "learning_rate": 1.99938076245307e-05, + "loss": 1.1041, + "step": 666 + }, + { + "epoch": 0.04094662205715338, + "grad_norm": 0.7873798179029791, + "learning_rate": 1.9993737463854814e-05, + "loss": 1.2006, + "step": 667 + }, + { + "epoch": 0.04100801129561988, + "grad_norm": 0.7082291834362182, + "learning_rate": 1.9993666908073037e-05, + "loss": 1.1093, + "step": 668 + }, + { + "epoch": 0.04106940053408637, + "grad_norm": 0.7961384596162016, + "learning_rate": 1.9993595957188153e-05, + "loss": 1.208, + "step": 669 + }, + { + "epoch": 0.04113078977255287, + "grad_norm": 0.7177135199595838, + "learning_rate": 1.9993524611202976e-05, + "loss": 1.1321, + "step": 670 + }, + { + "epoch": 0.04119217901101937, + "grad_norm": 0.8614145604540313, + "learning_rate": 1.999345287012032e-05, + "loss": 1.1978, + "step": 671 + }, + { + "epoch": 0.04125356824948587, + "grad_norm": 0.7477736363103697, + "learning_rate": 1.9993380733943023e-05, + "loss": 1.1035, + "step": 672 + }, + { + "epoch": 0.041314957487952365, + "grad_norm": 0.7480277910354071, + "learning_rate": 1.9993308202673936e-05, + "loss": 1.1555, + "step": 673 + }, + { + "epoch": 0.04137634672641886, + "grad_norm": 0.787913827568302, + "learning_rate": 1.9993235276315933e-05, + "loss": 1.152, + "step": 674 + }, + { + "epoch": 0.041437735964885355, + "grad_norm": 0.7205017455802788, + "learning_rate": 1.9993161954871887e-05, + "loss": 1.0941, + "step": 675 + }, + { + "epoch": 0.041499125203351854, + "grad_norm": 0.7570435957722003, + "learning_rate": 1.9993088238344704e-05, + "loss": 1.1637, + "step": 676 + }, + { + "epoch": 0.04156051444181835, + "grad_norm": 0.7828182009927438, + "learning_rate": 1.9993014126737296e-05, + "loss": 1.1528, + "step": 677 + }, + { + "epoch": 0.041621903680284844, + "grad_norm": 0.7597241211822304, + "learning_rate": 1.9992939620052593e-05, + "loss": 1.1324, + "step": 678 + }, + { + "epoch": 0.04168329291875134, + "grad_norm": 0.7414861334033302, + "learning_rate": 1.9992864718293542e-05, + "loss": 1.153, + "step": 679 + }, + { + "epoch": 0.04174468215721784, + "grad_norm": 0.7966738987436641, + "learning_rate": 1.99927894214631e-05, + "loss": 1.2156, + "step": 680 + }, + { + "epoch": 0.04180607139568434, + "grad_norm": 0.7451548811484917, + "learning_rate": 1.9992713729564248e-05, + "loss": 1.1818, + "step": 681 + }, + { + "epoch": 0.04186746063415083, + "grad_norm": 0.7394141998968435, + "learning_rate": 1.9992637642599977e-05, + "loss": 1.1361, + "step": 682 + }, + { + "epoch": 0.04192884987261733, + "grad_norm": 0.7828371953796316, + "learning_rate": 1.99925611605733e-05, + "loss": 1.1314, + "step": 683 + }, + { + "epoch": 0.04199023911108383, + "grad_norm": 0.6682537222579537, + "learning_rate": 1.999248428348723e-05, + "loss": 1.052, + "step": 684 + }, + { + "epoch": 0.04205162834955033, + "grad_norm": 0.7276202355568778, + "learning_rate": 1.9992407011344818e-05, + "loss": 1.1689, + "step": 685 + }, + { + "epoch": 0.04211301758801682, + "grad_norm": 0.747740510626253, + "learning_rate": 1.999232934414911e-05, + "loss": 1.2042, + "step": 686 + }, + { + "epoch": 0.04217440682648332, + "grad_norm": 0.7058222239023345, + "learning_rate": 1.999225128190318e-05, + "loss": 1.1354, + "step": 687 + }, + { + "epoch": 0.042235796064949815, + "grad_norm": 0.6779022147844141, + "learning_rate": 1.999217282461012e-05, + "loss": 1.0549, + "step": 688 + }, + { + "epoch": 0.042297185303416314, + "grad_norm": 0.7397154792114042, + "learning_rate": 1.999209397227302e-05, + "loss": 1.1447, + "step": 689 + }, + { + "epoch": 0.042358574541882806, + "grad_norm": 0.7562122224609771, + "learning_rate": 1.9992014724895007e-05, + "loss": 1.1171, + "step": 690 + }, + { + "epoch": 0.042419963780349304, + "grad_norm": 0.7102930462158082, + "learning_rate": 1.999193508247921e-05, + "loss": 1.1375, + "step": 691 + }, + { + "epoch": 0.0424813530188158, + "grad_norm": 0.7302780143985326, + "learning_rate": 1.9991855045028777e-05, + "loss": 1.1213, + "step": 692 + }, + { + "epoch": 0.0425427422572823, + "grad_norm": 0.6707567536134376, + "learning_rate": 1.9991774612546878e-05, + "loss": 1.104, + "step": 693 + }, + { + "epoch": 0.04260413149574879, + "grad_norm": 0.7240291771553814, + "learning_rate": 1.9991693785036686e-05, + "loss": 1.1587, + "step": 694 + }, + { + "epoch": 0.04266552073421529, + "grad_norm": 0.7094417503247543, + "learning_rate": 1.99916125625014e-05, + "loss": 1.1532, + "step": 695 + }, + { + "epoch": 0.04272690997268179, + "grad_norm": 0.6884481750303952, + "learning_rate": 1.999153094494423e-05, + "loss": 1.0874, + "step": 696 + }, + { + "epoch": 0.04278829921114829, + "grad_norm": 0.7097577898046603, + "learning_rate": 1.9991448932368404e-05, + "loss": 1.1084, + "step": 697 + }, + { + "epoch": 0.04284968844961478, + "grad_norm": 0.7656956184375354, + "learning_rate": 1.9991366524777162e-05, + "loss": 1.1746, + "step": 698 + }, + { + "epoch": 0.04291107768808128, + "grad_norm": 0.7734773990630841, + "learning_rate": 1.9991283722173765e-05, + "loss": 1.1493, + "step": 699 + }, + { + "epoch": 0.04297246692654778, + "grad_norm": 0.7415565812460126, + "learning_rate": 1.9991200524561486e-05, + "loss": 1.1644, + "step": 700 + }, + { + "epoch": 0.043033856165014275, + "grad_norm": 0.7254591424953727, + "learning_rate": 1.9991116931943612e-05, + "loss": 1.1357, + "step": 701 + }, + { + "epoch": 0.04309524540348077, + "grad_norm": 0.7085582952539793, + "learning_rate": 1.9991032944323453e-05, + "loss": 1.1048, + "step": 702 + }, + { + "epoch": 0.043156634641947265, + "grad_norm": 0.7539119308579981, + "learning_rate": 1.999094856170432e-05, + "loss": 1.1526, + "step": 703 + }, + { + "epoch": 0.043218023880413764, + "grad_norm": 0.7607983574262258, + "learning_rate": 1.999086378408956e-05, + "loss": 1.1431, + "step": 704 + }, + { + "epoch": 0.04327941311888026, + "grad_norm": 0.7197074510281708, + "learning_rate": 1.999077861148252e-05, + "loss": 1.1858, + "step": 705 + }, + { + "epoch": 0.043340802357346754, + "grad_norm": 0.7050539335610922, + "learning_rate": 1.999069304388656e-05, + "loss": 1.0954, + "step": 706 + }, + { + "epoch": 0.04340219159581325, + "grad_norm": 0.714898490172679, + "learning_rate": 1.9990607081305077e-05, + "loss": 1.1274, + "step": 707 + }, + { + "epoch": 0.04346358083427975, + "grad_norm": 0.7347928252080688, + "learning_rate": 1.999052072374146e-05, + "loss": 1.1244, + "step": 708 + }, + { + "epoch": 0.04352497007274625, + "grad_norm": 0.7169849337266591, + "learning_rate": 1.9990433971199125e-05, + "loss": 1.1253, + "step": 709 + }, + { + "epoch": 0.04358635931121274, + "grad_norm": 0.7890256227521136, + "learning_rate": 1.9990346823681506e-05, + "loss": 1.1892, + "step": 710 + }, + { + "epoch": 0.04364774854967924, + "grad_norm": 0.7660896558500344, + "learning_rate": 1.999025928119204e-05, + "loss": 1.1869, + "step": 711 + }, + { + "epoch": 0.04370913778814574, + "grad_norm": 0.7582350408451911, + "learning_rate": 1.9990171343734198e-05, + "loss": 1.1758, + "step": 712 + }, + { + "epoch": 0.04377052702661224, + "grad_norm": 0.718164720723471, + "learning_rate": 1.999008301131145e-05, + "loss": 1.1215, + "step": 713 + }, + { + "epoch": 0.04383191626507873, + "grad_norm": 0.7152990578214419, + "learning_rate": 1.9989994283927287e-05, + "loss": 1.122, + "step": 714 + }, + { + "epoch": 0.04389330550354523, + "grad_norm": 0.7599565586893884, + "learning_rate": 1.9989905161585223e-05, + "loss": 1.1619, + "step": 715 + }, + { + "epoch": 0.043954694742011725, + "grad_norm": 0.7081042070882334, + "learning_rate": 1.9989815644288778e-05, + "loss": 1.0917, + "step": 716 + }, + { + "epoch": 0.044016083980478224, + "grad_norm": 0.7560295217365395, + "learning_rate": 1.998972573204149e-05, + "loss": 1.1878, + "step": 717 + }, + { + "epoch": 0.04407747321894472, + "grad_norm": 0.6671903814101862, + "learning_rate": 1.9989635424846913e-05, + "loss": 1.077, + "step": 718 + }, + { + "epoch": 0.044138862457411214, + "grad_norm": 0.7297234844391133, + "learning_rate": 1.9989544722708622e-05, + "loss": 1.1534, + "step": 719 + }, + { + "epoch": 0.04420025169587771, + "grad_norm": 0.7824904338568159, + "learning_rate": 1.99894536256302e-05, + "loss": 1.0942, + "step": 720 + }, + { + "epoch": 0.04426164093434421, + "grad_norm": 0.7306751805047218, + "learning_rate": 1.9989362133615248e-05, + "loss": 1.1657, + "step": 721 + }, + { + "epoch": 0.04432303017281071, + "grad_norm": 0.7111904137119877, + "learning_rate": 1.9989270246667385e-05, + "loss": 1.1559, + "step": 722 + }, + { + "epoch": 0.0443844194112772, + "grad_norm": 0.7511373628245224, + "learning_rate": 1.998917796479024e-05, + "loss": 1.1662, + "step": 723 + }, + { + "epoch": 0.0444458086497437, + "grad_norm": 0.8054539614811788, + "learning_rate": 1.998908528798747e-05, + "loss": 1.1647, + "step": 724 + }, + { + "epoch": 0.0445071978882102, + "grad_norm": 0.7078039044246675, + "learning_rate": 1.9988992216262727e-05, + "loss": 1.0931, + "step": 725 + }, + { + "epoch": 0.0445685871266767, + "grad_norm": 0.7132056078250603, + "learning_rate": 1.9988898749619702e-05, + "loss": 1.1253, + "step": 726 + }, + { + "epoch": 0.04462997636514319, + "grad_norm": 0.7052837852929476, + "learning_rate": 1.9988804888062083e-05, + "loss": 1.1008, + "step": 727 + }, + { + "epoch": 0.04469136560360969, + "grad_norm": 0.7544915384210167, + "learning_rate": 1.998871063159358e-05, + "loss": 1.1528, + "step": 728 + }, + { + "epoch": 0.044752754842076185, + "grad_norm": 0.7747700518760225, + "learning_rate": 1.9988615980217926e-05, + "loss": 1.1416, + "step": 729 + }, + { + "epoch": 0.044814144080542684, + "grad_norm": 0.749496302274901, + "learning_rate": 1.998852093393886e-05, + "loss": 1.1685, + "step": 730 + }, + { + "epoch": 0.044875533319009175, + "grad_norm": 0.7354741728713704, + "learning_rate": 1.9988425492760135e-05, + "loss": 1.1039, + "step": 731 + }, + { + "epoch": 0.044936922557475674, + "grad_norm": 0.7226116822755123, + "learning_rate": 1.9988329656685534e-05, + "loss": 1.1702, + "step": 732 + }, + { + "epoch": 0.04499831179594217, + "grad_norm": 0.7281026368210655, + "learning_rate": 1.9988233425718834e-05, + "loss": 1.1506, + "step": 733 + }, + { + "epoch": 0.04505970103440867, + "grad_norm": 0.744546446647622, + "learning_rate": 1.998813679986385e-05, + "loss": 1.1581, + "step": 734 + }, + { + "epoch": 0.04512109027287516, + "grad_norm": 0.7067066118437789, + "learning_rate": 1.9988039779124397e-05, + "loss": 1.1205, + "step": 735 + }, + { + "epoch": 0.04518247951134166, + "grad_norm": 0.7895017234654704, + "learning_rate": 1.998794236350431e-05, + "loss": 1.2113, + "step": 736 + }, + { + "epoch": 0.04524386874980816, + "grad_norm": 0.7504811381097671, + "learning_rate": 1.9987844553007444e-05, + "loss": 1.1744, + "step": 737 + }, + { + "epoch": 0.04530525798827466, + "grad_norm": 0.7579015137523307, + "learning_rate": 1.9987746347637667e-05, + "loss": 1.1952, + "step": 738 + }, + { + "epoch": 0.04536664722674115, + "grad_norm": 0.7065761435424049, + "learning_rate": 1.9987647747398854e-05, + "loss": 1.0851, + "step": 739 + }, + { + "epoch": 0.04542803646520765, + "grad_norm": 0.7250531078210584, + "learning_rate": 1.998754875229491e-05, + "loss": 1.1067, + "step": 740 + }, + { + "epoch": 0.04548942570367415, + "grad_norm": 0.7337294784172627, + "learning_rate": 1.9987449362329746e-05, + "loss": 1.1613, + "step": 741 + }, + { + "epoch": 0.045550814942140645, + "grad_norm": 0.6951092288500983, + "learning_rate": 1.9987349577507292e-05, + "loss": 1.1052, + "step": 742 + }, + { + "epoch": 0.04561220418060714, + "grad_norm": 0.7328377114301406, + "learning_rate": 1.9987249397831495e-05, + "loss": 1.168, + "step": 743 + }, + { + "epoch": 0.045673593419073635, + "grad_norm": 0.7223607275225179, + "learning_rate": 1.998714882330631e-05, + "loss": 1.1544, + "step": 744 + }, + { + "epoch": 0.045734982657540134, + "grad_norm": 0.7534260001855979, + "learning_rate": 1.998704785393572e-05, + "loss": 1.1243, + "step": 745 + }, + { + "epoch": 0.04579637189600663, + "grad_norm": 0.7252693647254349, + "learning_rate": 1.9986946489723712e-05, + "loss": 1.101, + "step": 746 + }, + { + "epoch": 0.045857761134473124, + "grad_norm": 0.747757021482102, + "learning_rate": 1.9986844730674297e-05, + "loss": 1.1642, + "step": 747 + }, + { + "epoch": 0.04591915037293962, + "grad_norm": 0.7324536638187307, + "learning_rate": 1.9986742576791495e-05, + "loss": 1.1518, + "step": 748 + }, + { + "epoch": 0.04598053961140612, + "grad_norm": 0.7071091204417692, + "learning_rate": 1.9986640028079348e-05, + "loss": 1.0844, + "step": 749 + }, + { + "epoch": 0.04604192884987262, + "grad_norm": 0.7808708077457156, + "learning_rate": 1.9986537084541905e-05, + "loss": 1.1554, + "step": 750 + }, + { + "epoch": 0.04610331808833911, + "grad_norm": 0.7622222874443106, + "learning_rate": 1.998643374618324e-05, + "loss": 1.2015, + "step": 751 + }, + { + "epoch": 0.04616470732680561, + "grad_norm": 0.6868487452202546, + "learning_rate": 1.998633001300744e-05, + "loss": 1.1172, + "step": 752 + }, + { + "epoch": 0.04622609656527211, + "grad_norm": 0.803803836623923, + "learning_rate": 1.9986225885018604e-05, + "loss": 1.2499, + "step": 753 + }, + { + "epoch": 0.04628748580373861, + "grad_norm": 0.7362045472183932, + "learning_rate": 1.998612136222085e-05, + "loss": 1.1688, + "step": 754 + }, + { + "epoch": 0.0463488750422051, + "grad_norm": 0.7226807449138658, + "learning_rate": 1.9986016444618302e-05, + "loss": 1.1085, + "step": 755 + }, + { + "epoch": 0.0464102642806716, + "grad_norm": 0.7253105705433878, + "learning_rate": 1.9985911132215122e-05, + "loss": 1.1924, + "step": 756 + }, + { + "epoch": 0.046471653519138095, + "grad_norm": 0.7246520728892619, + "learning_rate": 1.9985805425015466e-05, + "loss": 1.1462, + "step": 757 + }, + { + "epoch": 0.046533042757604594, + "grad_norm": 0.6949381300317188, + "learning_rate": 1.9985699323023507e-05, + "loss": 1.0891, + "step": 758 + }, + { + "epoch": 0.046594431996071085, + "grad_norm": 0.7414285175616028, + "learning_rate": 1.9985592826243454e-05, + "loss": 1.1608, + "step": 759 + }, + { + "epoch": 0.046655821234537584, + "grad_norm": 0.7256446189563095, + "learning_rate": 1.9985485934679508e-05, + "loss": 1.0694, + "step": 760 + }, + { + "epoch": 0.04671721047300408, + "grad_norm": 0.7280218923111027, + "learning_rate": 1.9985378648335897e-05, + "loss": 1.1422, + "step": 761 + }, + { + "epoch": 0.04677859971147058, + "grad_norm": 0.7287114536618953, + "learning_rate": 1.998527096721686e-05, + "loss": 1.1615, + "step": 762 + }, + { + "epoch": 0.04683998894993708, + "grad_norm": 0.7548121358979691, + "learning_rate": 1.998516289132666e-05, + "loss": 1.1415, + "step": 763 + }, + { + "epoch": 0.04690137818840357, + "grad_norm": 0.7433062098327233, + "learning_rate": 1.9985054420669562e-05, + "loss": 1.101, + "step": 764 + }, + { + "epoch": 0.04696276742687007, + "grad_norm": 0.736090068086758, + "learning_rate": 1.9984945555249865e-05, + "loss": 1.1345, + "step": 765 + }, + { + "epoch": 0.04702415666533657, + "grad_norm": 0.7157407893609404, + "learning_rate": 1.9984836295071863e-05, + "loss": 1.1314, + "step": 766 + }, + { + "epoch": 0.04708554590380307, + "grad_norm": 0.7342913051956615, + "learning_rate": 1.998472664013988e-05, + "loss": 1.173, + "step": 767 + }, + { + "epoch": 0.04714693514226956, + "grad_norm": 0.7494999818444803, + "learning_rate": 1.998461659045825e-05, + "loss": 1.1262, + "step": 768 + }, + { + "epoch": 0.04720832438073606, + "grad_norm": 0.7134225000708558, + "learning_rate": 1.9984506146031327e-05, + "loss": 1.0905, + "step": 769 + }, + { + "epoch": 0.047269713619202555, + "grad_norm": 0.7534344934027637, + "learning_rate": 1.9984395306863473e-05, + "loss": 1.1567, + "step": 770 + }, + { + "epoch": 0.047331102857669054, + "grad_norm": 0.7190049357245003, + "learning_rate": 1.9984284072959075e-05, + "loss": 1.1281, + "step": 771 + }, + { + "epoch": 0.047392492096135545, + "grad_norm": 0.7202800928225384, + "learning_rate": 1.9984172444322524e-05, + "loss": 0.8226, + "step": 772 + }, + { + "epoch": 0.047453881334602044, + "grad_norm": 0.730276794289433, + "learning_rate": 1.998406042095824e-05, + "loss": 1.1289, + "step": 773 + }, + { + "epoch": 0.04751527057306854, + "grad_norm": 0.7702504000778595, + "learning_rate": 1.998394800287065e-05, + "loss": 1.1452, + "step": 774 + }, + { + "epoch": 0.04757665981153504, + "grad_norm": 0.6841256067565002, + "learning_rate": 1.9983835190064194e-05, + "loss": 1.1142, + "step": 775 + }, + { + "epoch": 0.04763804905000153, + "grad_norm": 0.7247000261475215, + "learning_rate": 1.998372198254334e-05, + "loss": 1.1496, + "step": 776 + }, + { + "epoch": 0.04769943828846803, + "grad_norm": 0.7411563683283392, + "learning_rate": 1.9983608380312557e-05, + "loss": 1.1197, + "step": 777 + }, + { + "epoch": 0.04776082752693453, + "grad_norm": 0.6872731810451462, + "learning_rate": 1.9983494383376337e-05, + "loss": 1.1191, + "step": 778 + }, + { + "epoch": 0.04782221676540103, + "grad_norm": 0.7207563831434974, + "learning_rate": 1.998337999173919e-05, + "loss": 1.1286, + "step": 779 + }, + { + "epoch": 0.04788360600386752, + "grad_norm": 0.7635404282661882, + "learning_rate": 1.998326520540564e-05, + "loss": 1.1917, + "step": 780 + }, + { + "epoch": 0.04794499524233402, + "grad_norm": 0.7244539463007917, + "learning_rate": 1.9983150024380216e-05, + "loss": 1.0968, + "step": 781 + }, + { + "epoch": 0.04800638448080052, + "grad_norm": 0.7261632413702777, + "learning_rate": 1.998303444866748e-05, + "loss": 1.0779, + "step": 782 + }, + { + "epoch": 0.048067773719267015, + "grad_norm": 0.6823554599565703, + "learning_rate": 1.9982918478272e-05, + "loss": 1.0755, + "step": 783 + }, + { + "epoch": 0.04812916295773351, + "grad_norm": 0.6822694841607303, + "learning_rate": 1.9982802113198364e-05, + "loss": 1.0987, + "step": 784 + }, + { + "epoch": 0.048190552196200005, + "grad_norm": 0.7836920389042026, + "learning_rate": 1.9982685353451162e-05, + "loss": 1.2005, + "step": 785 + }, + { + "epoch": 0.048251941434666504, + "grad_norm": 0.7634079405319806, + "learning_rate": 1.9982568199035023e-05, + "loss": 1.1533, + "step": 786 + }, + { + "epoch": 0.048313330673133, + "grad_norm": 0.7190974093136395, + "learning_rate": 1.9982450649954568e-05, + "loss": 1.1292, + "step": 787 + }, + { + "epoch": 0.048374719911599494, + "grad_norm": 0.7289411652631115, + "learning_rate": 1.998233270621445e-05, + "loss": 1.1575, + "step": 788 + }, + { + "epoch": 0.04843610915006599, + "grad_norm": 0.7656628408242938, + "learning_rate": 1.998221436781933e-05, + "loss": 1.1682, + "step": 789 + }, + { + "epoch": 0.04849749838853249, + "grad_norm": 0.7515065288080464, + "learning_rate": 1.998209563477389e-05, + "loss": 1.1761, + "step": 790 + }, + { + "epoch": 0.04855888762699899, + "grad_norm": 0.6272621729292625, + "learning_rate": 1.998197650708282e-05, + "loss": 0.7934, + "step": 791 + }, + { + "epoch": 0.04862027686546548, + "grad_norm": 0.7241484098709282, + "learning_rate": 1.998185698475083e-05, + "loss": 1.0988, + "step": 792 + }, + { + "epoch": 0.04868166610393198, + "grad_norm": 0.7437297867976583, + "learning_rate": 1.998173706778265e-05, + "loss": 1.1743, + "step": 793 + }, + { + "epoch": 0.04874305534239848, + "grad_norm": 0.7582568971867396, + "learning_rate": 1.9981616756183015e-05, + "loss": 1.2054, + "step": 794 + }, + { + "epoch": 0.04880444458086498, + "grad_norm": 0.7437917872014516, + "learning_rate": 1.9981496049956686e-05, + "loss": 1.1493, + "step": 795 + }, + { + "epoch": 0.04886583381933147, + "grad_norm": 0.7852479556260966, + "learning_rate": 1.9981374949108434e-05, + "loss": 1.1948, + "step": 796 + }, + { + "epoch": 0.04892722305779797, + "grad_norm": 0.7578763959492948, + "learning_rate": 1.9981253453643043e-05, + "loss": 1.1979, + "step": 797 + }, + { + "epoch": 0.048988612296264465, + "grad_norm": 0.7277533577108973, + "learning_rate": 1.9981131563565324e-05, + "loss": 1.0896, + "step": 798 + }, + { + "epoch": 0.049050001534730964, + "grad_norm": 0.707677703062527, + "learning_rate": 1.9981009278880087e-05, + "loss": 1.0671, + "step": 799 + }, + { + "epoch": 0.049111390773197455, + "grad_norm": 0.748204957645314, + "learning_rate": 1.9980886599592172e-05, + "loss": 1.1081, + "step": 800 + }, + { + "epoch": 0.049172780011663954, + "grad_norm": 0.7381205771138163, + "learning_rate": 1.9980763525706427e-05, + "loss": 1.1719, + "step": 801 + }, + { + "epoch": 0.04923416925013045, + "grad_norm": 0.7530172327482457, + "learning_rate": 1.9980640057227724e-05, + "loss": 1.1128, + "step": 802 + }, + { + "epoch": 0.04929555848859695, + "grad_norm": 0.6992475939345937, + "learning_rate": 1.9980516194160934e-05, + "loss": 1.0989, + "step": 803 + }, + { + "epoch": 0.04935694772706344, + "grad_norm": 0.7306616617180522, + "learning_rate": 1.998039193651096e-05, + "loss": 1.0689, + "step": 804 + }, + { + "epoch": 0.04941833696552994, + "grad_norm": 0.7932469361744703, + "learning_rate": 1.9980267284282718e-05, + "loss": 1.1843, + "step": 805 + }, + { + "epoch": 0.04947972620399644, + "grad_norm": 0.7222638032703429, + "learning_rate": 1.9980142237481127e-05, + "loss": 1.0842, + "step": 806 + }, + { + "epoch": 0.04954111544246294, + "grad_norm": 0.8001336788959622, + "learning_rate": 1.9980016796111138e-05, + "loss": 1.1381, + "step": 807 + }, + { + "epoch": 0.049602504680929436, + "grad_norm": 0.7148563212413472, + "learning_rate": 1.997989096017771e-05, + "loss": 1.1316, + "step": 808 + }, + { + "epoch": 0.04966389391939593, + "grad_norm": 0.6975950811294557, + "learning_rate": 1.9979764729685812e-05, + "loss": 1.1293, + "step": 809 + }, + { + "epoch": 0.04972528315786243, + "grad_norm": 0.7556131054819691, + "learning_rate": 1.9979638104640443e-05, + "loss": 1.0694, + "step": 810 + }, + { + "epoch": 0.049786672396328925, + "grad_norm": 0.7192221570835338, + "learning_rate": 1.99795110850466e-05, + "loss": 1.1266, + "step": 811 + }, + { + "epoch": 0.049848061634795424, + "grad_norm": 0.7134368014470679, + "learning_rate": 1.9979383670909316e-05, + "loss": 1.118, + "step": 812 + }, + { + "epoch": 0.049909450873261915, + "grad_norm": 0.7794160903676629, + "learning_rate": 1.9979255862233618e-05, + "loss": 1.1587, + "step": 813 + }, + { + "epoch": 0.049970840111728414, + "grad_norm": 0.7199056012880688, + "learning_rate": 1.9979127659024563e-05, + "loss": 1.1346, + "step": 814 + }, + { + "epoch": 0.05003222935019491, + "grad_norm": 0.7267680979015805, + "learning_rate": 1.9978999061287218e-05, + "loss": 1.0688, + "step": 815 + }, + { + "epoch": 0.05009361858866141, + "grad_norm": 0.7489975119219207, + "learning_rate": 1.9978870069026674e-05, + "loss": 1.1411, + "step": 816 + }, + { + "epoch": 0.0501550078271279, + "grad_norm": 0.7886121207793451, + "learning_rate": 1.9978740682248022e-05, + "loss": 1.1988, + "step": 817 + }, + { + "epoch": 0.0502163970655944, + "grad_norm": 0.715532146122128, + "learning_rate": 1.9978610900956382e-05, + "loss": 1.0892, + "step": 818 + }, + { + "epoch": 0.0502777863040609, + "grad_norm": 0.7317696749303969, + "learning_rate": 1.997848072515688e-05, + "loss": 1.1325, + "step": 819 + }, + { + "epoch": 0.0503391755425274, + "grad_norm": 0.7065643166474604, + "learning_rate": 1.997835015485467e-05, + "loss": 1.1191, + "step": 820 + }, + { + "epoch": 0.05040056478099389, + "grad_norm": 0.7532452031757954, + "learning_rate": 1.9978219190054908e-05, + "loss": 1.0988, + "step": 821 + }, + { + "epoch": 0.05046195401946039, + "grad_norm": 0.7350099745565847, + "learning_rate": 1.9978087830762775e-05, + "loss": 1.1152, + "step": 822 + }, + { + "epoch": 0.050523343257926887, + "grad_norm": 0.8046183211043797, + "learning_rate": 1.9977956076983464e-05, + "loss": 1.1605, + "step": 823 + }, + { + "epoch": 0.050584732496393385, + "grad_norm": 0.7369028226538585, + "learning_rate": 1.9977823928722184e-05, + "loss": 1.0826, + "step": 824 + }, + { + "epoch": 0.05064612173485988, + "grad_norm": 0.7397196010015087, + "learning_rate": 1.9977691385984158e-05, + "loss": 1.1444, + "step": 825 + }, + { + "epoch": 0.050707510973326375, + "grad_norm": 0.7436687966081014, + "learning_rate": 1.997755844877463e-05, + "loss": 1.1412, + "step": 826 + }, + { + "epoch": 0.050768900211792874, + "grad_norm": 0.7189071995400316, + "learning_rate": 1.9977425117098847e-05, + "loss": 1.117, + "step": 827 + }, + { + "epoch": 0.05083028945025937, + "grad_norm": 0.7251934743500912, + "learning_rate": 1.9977291390962092e-05, + "loss": 1.17, + "step": 828 + }, + { + "epoch": 0.050891678688725864, + "grad_norm": 0.7631810714382377, + "learning_rate": 1.9977157270369642e-05, + "loss": 1.1646, + "step": 829 + }, + { + "epoch": 0.05095306792719236, + "grad_norm": 0.7665264546353673, + "learning_rate": 1.9977022755326803e-05, + "loss": 1.1921, + "step": 830 + }, + { + "epoch": 0.05101445716565886, + "grad_norm": 0.7148682303569512, + "learning_rate": 1.9976887845838898e-05, + "loss": 1.1285, + "step": 831 + }, + { + "epoch": 0.05107584640412536, + "grad_norm": 0.719361592318689, + "learning_rate": 1.9976752541911253e-05, + "loss": 1.1123, + "step": 832 + }, + { + "epoch": 0.05113723564259185, + "grad_norm": 0.7210683893069484, + "learning_rate": 1.9976616843549218e-05, + "loss": 1.2469, + "step": 833 + }, + { + "epoch": 0.05119862488105835, + "grad_norm": 0.7225935498824239, + "learning_rate": 1.9976480750758166e-05, + "loss": 1.1148, + "step": 834 + }, + { + "epoch": 0.05126001411952485, + "grad_norm": 0.6897373172711717, + "learning_rate": 1.9976344263543467e-05, + "loss": 1.0903, + "step": 835 + }, + { + "epoch": 0.051321403357991346, + "grad_norm": 0.7559365271103914, + "learning_rate": 1.9976207381910526e-05, + "loss": 1.1596, + "step": 836 + }, + { + "epoch": 0.05138279259645784, + "grad_norm": 0.7779309783872772, + "learning_rate": 1.9976070105864747e-05, + "loss": 1.1178, + "step": 837 + }, + { + "epoch": 0.05144418183492434, + "grad_norm": 0.7147371030259492, + "learning_rate": 1.9975932435411564e-05, + "loss": 1.1271, + "step": 838 + }, + { + "epoch": 0.051505571073390835, + "grad_norm": 0.7028019141869498, + "learning_rate": 1.997579437055642e-05, + "loss": 1.0896, + "step": 839 + }, + { + "epoch": 0.051566960311857334, + "grad_norm": 0.7505884369771837, + "learning_rate": 1.9975655911304767e-05, + "loss": 1.1319, + "step": 840 + }, + { + "epoch": 0.051628349550323825, + "grad_norm": 0.8182624944407202, + "learning_rate": 1.9975517057662078e-05, + "loss": 1.1878, + "step": 841 + }, + { + "epoch": 0.051689738788790324, + "grad_norm": 0.7345421530229264, + "learning_rate": 1.997537780963385e-05, + "loss": 1.0855, + "step": 842 + }, + { + "epoch": 0.05175112802725682, + "grad_norm": 0.7243904113033043, + "learning_rate": 1.9975238167225587e-05, + "loss": 1.164, + "step": 843 + }, + { + "epoch": 0.05181251726572332, + "grad_norm": 0.6968553336751191, + "learning_rate": 1.997509813044281e-05, + "loss": 1.1313, + "step": 844 + }, + { + "epoch": 0.05187390650418981, + "grad_norm": 0.7259872008329731, + "learning_rate": 1.9974957699291045e-05, + "loss": 1.1593, + "step": 845 + }, + { + "epoch": 0.05193529574265631, + "grad_norm": 0.6965643754368576, + "learning_rate": 1.997481687377586e-05, + "loss": 1.1206, + "step": 846 + }, + { + "epoch": 0.05199668498112281, + "grad_norm": 0.7004571058983039, + "learning_rate": 1.997467565390281e-05, + "loss": 1.0792, + "step": 847 + }, + { + "epoch": 0.05205807421958931, + "grad_norm": 0.7139861425669346, + "learning_rate": 1.9974534039677486e-05, + "loss": 1.0965, + "step": 848 + }, + { + "epoch": 0.0521194634580558, + "grad_norm": 0.6837842819899979, + "learning_rate": 1.9974392031105484e-05, + "loss": 1.1215, + "step": 849 + }, + { + "epoch": 0.0521808526965223, + "grad_norm": 0.7479022778400282, + "learning_rate": 1.9974249628192414e-05, + "loss": 1.1321, + "step": 850 + }, + { + "epoch": 0.052242241934988796, + "grad_norm": 0.7439068737939654, + "learning_rate": 1.9974106830943914e-05, + "loss": 1.146, + "step": 851 + }, + { + "epoch": 0.052303631173455295, + "grad_norm": 0.7588824911093115, + "learning_rate": 1.9973963639365626e-05, + "loss": 1.1745, + "step": 852 + }, + { + "epoch": 0.052365020411921794, + "grad_norm": 0.7681807243008826, + "learning_rate": 1.9973820053463212e-05, + "loss": 1.158, + "step": 853 + }, + { + "epoch": 0.052426409650388285, + "grad_norm": 0.7531582560003983, + "learning_rate": 1.9973676073242342e-05, + "loss": 1.1554, + "step": 854 + }, + { + "epoch": 0.052487798888854784, + "grad_norm": 0.7353881797782771, + "learning_rate": 1.997353169870872e-05, + "loss": 1.1243, + "step": 855 + }, + { + "epoch": 0.05254918812732128, + "grad_norm": 0.6833125317822988, + "learning_rate": 1.9973386929868046e-05, + "loss": 1.0877, + "step": 856 + }, + { + "epoch": 0.05261057736578778, + "grad_norm": 0.7235139504337162, + "learning_rate": 1.997324176672604e-05, + "loss": 1.1483, + "step": 857 + }, + { + "epoch": 0.05267196660425427, + "grad_norm": 0.7700146281803621, + "learning_rate": 1.9973096209288454e-05, + "loss": 1.161, + "step": 858 + }, + { + "epoch": 0.05273335584272077, + "grad_norm": 0.7618306995019547, + "learning_rate": 1.9972950257561032e-05, + "loss": 1.1675, + "step": 859 + }, + { + "epoch": 0.05279474508118727, + "grad_norm": 0.7447131799469741, + "learning_rate": 1.9972803911549547e-05, + "loss": 1.1309, + "step": 860 + }, + { + "epoch": 0.05285613431965377, + "grad_norm": 0.735199485511177, + "learning_rate": 1.9972657171259784e-05, + "loss": 1.1305, + "step": 861 + }, + { + "epoch": 0.05291752355812026, + "grad_norm": 0.7206501293695079, + "learning_rate": 1.9972510036697546e-05, + "loss": 1.1486, + "step": 862 + }, + { + "epoch": 0.05297891279658676, + "grad_norm": 0.7385602356649935, + "learning_rate": 1.997236250786865e-05, + "loss": 1.163, + "step": 863 + }, + { + "epoch": 0.053040302035053256, + "grad_norm": 0.726721769705734, + "learning_rate": 1.997221458477893e-05, + "loss": 1.1457, + "step": 864 + }, + { + "epoch": 0.053101691273519755, + "grad_norm": 0.6982707495048232, + "learning_rate": 1.997206626743423e-05, + "loss": 1.1148, + "step": 865 + }, + { + "epoch": 0.053163080511986247, + "grad_norm": 0.6809491889364396, + "learning_rate": 1.9971917555840415e-05, + "loss": 1.0748, + "step": 866 + }, + { + "epoch": 0.053224469750452745, + "grad_norm": 0.7606449384314324, + "learning_rate": 1.9971768450003367e-05, + "loss": 1.1515, + "step": 867 + }, + { + "epoch": 0.053285858988919244, + "grad_norm": 0.7185811141864792, + "learning_rate": 1.9971618949928978e-05, + "loss": 1.1361, + "step": 868 + }, + { + "epoch": 0.05334724822738574, + "grad_norm": 0.6731231324512101, + "learning_rate": 1.997146905562316e-05, + "loss": 1.1255, + "step": 869 + }, + { + "epoch": 0.053408637465852234, + "grad_norm": 0.6960748267258489, + "learning_rate": 1.9971318767091843e-05, + "loss": 1.0763, + "step": 870 + }, + { + "epoch": 0.05347002670431873, + "grad_norm": 0.7104089511458213, + "learning_rate": 1.9971168084340963e-05, + "loss": 1.1238, + "step": 871 + }, + { + "epoch": 0.05353141594278523, + "grad_norm": 0.7800330825221081, + "learning_rate": 1.997101700737648e-05, + "loss": 1.1913, + "step": 872 + }, + { + "epoch": 0.05359280518125173, + "grad_norm": 0.6604326064947451, + "learning_rate": 1.997086553620436e-05, + "loss": 1.0054, + "step": 873 + }, + { + "epoch": 0.05365419441971822, + "grad_norm": 0.6857288098916402, + "learning_rate": 1.9970713670830603e-05, + "loss": 1.0822, + "step": 874 + }, + { + "epoch": 0.05371558365818472, + "grad_norm": 0.7386780163839396, + "learning_rate": 1.9970561411261206e-05, + "loss": 1.1633, + "step": 875 + }, + { + "epoch": 0.05377697289665122, + "grad_norm": 1.0436846782103062, + "learning_rate": 1.9970408757502188e-05, + "loss": 1.194, + "step": 876 + }, + { + "epoch": 0.053838362135117716, + "grad_norm": 0.7343641351259214, + "learning_rate": 1.997025570955959e-05, + "loss": 1.1432, + "step": 877 + }, + { + "epoch": 0.05389975137358421, + "grad_norm": 0.7151298443527637, + "learning_rate": 1.9970102267439458e-05, + "loss": 1.0868, + "step": 878 + }, + { + "epoch": 0.053961140612050706, + "grad_norm": 0.8001054861676057, + "learning_rate": 1.996994843114786e-05, + "loss": 1.1121, + "step": 879 + }, + { + "epoch": 0.054022529850517205, + "grad_norm": 0.7605549303635953, + "learning_rate": 1.9969794200690874e-05, + "loss": 1.1674, + "step": 880 + }, + { + "epoch": 0.054083919088983703, + "grad_norm": 0.7112898510604219, + "learning_rate": 1.9969639576074608e-05, + "loss": 1.0996, + "step": 881 + }, + { + "epoch": 0.054145308327450195, + "grad_norm": 0.7550327615149613, + "learning_rate": 1.996948455730516e-05, + "loss": 1.1344, + "step": 882 + }, + { + "epoch": 0.054206697565916694, + "grad_norm": 0.7117865810773125, + "learning_rate": 1.9969329144388673e-05, + "loss": 1.1366, + "step": 883 + }, + { + "epoch": 0.05426808680438319, + "grad_norm": 0.7435842374866539, + "learning_rate": 1.9969173337331283e-05, + "loss": 1.1428, + "step": 884 + }, + { + "epoch": 0.05432947604284969, + "grad_norm": 0.6967227947356882, + "learning_rate": 1.996901713613915e-05, + "loss": 1.0782, + "step": 885 + }, + { + "epoch": 0.05439086528131618, + "grad_norm": 0.7529251480643699, + "learning_rate": 1.9968860540818453e-05, + "loss": 1.1839, + "step": 886 + }, + { + "epoch": 0.05445225451978268, + "grad_norm": 0.7260816890939995, + "learning_rate": 1.9968703551375384e-05, + "loss": 1.134, + "step": 887 + }, + { + "epoch": 0.05451364375824918, + "grad_norm": 0.6869932343743724, + "learning_rate": 1.9968546167816142e-05, + "loss": 1.0676, + "step": 888 + }, + { + "epoch": 0.05457503299671568, + "grad_norm": 0.7061646772829867, + "learning_rate": 1.996838839014696e-05, + "loss": 1.1175, + "step": 889 + }, + { + "epoch": 0.05463642223518217, + "grad_norm": 0.6977003475674367, + "learning_rate": 1.9968230218374067e-05, + "loss": 1.0668, + "step": 890 + }, + { + "epoch": 0.05469781147364867, + "grad_norm": 0.6966480348577078, + "learning_rate": 1.9968071652503723e-05, + "loss": 1.1238, + "step": 891 + }, + { + "epoch": 0.054759200712115166, + "grad_norm": 0.6894984112662726, + "learning_rate": 1.996791269254219e-05, + "loss": 1.1079, + "step": 892 + }, + { + "epoch": 0.054820589950581665, + "grad_norm": 0.7162228127717987, + "learning_rate": 1.9967753338495755e-05, + "loss": 1.1559, + "step": 893 + }, + { + "epoch": 0.054881979189048156, + "grad_norm": 0.6845694484498657, + "learning_rate": 1.9967593590370725e-05, + "loss": 1.056, + "step": 894 + }, + { + "epoch": 0.054943368427514655, + "grad_norm": 0.7208622178889027, + "learning_rate": 1.9967433448173404e-05, + "loss": 1.1262, + "step": 895 + }, + { + "epoch": 0.055004757665981154, + "grad_norm": 0.6698901703400801, + "learning_rate": 1.9967272911910133e-05, + "loss": 1.1539, + "step": 896 + }, + { + "epoch": 0.05506614690444765, + "grad_norm": 0.7500049954354371, + "learning_rate": 1.9967111981587256e-05, + "loss": 1.088, + "step": 897 + }, + { + "epoch": 0.05512753614291415, + "grad_norm": 0.7635722318753629, + "learning_rate": 1.996695065721113e-05, + "loss": 1.172, + "step": 898 + }, + { + "epoch": 0.05518892538138064, + "grad_norm": 0.7201758666841303, + "learning_rate": 1.996678893878814e-05, + "loss": 1.1444, + "step": 899 + }, + { + "epoch": 0.05525031461984714, + "grad_norm": 0.7196665317843489, + "learning_rate": 1.9966626826324676e-05, + "loss": 1.1641, + "step": 900 + }, + { + "epoch": 0.05531170385831364, + "grad_norm": 0.7056190012486814, + "learning_rate": 1.996646431982715e-05, + "loss": 1.0929, + "step": 901 + }, + { + "epoch": 0.05537309309678014, + "grad_norm": 0.7218731785286906, + "learning_rate": 1.9966301419301985e-05, + "loss": 1.1166, + "step": 902 + }, + { + "epoch": 0.05543448233524663, + "grad_norm": 0.7499354472211508, + "learning_rate": 1.996613812475562e-05, + "loss": 1.1263, + "step": 903 + }, + { + "epoch": 0.05549587157371313, + "grad_norm": 0.6596187253018067, + "learning_rate": 1.9965974436194514e-05, + "loss": 1.0505, + "step": 904 + }, + { + "epoch": 0.055557260812179626, + "grad_norm": 0.7821266939607426, + "learning_rate": 1.9965810353625134e-05, + "loss": 0.8042, + "step": 905 + }, + { + "epoch": 0.055618650050646125, + "grad_norm": 0.7608807580134528, + "learning_rate": 1.996564587705397e-05, + "loss": 1.1622, + "step": 906 + }, + { + "epoch": 0.055680039289112616, + "grad_norm": 0.7500384954858944, + "learning_rate": 1.996548100648753e-05, + "loss": 1.0953, + "step": 907 + }, + { + "epoch": 0.055741428527579115, + "grad_norm": 0.7455223378494344, + "learning_rate": 1.9965315741932324e-05, + "loss": 1.1092, + "step": 908 + }, + { + "epoch": 0.05580281776604561, + "grad_norm": 0.7916791216368545, + "learning_rate": 1.9965150083394883e-05, + "loss": 1.1869, + "step": 909 + }, + { + "epoch": 0.05586420700451211, + "grad_norm": 0.6893898619258079, + "learning_rate": 1.9964984030881767e-05, + "loss": 1.1213, + "step": 910 + }, + { + "epoch": 0.055925596242978604, + "grad_norm": 0.727164533166789, + "learning_rate": 1.9964817584399535e-05, + "loss": 1.146, + "step": 911 + }, + { + "epoch": 0.0559869854814451, + "grad_norm": 0.7248938450995017, + "learning_rate": 1.996465074395477e-05, + "loss": 1.0843, + "step": 912 + }, + { + "epoch": 0.0560483747199116, + "grad_norm": 0.6888212009091869, + "learning_rate": 1.9964483509554064e-05, + "loss": 1.1505, + "step": 913 + }, + { + "epoch": 0.0561097639583781, + "grad_norm": 0.7239495764410521, + "learning_rate": 1.996431588120403e-05, + "loss": 1.146, + "step": 914 + }, + { + "epoch": 0.05617115319684459, + "grad_norm": 0.6966121374390623, + "learning_rate": 1.99641478589113e-05, + "loss": 1.1217, + "step": 915 + }, + { + "epoch": 0.05623254243531109, + "grad_norm": 0.6916760899700891, + "learning_rate": 1.9963979442682508e-05, + "loss": 1.1157, + "step": 916 + }, + { + "epoch": 0.05629393167377759, + "grad_norm": 0.721763091640295, + "learning_rate": 1.9963810632524324e-05, + "loss": 1.1349, + "step": 917 + }, + { + "epoch": 0.056355320912244086, + "grad_norm": 0.7106422509260326, + "learning_rate": 1.996364142844341e-05, + "loss": 1.1412, + "step": 918 + }, + { + "epoch": 0.05641671015071058, + "grad_norm": 0.6849687754097832, + "learning_rate": 1.9963471830446463e-05, + "loss": 1.0972, + "step": 919 + }, + { + "epoch": 0.056478099389177076, + "grad_norm": 0.711171665959118, + "learning_rate": 1.9963301838540187e-05, + "loss": 1.1485, + "step": 920 + }, + { + "epoch": 0.056539488627643575, + "grad_norm": 0.7008559573432226, + "learning_rate": 1.99631314527313e-05, + "loss": 1.1213, + "step": 921 + }, + { + "epoch": 0.05660087786611007, + "grad_norm": 0.7042056575969771, + "learning_rate": 1.9962960673026538e-05, + "loss": 1.122, + "step": 922 + }, + { + "epoch": 0.056662267104576565, + "grad_norm": 0.7146497140518919, + "learning_rate": 1.9962789499432663e-05, + "loss": 1.1151, + "step": 923 + }, + { + "epoch": 0.056723656343043063, + "grad_norm": 0.6849946761388952, + "learning_rate": 1.9962617931956427e-05, + "loss": 1.0889, + "step": 924 + }, + { + "epoch": 0.05678504558150956, + "grad_norm": 0.6813407802993461, + "learning_rate": 1.9962445970604622e-05, + "loss": 1.1161, + "step": 925 + }, + { + "epoch": 0.05684643481997606, + "grad_norm": 0.6924139785861264, + "learning_rate": 1.9962273615384046e-05, + "loss": 1.118, + "step": 926 + }, + { + "epoch": 0.05690782405844255, + "grad_norm": 0.6788305476349128, + "learning_rate": 1.9962100866301513e-05, + "loss": 1.0993, + "step": 927 + }, + { + "epoch": 0.05696921329690905, + "grad_norm": 0.707691218955064, + "learning_rate": 1.996192772336385e-05, + "loss": 1.1113, + "step": 928 + }, + { + "epoch": 0.05703060253537555, + "grad_norm": 0.7287411513391213, + "learning_rate": 1.9961754186577906e-05, + "loss": 1.1938, + "step": 929 + }, + { + "epoch": 0.05709199177384205, + "grad_norm": 0.6770458160924661, + "learning_rate": 1.996158025595054e-05, + "loss": 1.1378, + "step": 930 + }, + { + "epoch": 0.05715338101230854, + "grad_norm": 0.7084735624351934, + "learning_rate": 1.9961405931488622e-05, + "loss": 1.108, + "step": 931 + }, + { + "epoch": 0.05721477025077504, + "grad_norm": 0.7068453181333421, + "learning_rate": 1.9961231213199053e-05, + "loss": 1.1746, + "step": 932 + }, + { + "epoch": 0.057276159489241536, + "grad_norm": 0.6806565342790187, + "learning_rate": 1.9961056101088738e-05, + "loss": 1.0798, + "step": 933 + }, + { + "epoch": 0.057337548727708035, + "grad_norm": 0.6998449418046805, + "learning_rate": 1.9960880595164603e-05, + "loss": 1.0967, + "step": 934 + }, + { + "epoch": 0.057398937966174526, + "grad_norm": 0.7239855003922621, + "learning_rate": 1.996070469543358e-05, + "loss": 1.1971, + "step": 935 + }, + { + "epoch": 0.057460327204641025, + "grad_norm": 0.7415418058441445, + "learning_rate": 1.996052840190263e-05, + "loss": 1.1704, + "step": 936 + }, + { + "epoch": 0.05752171644310752, + "grad_norm": 0.731885126990757, + "learning_rate": 1.9960351714578718e-05, + "loss": 1.1612, + "step": 937 + }, + { + "epoch": 0.05758310568157402, + "grad_norm": 0.7225173073551179, + "learning_rate": 1.996017463346883e-05, + "loss": 1.1117, + "step": 938 + }, + { + "epoch": 0.057644494920040514, + "grad_norm": 0.7044017121674717, + "learning_rate": 1.995999715857997e-05, + "loss": 1.068, + "step": 939 + }, + { + "epoch": 0.05770588415850701, + "grad_norm": 0.7406272211253818, + "learning_rate": 1.995981928991915e-05, + "loss": 1.1124, + "step": 940 + }, + { + "epoch": 0.05776727339697351, + "grad_norm": 0.7359537783262093, + "learning_rate": 1.9959641027493405e-05, + "loss": 1.144, + "step": 941 + }, + { + "epoch": 0.05782866263544001, + "grad_norm": 0.7120773982565373, + "learning_rate": 1.9959462371309785e-05, + "loss": 1.137, + "step": 942 + }, + { + "epoch": 0.05789005187390651, + "grad_norm": 0.6935791651999402, + "learning_rate": 1.995928332137535e-05, + "loss": 1.0986, + "step": 943 + }, + { + "epoch": 0.057951441112373, + "grad_norm": 0.7483880681714625, + "learning_rate": 1.9959103877697178e-05, + "loss": 1.1445, + "step": 944 + }, + { + "epoch": 0.0580128303508395, + "grad_norm": 0.7078352943189852, + "learning_rate": 1.9958924040282365e-05, + "loss": 1.0991, + "step": 945 + }, + { + "epoch": 0.058074219589305996, + "grad_norm": 0.6785193339228087, + "learning_rate": 1.9958743809138018e-05, + "loss": 1.0558, + "step": 946 + }, + { + "epoch": 0.058135608827772495, + "grad_norm": 0.7068963452347747, + "learning_rate": 1.995856318427127e-05, + "loss": 1.0829, + "step": 947 + }, + { + "epoch": 0.058196998066238986, + "grad_norm": 0.6967666348171478, + "learning_rate": 1.9958382165689253e-05, + "loss": 1.1048, + "step": 948 + }, + { + "epoch": 0.058258387304705485, + "grad_norm": 0.6971334991241783, + "learning_rate": 1.995820075339913e-05, + "loss": 1.0887, + "step": 949 + }, + { + "epoch": 0.05831977654317198, + "grad_norm": 0.7015921635005818, + "learning_rate": 1.995801894740807e-05, + "loss": 1.0974, + "step": 950 + }, + { + "epoch": 0.05838116578163848, + "grad_norm": 0.7213093026302275, + "learning_rate": 1.9957836747723266e-05, + "loss": 1.1101, + "step": 951 + }, + { + "epoch": 0.05844255502010497, + "grad_norm": 0.7509438385596041, + "learning_rate": 1.995765415435191e-05, + "loss": 1.1288, + "step": 952 + }, + { + "epoch": 0.05850394425857147, + "grad_norm": 0.6870751369501742, + "learning_rate": 1.9957471167301232e-05, + "loss": 1.0282, + "step": 953 + }, + { + "epoch": 0.05856533349703797, + "grad_norm": 0.6591707022646244, + "learning_rate": 1.995728778657846e-05, + "loss": 1.1076, + "step": 954 + }, + { + "epoch": 0.05862672273550447, + "grad_norm": 0.7050556699692314, + "learning_rate": 1.995710401219085e-05, + "loss": 1.1075, + "step": 955 + }, + { + "epoch": 0.05868811197397096, + "grad_norm": 0.7402608046706802, + "learning_rate": 1.9956919844145663e-05, + "loss": 1.1314, + "step": 956 + }, + { + "epoch": 0.05874950121243746, + "grad_norm": 0.6751546511799987, + "learning_rate": 1.995673528245018e-05, + "loss": 1.108, + "step": 957 + }, + { + "epoch": 0.05881089045090396, + "grad_norm": 0.6969905768694461, + "learning_rate": 1.99565503271117e-05, + "loss": 1.0887, + "step": 958 + }, + { + "epoch": 0.058872279689370456, + "grad_norm": 0.79703428404519, + "learning_rate": 1.9956364978137536e-05, + "loss": 1.188, + "step": 959 + }, + { + "epoch": 0.05893366892783695, + "grad_norm": 0.6279344321195458, + "learning_rate": 1.995617923553501e-05, + "loss": 0.8149, + "step": 960 + }, + { + "epoch": 0.058995058166303446, + "grad_norm": 0.7365661488474026, + "learning_rate": 1.995599309931147e-05, + "loss": 1.0603, + "step": 961 + }, + { + "epoch": 0.059056447404769945, + "grad_norm": 0.7142361932026522, + "learning_rate": 1.9955806569474277e-05, + "loss": 1.1123, + "step": 962 + }, + { + "epoch": 0.05911783664323644, + "grad_norm": 0.7264740080104672, + "learning_rate": 1.99556196460308e-05, + "loss": 1.1707, + "step": 963 + }, + { + "epoch": 0.059179225881702935, + "grad_norm": 0.7393558541132236, + "learning_rate": 1.9955432328988437e-05, + "loss": 1.1471, + "step": 964 + }, + { + "epoch": 0.05924061512016943, + "grad_norm": 0.6960864881894588, + "learning_rate": 1.9955244618354582e-05, + "loss": 1.152, + "step": 965 + }, + { + "epoch": 0.05930200435863593, + "grad_norm": 0.7304967047157572, + "learning_rate": 1.9955056514136667e-05, + "loss": 1.122, + "step": 966 + }, + { + "epoch": 0.05936339359710243, + "grad_norm": 0.6540802725625529, + "learning_rate": 1.9954868016342125e-05, + "loss": 1.0475, + "step": 967 + }, + { + "epoch": 0.05942478283556892, + "grad_norm": 0.6920068502609049, + "learning_rate": 1.9954679124978407e-05, + "loss": 1.1108, + "step": 968 + }, + { + "epoch": 0.05948617207403542, + "grad_norm": 0.7017959411744159, + "learning_rate": 1.995448984005298e-05, + "loss": 1.1078, + "step": 969 + }, + { + "epoch": 0.05954756131250192, + "grad_norm": 0.7460729664072924, + "learning_rate": 1.9954300161573333e-05, + "loss": 1.1008, + "step": 970 + }, + { + "epoch": 0.05960895055096842, + "grad_norm": 0.6558500008588308, + "learning_rate": 1.9954110089546958e-05, + "loss": 1.0257, + "step": 971 + }, + { + "epoch": 0.05967033978943491, + "grad_norm": 0.7447250626380195, + "learning_rate": 1.9953919623981373e-05, + "loss": 1.1039, + "step": 972 + }, + { + "epoch": 0.05973172902790141, + "grad_norm": 0.7411730797812174, + "learning_rate": 1.995372876488411e-05, + "loss": 1.1689, + "step": 973 + }, + { + "epoch": 0.059793118266367906, + "grad_norm": 0.7786439026324248, + "learning_rate": 1.995353751226271e-05, + "loss": 1.2032, + "step": 974 + }, + { + "epoch": 0.059854507504834405, + "grad_norm": 0.7177618005902054, + "learning_rate": 1.995334586612474e-05, + "loss": 1.1492, + "step": 975 + }, + { + "epoch": 0.059915896743300896, + "grad_norm": 0.6726860700465708, + "learning_rate": 1.995315382647777e-05, + "loss": 1.0604, + "step": 976 + }, + { + "epoch": 0.059977285981767395, + "grad_norm": 0.733470200458601, + "learning_rate": 1.99529613933294e-05, + "loss": 1.1689, + "step": 977 + }, + { + "epoch": 0.06003867522023389, + "grad_norm": 0.7699211320291077, + "learning_rate": 1.995276856668723e-05, + "loss": 1.0804, + "step": 978 + }, + { + "epoch": 0.06010006445870039, + "grad_norm": 0.7414477692770061, + "learning_rate": 1.995257534655889e-05, + "loss": 1.1559, + "step": 979 + }, + { + "epoch": 0.06016145369716688, + "grad_norm": 0.7173826006268019, + "learning_rate": 1.9952381732952016e-05, + "loss": 1.1343, + "step": 980 + }, + { + "epoch": 0.06022284293563338, + "grad_norm": 0.6998322346904831, + "learning_rate": 1.9952187725874262e-05, + "loss": 1.1095, + "step": 981 + }, + { + "epoch": 0.06028423217409988, + "grad_norm": 0.7363755782682772, + "learning_rate": 1.99519933253333e-05, + "loss": 1.1455, + "step": 982 + }, + { + "epoch": 0.06034562141256638, + "grad_norm": 0.7189375997688671, + "learning_rate": 1.9951798531336814e-05, + "loss": 1.1637, + "step": 983 + }, + { + "epoch": 0.06040701065103287, + "grad_norm": 0.704326563886428, + "learning_rate": 1.9951603343892506e-05, + "loss": 1.1491, + "step": 984 + }, + { + "epoch": 0.06046839988949937, + "grad_norm": 0.6576303104546052, + "learning_rate": 1.9951407763008098e-05, + "loss": 1.1538, + "step": 985 + }, + { + "epoch": 0.06052978912796587, + "grad_norm": 0.6686701072895219, + "learning_rate": 1.995121178869131e-05, + "loss": 1.0676, + "step": 986 + }, + { + "epoch": 0.060591178366432366, + "grad_norm": 0.6710985747776785, + "learning_rate": 1.99510154209499e-05, + "loss": 1.1204, + "step": 987 + }, + { + "epoch": 0.060652567604898865, + "grad_norm": 0.6841316829336822, + "learning_rate": 1.995081865979163e-05, + "loss": 1.1338, + "step": 988 + }, + { + "epoch": 0.060713956843365356, + "grad_norm": 0.7075478394116035, + "learning_rate": 1.9950621505224276e-05, + "loss": 1.0721, + "step": 989 + }, + { + "epoch": 0.060775346081831855, + "grad_norm": 0.7492995154052825, + "learning_rate": 1.9950423957255635e-05, + "loss": 1.1461, + "step": 990 + }, + { + "epoch": 0.06083673532029835, + "grad_norm": 0.7216120241834718, + "learning_rate": 1.9950226015893515e-05, + "loss": 1.132, + "step": 991 + }, + { + "epoch": 0.06089812455876485, + "grad_norm": 0.7064561634320181, + "learning_rate": 1.9950027681145743e-05, + "loss": 1.0942, + "step": 992 + }, + { + "epoch": 0.06095951379723134, + "grad_norm": 0.6859829103024435, + "learning_rate": 1.9949828953020164e-05, + "loss": 1.1107, + "step": 993 + }, + { + "epoch": 0.06102090303569784, + "grad_norm": 0.6993945338826659, + "learning_rate": 1.994962983152463e-05, + "loss": 1.0792, + "step": 994 + }, + { + "epoch": 0.06108229227416434, + "grad_norm": 0.6829199658460964, + "learning_rate": 1.9949430316667012e-05, + "loss": 1.0903, + "step": 995 + }, + { + "epoch": 0.06114368151263084, + "grad_norm": 0.7070501212289965, + "learning_rate": 1.99492304084552e-05, + "loss": 1.0363, + "step": 996 + }, + { + "epoch": 0.06120507075109733, + "grad_norm": 0.7851989321454843, + "learning_rate": 1.99490301068971e-05, + "loss": 1.1322, + "step": 997 + }, + { + "epoch": 0.06126645998956383, + "grad_norm": 0.7196182890007453, + "learning_rate": 1.9948829412000624e-05, + "loss": 1.1109, + "step": 998 + }, + { + "epoch": 0.06132784922803033, + "grad_norm": 0.6905794692581491, + "learning_rate": 1.9948628323773717e-05, + "loss": 1.1277, + "step": 999 + }, + { + "epoch": 0.061389238466496826, + "grad_norm": 0.743499545328414, + "learning_rate": 1.9948426842224322e-05, + "loss": 1.1412, + "step": 1000 + }, + { + "epoch": 0.06145062770496332, + "grad_norm": 0.7088802713527481, + "learning_rate": 1.9948224967360407e-05, + "loss": 1.1041, + "step": 1001 + }, + { + "epoch": 0.061512016943429816, + "grad_norm": 0.6957241474265962, + "learning_rate": 1.994802269918995e-05, + "loss": 1.1222, + "step": 1002 + }, + { + "epoch": 0.061573406181896315, + "grad_norm": 0.7458829236634117, + "learning_rate": 1.994782003772095e-05, + "loss": 1.1124, + "step": 1003 + }, + { + "epoch": 0.06163479542036281, + "grad_norm": 0.7164834634075483, + "learning_rate": 1.994761698296142e-05, + "loss": 1.121, + "step": 1004 + }, + { + "epoch": 0.061696184658829305, + "grad_norm": 0.7817532669527326, + "learning_rate": 1.9947413534919386e-05, + "loss": 1.1659, + "step": 1005 + }, + { + "epoch": 0.0617575738972958, + "grad_norm": 0.7086299385013355, + "learning_rate": 1.9947209693602892e-05, + "loss": 1.1583, + "step": 1006 + }, + { + "epoch": 0.0618189631357623, + "grad_norm": 0.691766885238514, + "learning_rate": 1.994700545902e-05, + "loss": 1.0824, + "step": 1007 + }, + { + "epoch": 0.0618803523742288, + "grad_norm": 0.7360968559356352, + "learning_rate": 1.9946800831178778e-05, + "loss": 1.2075, + "step": 1008 + }, + { + "epoch": 0.06194174161269529, + "grad_norm": 0.7280256517861071, + "learning_rate": 1.9946595810087324e-05, + "loss": 1.1258, + "step": 1009 + }, + { + "epoch": 0.06200313085116179, + "grad_norm": 0.6865879294110315, + "learning_rate": 1.9946390395753737e-05, + "loss": 1.1237, + "step": 1010 + }, + { + "epoch": 0.06206452008962829, + "grad_norm": 0.7076701118912161, + "learning_rate": 1.994618458818614e-05, + "loss": 1.091, + "step": 1011 + }, + { + "epoch": 0.06212590932809479, + "grad_norm": 0.6459236707333548, + "learning_rate": 1.994597838739267e-05, + "loss": 1.0506, + "step": 1012 + }, + { + "epoch": 0.06218729856656128, + "grad_norm": 0.7197144565066088, + "learning_rate": 1.9945771793381486e-05, + "loss": 1.1471, + "step": 1013 + }, + { + "epoch": 0.06224868780502778, + "grad_norm": 0.7208086847282473, + "learning_rate": 1.9945564806160744e-05, + "loss": 1.117, + "step": 1014 + }, + { + "epoch": 0.062310077043494276, + "grad_norm": 0.6789498537113078, + "learning_rate": 1.9945357425738634e-05, + "loss": 1.0852, + "step": 1015 + }, + { + "epoch": 0.062371466281960775, + "grad_norm": 0.7627799591750611, + "learning_rate": 1.994514965212335e-05, + "loss": 1.1289, + "step": 1016 + }, + { + "epoch": 0.062432855520427266, + "grad_norm": 0.7166699520383353, + "learning_rate": 1.9944941485323114e-05, + "loss": 1.0645, + "step": 1017 + }, + { + "epoch": 0.062494244758893765, + "grad_norm": 0.6728630686305658, + "learning_rate": 1.994473292534615e-05, + "loss": 1.0877, + "step": 1018 + }, + { + "epoch": 0.06255563399736026, + "grad_norm": 0.7245626078678764, + "learning_rate": 1.9944523972200708e-05, + "loss": 1.0905, + "step": 1019 + }, + { + "epoch": 0.06261702323582675, + "grad_norm": 0.7145276966686405, + "learning_rate": 1.9944314625895043e-05, + "loss": 1.0526, + "step": 1020 + }, + { + "epoch": 0.06267841247429326, + "grad_norm": 0.7090346961380832, + "learning_rate": 1.9944104886437434e-05, + "loss": 1.0912, + "step": 1021 + }, + { + "epoch": 0.06273980171275975, + "grad_norm": 0.7115961297779134, + "learning_rate": 1.9943894753836176e-05, + "loss": 1.1422, + "step": 1022 + }, + { + "epoch": 0.06280119095122624, + "grad_norm": 0.726900764859675, + "learning_rate": 1.9943684228099576e-05, + "loss": 1.1192, + "step": 1023 + }, + { + "epoch": 0.06286258018969275, + "grad_norm": 0.6660641917586639, + "learning_rate": 1.9943473309235953e-05, + "loss": 0.8423, + "step": 1024 + }, + { + "epoch": 0.06292396942815924, + "grad_norm": 0.6806702798140986, + "learning_rate": 1.994326199725365e-05, + "loss": 1.0969, + "step": 1025 + }, + { + "epoch": 0.06298535866662575, + "grad_norm": 0.7514047024143096, + "learning_rate": 1.994305029216102e-05, + "loss": 1.1007, + "step": 1026 + }, + { + "epoch": 0.06304674790509224, + "grad_norm": 0.6829563418319989, + "learning_rate": 1.9942838193966434e-05, + "loss": 1.0789, + "step": 1027 + }, + { + "epoch": 0.06310813714355873, + "grad_norm": 0.7294818907616922, + "learning_rate": 1.9942625702678275e-05, + "loss": 1.1534, + "step": 1028 + }, + { + "epoch": 0.06316952638202523, + "grad_norm": 0.7552260206178909, + "learning_rate": 1.9942412818304944e-05, + "loss": 1.1196, + "step": 1029 + }, + { + "epoch": 0.06323091562049173, + "grad_norm": 0.7134642034078001, + "learning_rate": 1.9942199540854858e-05, + "loss": 1.0892, + "step": 1030 + }, + { + "epoch": 0.06329230485895823, + "grad_norm": 0.6506084894819081, + "learning_rate": 1.9941985870336452e-05, + "loss": 1.052, + "step": 1031 + }, + { + "epoch": 0.06335369409742472, + "grad_norm": 0.7415110672359404, + "learning_rate": 1.994177180675817e-05, + "loss": 1.0891, + "step": 1032 + }, + { + "epoch": 0.06341508333589121, + "grad_norm": 0.6517756471309314, + "learning_rate": 1.9941557350128477e-05, + "loss": 1.0961, + "step": 1033 + }, + { + "epoch": 0.06347647257435772, + "grad_norm": 0.7232348485086876, + "learning_rate": 1.994134250045585e-05, + "loss": 1.1405, + "step": 1034 + }, + { + "epoch": 0.06353786181282421, + "grad_norm": 0.7088705182406771, + "learning_rate": 1.9941127257748784e-05, + "loss": 1.0954, + "step": 1035 + }, + { + "epoch": 0.0635992510512907, + "grad_norm": 0.6869120819840114, + "learning_rate": 1.9940911622015786e-05, + "loss": 1.1184, + "step": 1036 + }, + { + "epoch": 0.06366064028975721, + "grad_norm": 0.6659544347666773, + "learning_rate": 1.9940695593265386e-05, + "loss": 1.0736, + "step": 1037 + }, + { + "epoch": 0.0637220295282237, + "grad_norm": 0.6897668340992034, + "learning_rate": 1.9940479171506126e-05, + "loss": 1.0874, + "step": 1038 + }, + { + "epoch": 0.0637834187666902, + "grad_norm": 0.6803816625860779, + "learning_rate": 1.9940262356746553e-05, + "loss": 1.0734, + "step": 1039 + }, + { + "epoch": 0.0638448080051567, + "grad_norm": 0.7551654443448673, + "learning_rate": 1.994004514899525e-05, + "loss": 1.1931, + "step": 1040 + }, + { + "epoch": 0.06390619724362319, + "grad_norm": 0.7494914013822495, + "learning_rate": 1.9939827548260793e-05, + "loss": 1.1606, + "step": 1041 + }, + { + "epoch": 0.0639675864820897, + "grad_norm": 0.7306780273109572, + "learning_rate": 1.99396095545518e-05, + "loss": 1.1127, + "step": 1042 + }, + { + "epoch": 0.06402897572055619, + "grad_norm": 0.6985851375302441, + "learning_rate": 1.9939391167876875e-05, + "loss": 1.0907, + "step": 1043 + }, + { + "epoch": 0.06409036495902268, + "grad_norm": 0.7136793106643905, + "learning_rate": 1.993917238824466e-05, + "loss": 1.1246, + "step": 1044 + }, + { + "epoch": 0.06415175419748918, + "grad_norm": 0.7242846505916726, + "learning_rate": 1.9938953215663795e-05, + "loss": 1.0715, + "step": 1045 + }, + { + "epoch": 0.06421314343595567, + "grad_norm": 0.7272892945428503, + "learning_rate": 1.993873365014296e-05, + "loss": 1.121, + "step": 1046 + }, + { + "epoch": 0.06427453267442218, + "grad_norm": 0.7183911622527438, + "learning_rate": 1.9938513691690823e-05, + "loss": 1.0944, + "step": 1047 + }, + { + "epoch": 0.06433592191288867, + "grad_norm": 0.698719395037527, + "learning_rate": 1.993829334031609e-05, + "loss": 1.1414, + "step": 1048 + }, + { + "epoch": 0.06439731115135516, + "grad_norm": 0.7885828125102973, + "learning_rate": 1.9938072596027464e-05, + "loss": 1.1566, + "step": 1049 + }, + { + "epoch": 0.06445870038982167, + "grad_norm": 0.6557408259883557, + "learning_rate": 1.9937851458833675e-05, + "loss": 1.0792, + "step": 1050 + }, + { + "epoch": 0.06452008962828816, + "grad_norm": 0.7480243331440886, + "learning_rate": 1.9937629928743468e-05, + "loss": 1.1242, + "step": 1051 + }, + { + "epoch": 0.06458147886675465, + "grad_norm": 0.7225940251915665, + "learning_rate": 1.9937408005765596e-05, + "loss": 1.1172, + "step": 1052 + }, + { + "epoch": 0.06464286810522116, + "grad_norm": 0.6944460030787366, + "learning_rate": 1.9937185689908842e-05, + "loss": 1.0946, + "step": 1053 + }, + { + "epoch": 0.06470425734368765, + "grad_norm": 0.6366727953922009, + "learning_rate": 1.9936962981181985e-05, + "loss": 0.8062, + "step": 1054 + }, + { + "epoch": 0.06476564658215415, + "grad_norm": 0.6933860332490706, + "learning_rate": 1.993673987959384e-05, + "loss": 1.1533, + "step": 1055 + }, + { + "epoch": 0.06482703582062065, + "grad_norm": 0.6889092877088043, + "learning_rate": 1.9936516385153218e-05, + "loss": 1.1607, + "step": 1056 + }, + { + "epoch": 0.06488842505908714, + "grad_norm": 0.7072731341909343, + "learning_rate": 1.993629249786896e-05, + "loss": 1.1352, + "step": 1057 + }, + { + "epoch": 0.06494981429755364, + "grad_norm": 0.6284030408815563, + "learning_rate": 1.993606821774992e-05, + "loss": 1.0757, + "step": 1058 + }, + { + "epoch": 0.06501120353602013, + "grad_norm": 0.7532190317066815, + "learning_rate": 1.993584354480496e-05, + "loss": 1.1279, + "step": 1059 + }, + { + "epoch": 0.06507259277448663, + "grad_norm": 0.7306901396713728, + "learning_rate": 1.9935618479042958e-05, + "loss": 1.1266, + "step": 1060 + }, + { + "epoch": 0.06513398201295313, + "grad_norm": 0.686231631251216, + "learning_rate": 1.9935393020472827e-05, + "loss": 0.8026, + "step": 1061 + }, + { + "epoch": 0.06519537125141962, + "grad_norm": 0.7281728401478437, + "learning_rate": 1.9935167169103465e-05, + "loss": 1.0659, + "step": 1062 + }, + { + "epoch": 0.06525676048988613, + "grad_norm": 0.7325480483507273, + "learning_rate": 1.9934940924943814e-05, + "loss": 1.0917, + "step": 1063 + }, + { + "epoch": 0.06531814972835262, + "grad_norm": 0.7288824021769186, + "learning_rate": 1.993471428800281e-05, + "loss": 1.1254, + "step": 1064 + }, + { + "epoch": 0.06537953896681911, + "grad_norm": 0.7375803614212979, + "learning_rate": 1.993448725828941e-05, + "loss": 1.1715, + "step": 1065 + }, + { + "epoch": 0.06544092820528562, + "grad_norm": 0.6874473356902658, + "learning_rate": 1.99342598358126e-05, + "loss": 1.1012, + "step": 1066 + }, + { + "epoch": 0.06550231744375211, + "grad_norm": 0.6449538660004794, + "learning_rate": 1.9934032020581366e-05, + "loss": 1.0623, + "step": 1067 + }, + { + "epoch": 0.0655637066822186, + "grad_norm": 0.7262726754245834, + "learning_rate": 1.9933803812604714e-05, + "loss": 1.1194, + "step": 1068 + }, + { + "epoch": 0.0656250959206851, + "grad_norm": 0.7115153279002217, + "learning_rate": 1.993357521189167e-05, + "loss": 1.1356, + "step": 1069 + }, + { + "epoch": 0.0656864851591516, + "grad_norm": 0.6240316754368432, + "learning_rate": 1.993334621845127e-05, + "loss": 1.0449, + "step": 1070 + }, + { + "epoch": 0.0657478743976181, + "grad_norm": 0.638686688683007, + "learning_rate": 1.9933116832292566e-05, + "loss": 1.077, + "step": 1071 + }, + { + "epoch": 0.0658092636360846, + "grad_norm": 0.6928811114735507, + "learning_rate": 1.9932887053424626e-05, + "loss": 1.0637, + "step": 1072 + }, + { + "epoch": 0.06587065287455109, + "grad_norm": 0.6975055095249653, + "learning_rate": 1.9932656881856534e-05, + "loss": 1.0774, + "step": 1073 + }, + { + "epoch": 0.06593204211301759, + "grad_norm": 0.7100350878794324, + "learning_rate": 1.99324263175974e-05, + "loss": 1.1148, + "step": 1074 + }, + { + "epoch": 0.06599343135148408, + "grad_norm": 0.6968474080444191, + "learning_rate": 1.9932195360656324e-05, + "loss": 1.0785, + "step": 1075 + }, + { + "epoch": 0.06605482058995059, + "grad_norm": 0.7546490785087129, + "learning_rate": 1.9931964011042443e-05, + "loss": 1.0926, + "step": 1076 + }, + { + "epoch": 0.06611620982841708, + "grad_norm": 0.7707294318747008, + "learning_rate": 1.9931732268764908e-05, + "loss": 1.1141, + "step": 1077 + }, + { + "epoch": 0.06617759906688357, + "grad_norm": 0.6954725628962702, + "learning_rate": 1.993150013383288e-05, + "loss": 1.1016, + "step": 1078 + }, + { + "epoch": 0.06623898830535008, + "grad_norm": 0.7498801159089421, + "learning_rate": 1.993126760625553e-05, + "loss": 1.1135, + "step": 1079 + }, + { + "epoch": 0.06630037754381657, + "grad_norm": 0.707274736631329, + "learning_rate": 1.993103468604206e-05, + "loss": 1.1034, + "step": 1080 + }, + { + "epoch": 0.06636176678228306, + "grad_norm": 0.6485222463314516, + "learning_rate": 1.9930801373201668e-05, + "loss": 1.0563, + "step": 1081 + }, + { + "epoch": 0.06642315602074957, + "grad_norm": 0.713020448375718, + "learning_rate": 1.993056766774359e-05, + "loss": 1.1211, + "step": 1082 + }, + { + "epoch": 0.06648454525921606, + "grad_norm": 0.6944396571671687, + "learning_rate": 1.993033356967706e-05, + "loss": 1.114, + "step": 1083 + }, + { + "epoch": 0.06654593449768256, + "grad_norm": 0.6705599983320162, + "learning_rate": 1.9930099079011326e-05, + "loss": 1.0897, + "step": 1084 + }, + { + "epoch": 0.06660732373614905, + "grad_norm": 0.7280085520697323, + "learning_rate": 1.992986419575567e-05, + "loss": 1.1075, + "step": 1085 + }, + { + "epoch": 0.06666871297461555, + "grad_norm": 0.6706895946310851, + "learning_rate": 1.9929628919919373e-05, + "loss": 1.089, + "step": 1086 + }, + { + "epoch": 0.06673010221308205, + "grad_norm": 0.6800373731164967, + "learning_rate": 1.992939325151174e-05, + "loss": 1.1339, + "step": 1087 + }, + { + "epoch": 0.06679149145154854, + "grad_norm": 0.7584303969473462, + "learning_rate": 1.9929157190542082e-05, + "loss": 1.1307, + "step": 1088 + }, + { + "epoch": 0.06685288069001503, + "grad_norm": 0.7685964658390146, + "learning_rate": 1.9928920737019735e-05, + "loss": 1.1365, + "step": 1089 + }, + { + "epoch": 0.06691426992848154, + "grad_norm": 0.7212006671379351, + "learning_rate": 1.992868389095405e-05, + "loss": 1.1564, + "step": 1090 + }, + { + "epoch": 0.06697565916694803, + "grad_norm": 0.7384040272279176, + "learning_rate": 1.9928446652354387e-05, + "loss": 1.1294, + "step": 1091 + }, + { + "epoch": 0.06703704840541454, + "grad_norm": 0.6888312497707948, + "learning_rate": 1.992820902123013e-05, + "loss": 1.128, + "step": 1092 + }, + { + "epoch": 0.06709843764388103, + "grad_norm": 0.7562184371595614, + "learning_rate": 1.9927970997590666e-05, + "loss": 1.1301, + "step": 1093 + }, + { + "epoch": 0.06715982688234752, + "grad_norm": 0.7057451608541302, + "learning_rate": 1.992773258144541e-05, + "loss": 1.0613, + "step": 1094 + }, + { + "epoch": 0.06722121612081403, + "grad_norm": 0.645105889516922, + "learning_rate": 1.9927493772803794e-05, + "loss": 1.0402, + "step": 1095 + }, + { + "epoch": 0.06728260535928052, + "grad_norm": 0.735780820905807, + "learning_rate": 1.9927254571675247e-05, + "loss": 1.1681, + "step": 1096 + }, + { + "epoch": 0.06734399459774701, + "grad_norm": 0.637729289390822, + "learning_rate": 1.9927014978069235e-05, + "loss": 0.7858, + "step": 1097 + }, + { + "epoch": 0.06740538383621351, + "grad_norm": 0.6673307441910408, + "learning_rate": 1.9926774991995226e-05, + "loss": 1.0815, + "step": 1098 + }, + { + "epoch": 0.06746677307468, + "grad_norm": 0.7134040423972434, + "learning_rate": 1.992653461346271e-05, + "loss": 1.1259, + "step": 1099 + }, + { + "epoch": 0.06752816231314651, + "grad_norm": 0.5715380078032336, + "learning_rate": 1.992629384248119e-05, + "loss": 0.7823, + "step": 1100 + }, + { + "epoch": 0.067589551551613, + "grad_norm": 0.6904866876448433, + "learning_rate": 1.9926052679060186e-05, + "loss": 1.0561, + "step": 1101 + }, + { + "epoch": 0.0676509407900795, + "grad_norm": 0.6549555456517199, + "learning_rate": 1.9925811123209228e-05, + "loss": 1.0406, + "step": 1102 + }, + { + "epoch": 0.067712330028546, + "grad_norm": 0.7188486857969572, + "learning_rate": 1.9925569174937873e-05, + "loss": 1.125, + "step": 1103 + }, + { + "epoch": 0.06777371926701249, + "grad_norm": 0.7617944869910434, + "learning_rate": 1.992532683425568e-05, + "loss": 1.1983, + "step": 1104 + }, + { + "epoch": 0.06783510850547898, + "grad_norm": 0.6424361007245674, + "learning_rate": 1.9925084101172234e-05, + "loss": 1.1134, + "step": 1105 + }, + { + "epoch": 0.06789649774394549, + "grad_norm": 0.7123433486785062, + "learning_rate": 1.9924840975697132e-05, + "loss": 1.1262, + "step": 1106 + }, + { + "epoch": 0.06795788698241198, + "grad_norm": 0.7123376944205971, + "learning_rate": 1.9924597457839984e-05, + "loss": 1.1069, + "step": 1107 + }, + { + "epoch": 0.06801927622087849, + "grad_norm": 0.6959688445300888, + "learning_rate": 1.9924353547610415e-05, + "loss": 1.1113, + "step": 1108 + }, + { + "epoch": 0.06808066545934498, + "grad_norm": 0.6476171773071601, + "learning_rate": 1.9924109245018072e-05, + "loss": 1.0815, + "step": 1109 + }, + { + "epoch": 0.06814205469781147, + "grad_norm": 0.7269757540738526, + "learning_rate": 1.9923864550072617e-05, + "loss": 1.0559, + "step": 1110 + }, + { + "epoch": 0.06820344393627797, + "grad_norm": 0.7355112859740638, + "learning_rate": 1.9923619462783714e-05, + "loss": 1.1414, + "step": 1111 + }, + { + "epoch": 0.06826483317474447, + "grad_norm": 0.6999978360617188, + "learning_rate": 1.992337398316106e-05, + "loss": 1.1488, + "step": 1112 + }, + { + "epoch": 0.06832622241321096, + "grad_norm": 0.6903762581307635, + "learning_rate": 1.992312811121436e-05, + "loss": 1.106, + "step": 1113 + }, + { + "epoch": 0.06838761165167746, + "grad_norm": 0.6720183275649737, + "learning_rate": 1.9922881846953333e-05, + "loss": 1.0544, + "step": 1114 + }, + { + "epoch": 0.06844900089014395, + "grad_norm": 0.728567448134204, + "learning_rate": 1.9922635190387715e-05, + "loss": 1.1001, + "step": 1115 + }, + { + "epoch": 0.06851039012861046, + "grad_norm": 0.6845154375071957, + "learning_rate": 1.9922388141527257e-05, + "loss": 1.0278, + "step": 1116 + }, + { + "epoch": 0.06857177936707695, + "grad_norm": 0.7313011206591832, + "learning_rate": 1.9922140700381728e-05, + "loss": 1.1219, + "step": 1117 + }, + { + "epoch": 0.06863316860554344, + "grad_norm": 0.67613713184297, + "learning_rate": 1.9921892866960913e-05, + "loss": 1.0853, + "step": 1118 + }, + { + "epoch": 0.06869455784400995, + "grad_norm": 0.6841205959234943, + "learning_rate": 1.99216446412746e-05, + "loss": 1.0876, + "step": 1119 + }, + { + "epoch": 0.06875594708247644, + "grad_norm": 0.6625250435062684, + "learning_rate": 1.9921396023332615e-05, + "loss": 0.7823, + "step": 1120 + }, + { + "epoch": 0.06881733632094295, + "grad_norm": 0.7037827353316438, + "learning_rate": 1.9921147013144782e-05, + "loss": 1.116, + "step": 1121 + }, + { + "epoch": 0.06887872555940944, + "grad_norm": 0.6976056815179477, + "learning_rate": 1.9920897610720943e-05, + "loss": 1.1388, + "step": 1122 + }, + { + "epoch": 0.06894011479787593, + "grad_norm": 0.7058342935078334, + "learning_rate": 1.992064781607096e-05, + "loss": 1.1652, + "step": 1123 + }, + { + "epoch": 0.06900150403634243, + "grad_norm": 0.7250701996819292, + "learning_rate": 1.992039762920471e-05, + "loss": 1.0662, + "step": 1124 + }, + { + "epoch": 0.06906289327480893, + "grad_norm": 0.704042584045477, + "learning_rate": 1.9920147050132087e-05, + "loss": 1.0919, + "step": 1125 + }, + { + "epoch": 0.06912428251327542, + "grad_norm": 0.6799494765502979, + "learning_rate": 1.991989607886299e-05, + "loss": 1.0949, + "step": 1126 + }, + { + "epoch": 0.06918567175174192, + "grad_norm": 0.6669932862297407, + "learning_rate": 1.991964471540735e-05, + "loss": 1.0708, + "step": 1127 + }, + { + "epoch": 0.06924706099020841, + "grad_norm": 0.660503418415572, + "learning_rate": 1.99193929597751e-05, + "loss": 1.0341, + "step": 1128 + }, + { + "epoch": 0.06930845022867492, + "grad_norm": 0.6840980861296618, + "learning_rate": 1.991914081197619e-05, + "loss": 1.0258, + "step": 1129 + }, + { + "epoch": 0.06936983946714141, + "grad_norm": 0.6828816780112044, + "learning_rate": 1.9918888272020593e-05, + "loss": 1.0964, + "step": 1130 + }, + { + "epoch": 0.0694312287056079, + "grad_norm": 0.7045918788834254, + "learning_rate": 1.9918635339918294e-05, + "loss": 1.1197, + "step": 1131 + }, + { + "epoch": 0.06949261794407441, + "grad_norm": 0.6753526663914764, + "learning_rate": 1.991838201567929e-05, + "loss": 1.0671, + "step": 1132 + }, + { + "epoch": 0.0695540071825409, + "grad_norm": 0.690039597898019, + "learning_rate": 1.9918128299313598e-05, + "loss": 1.0902, + "step": 1133 + }, + { + "epoch": 0.06961539642100739, + "grad_norm": 0.6809965530532393, + "learning_rate": 1.991787419083125e-05, + "loss": 1.0733, + "step": 1134 + }, + { + "epoch": 0.0696767856594739, + "grad_norm": 0.6997556634171798, + "learning_rate": 1.9917619690242293e-05, + "loss": 1.0848, + "step": 1135 + }, + { + "epoch": 0.06973817489794039, + "grad_norm": 0.7000295550433211, + "learning_rate": 1.9917364797556782e-05, + "loss": 1.1183, + "step": 1136 + }, + { + "epoch": 0.0697995641364069, + "grad_norm": 0.6960224021054293, + "learning_rate": 1.99171095127848e-05, + "loss": 1.1173, + "step": 1137 + }, + { + "epoch": 0.06986095337487339, + "grad_norm": 0.6565494795819338, + "learning_rate": 1.991685383593644e-05, + "loss": 1.0497, + "step": 1138 + }, + { + "epoch": 0.06992234261333988, + "grad_norm": 0.6766920522594907, + "learning_rate": 1.991659776702181e-05, + "loss": 1.142, + "step": 1139 + }, + { + "epoch": 0.06998373185180638, + "grad_norm": 0.7210297633099194, + "learning_rate": 1.991634130605103e-05, + "loss": 1.1424, + "step": 1140 + }, + { + "epoch": 0.07004512109027287, + "grad_norm": 0.7206917741788861, + "learning_rate": 1.991608445303424e-05, + "loss": 1.099, + "step": 1141 + }, + { + "epoch": 0.07010651032873937, + "grad_norm": 0.7749368336878748, + "learning_rate": 1.99158272079816e-05, + "loss": 0.7919, + "step": 1142 + }, + { + "epoch": 0.07016789956720587, + "grad_norm": 0.7210480051719285, + "learning_rate": 1.9915569570903274e-05, + "loss": 1.106, + "step": 1143 + }, + { + "epoch": 0.07022928880567236, + "grad_norm": 0.6917653707976241, + "learning_rate": 1.9915311541809452e-05, + "loss": 1.1773, + "step": 1144 + }, + { + "epoch": 0.07029067804413887, + "grad_norm": 0.6885973810299612, + "learning_rate": 1.9915053120710333e-05, + "loss": 1.066, + "step": 1145 + }, + { + "epoch": 0.07035206728260536, + "grad_norm": 0.735391052524721, + "learning_rate": 1.9914794307616137e-05, + "loss": 1.1627, + "step": 1146 + }, + { + "epoch": 0.07041345652107185, + "grad_norm": 0.6043447390959539, + "learning_rate": 1.9914535102537095e-05, + "loss": 1.056, + "step": 1147 + }, + { + "epoch": 0.07047484575953836, + "grad_norm": 0.6881183168927006, + "learning_rate": 1.991427550548345e-05, + "loss": 1.1559, + "step": 1148 + }, + { + "epoch": 0.07053623499800485, + "grad_norm": 0.6656238683904386, + "learning_rate": 1.9914015516465472e-05, + "loss": 1.1353, + "step": 1149 + }, + { + "epoch": 0.07059762423647134, + "grad_norm": 0.6748348414822135, + "learning_rate": 1.9913755135493432e-05, + "loss": 1.0761, + "step": 1150 + }, + { + "epoch": 0.07065901347493785, + "grad_norm": 0.7188376528809904, + "learning_rate": 1.9913494362577635e-05, + "loss": 1.0887, + "step": 1151 + }, + { + "epoch": 0.07072040271340434, + "grad_norm": 0.6353700874354095, + "learning_rate": 1.991323319772838e-05, + "loss": 1.0167, + "step": 1152 + }, + { + "epoch": 0.07078179195187084, + "grad_norm": 0.6947828291135815, + "learning_rate": 1.9912971640956002e-05, + "loss": 1.1275, + "step": 1153 + }, + { + "epoch": 0.07084318119033733, + "grad_norm": 0.6866566653689176, + "learning_rate": 1.9912709692270834e-05, + "loss": 1.105, + "step": 1154 + }, + { + "epoch": 0.07090457042880383, + "grad_norm": 0.7064048026099542, + "learning_rate": 1.9912447351683233e-05, + "loss": 1.1139, + "step": 1155 + }, + { + "epoch": 0.07096595966727033, + "grad_norm": 0.7625288679274266, + "learning_rate": 1.9912184619203577e-05, + "loss": 1.1991, + "step": 1156 + }, + { + "epoch": 0.07102734890573682, + "grad_norm": 0.7028321729205788, + "learning_rate": 1.9911921494842247e-05, + "loss": 1.1604, + "step": 1157 + }, + { + "epoch": 0.07108873814420331, + "grad_norm": 0.6912232784645922, + "learning_rate": 1.9911657978609646e-05, + "loss": 1.1142, + "step": 1158 + }, + { + "epoch": 0.07115012738266982, + "grad_norm": 0.6500293756159081, + "learning_rate": 1.9911394070516195e-05, + "loss": 1.1027, + "step": 1159 + }, + { + "epoch": 0.07121151662113631, + "grad_norm": 0.7023446815823676, + "learning_rate": 1.9911129770572326e-05, + "loss": 1.1546, + "step": 1160 + }, + { + "epoch": 0.07127290585960282, + "grad_norm": 0.575732978639924, + "learning_rate": 1.9910865078788488e-05, + "loss": 1.0818, + "step": 1161 + }, + { + "epoch": 0.07133429509806931, + "grad_norm": 0.7043992804383442, + "learning_rate": 1.991059999517515e-05, + "loss": 1.1026, + "step": 1162 + }, + { + "epoch": 0.0713956843365358, + "grad_norm": 0.6214035018688333, + "learning_rate": 1.9910334519742785e-05, + "loss": 1.0971, + "step": 1163 + }, + { + "epoch": 0.0714570735750023, + "grad_norm": 0.6961953348346916, + "learning_rate": 1.9910068652501894e-05, + "loss": 1.1158, + "step": 1164 + }, + { + "epoch": 0.0715184628134688, + "grad_norm": 0.6983634950014883, + "learning_rate": 1.9909802393462985e-05, + "loss": 1.1339, + "step": 1165 + }, + { + "epoch": 0.0715798520519353, + "grad_norm": 0.7080956301908629, + "learning_rate": 1.990953574263659e-05, + "loss": 1.0862, + "step": 1166 + }, + { + "epoch": 0.0716412412904018, + "grad_norm": 0.6345636759262663, + "learning_rate": 1.990926870003324e-05, + "loss": 1.0697, + "step": 1167 + }, + { + "epoch": 0.07170263052886829, + "grad_norm": 0.6524717491398623, + "learning_rate": 1.9909001265663503e-05, + "loss": 1.0493, + "step": 1168 + }, + { + "epoch": 0.07176401976733479, + "grad_norm": 0.7212720032882652, + "learning_rate": 1.990873343953795e-05, + "loss": 1.1421, + "step": 1169 + }, + { + "epoch": 0.07182540900580128, + "grad_norm": 0.6388857897991497, + "learning_rate": 1.990846522166717e-05, + "loss": 1.0449, + "step": 1170 + }, + { + "epoch": 0.07188679824426777, + "grad_norm": 0.612162676657075, + "learning_rate": 1.990819661206176e-05, + "loss": 1.0561, + "step": 1171 + }, + { + "epoch": 0.07194818748273428, + "grad_norm": 0.7107228693354353, + "learning_rate": 1.990792761073235e-05, + "loss": 1.0977, + "step": 1172 + }, + { + "epoch": 0.07200957672120077, + "grad_norm": 0.7278721693709481, + "learning_rate": 1.9907658217689572e-05, + "loss": 1.0883, + "step": 1173 + }, + { + "epoch": 0.07207096595966728, + "grad_norm": 0.6447558373391024, + "learning_rate": 1.990738843294407e-05, + "loss": 1.0435, + "step": 1174 + }, + { + "epoch": 0.07213235519813377, + "grad_norm": 0.6311201362243619, + "learning_rate": 1.9907118256506517e-05, + "loss": 1.024, + "step": 1175 + }, + { + "epoch": 0.07219374443660026, + "grad_norm": 0.6531122364811534, + "learning_rate": 1.9906847688387595e-05, + "loss": 1.0723, + "step": 1176 + }, + { + "epoch": 0.07225513367506677, + "grad_norm": 0.6666159659538331, + "learning_rate": 1.9906576728597993e-05, + "loss": 1.0781, + "step": 1177 + }, + { + "epoch": 0.07231652291353326, + "grad_norm": 0.6547825375264916, + "learning_rate": 1.9906305377148433e-05, + "loss": 1.0598, + "step": 1178 + }, + { + "epoch": 0.07237791215199975, + "grad_norm": 0.6904419033367016, + "learning_rate": 1.990603363404964e-05, + "loss": 1.0298, + "step": 1179 + }, + { + "epoch": 0.07243930139046625, + "grad_norm": 0.6856397324398299, + "learning_rate": 1.990576149931235e-05, + "loss": 1.042, + "step": 1180 + }, + { + "epoch": 0.07250069062893275, + "grad_norm": 0.654833337442677, + "learning_rate": 1.990548897294733e-05, + "loss": 1.0251, + "step": 1181 + }, + { + "epoch": 0.07256207986739925, + "grad_norm": 0.7066209121485609, + "learning_rate": 1.9905216054965355e-05, + "loss": 1.055, + "step": 1182 + }, + { + "epoch": 0.07262346910586574, + "grad_norm": 0.6874369644497799, + "learning_rate": 1.990494274537721e-05, + "loss": 1.1331, + "step": 1183 + }, + { + "epoch": 0.07268485834433223, + "grad_norm": 0.7069161731415348, + "learning_rate": 1.9904669044193708e-05, + "loss": 1.0878, + "step": 1184 + }, + { + "epoch": 0.07274624758279874, + "grad_norm": 0.7348960038203817, + "learning_rate": 1.990439495142566e-05, + "loss": 1.0989, + "step": 1185 + }, + { + "epoch": 0.07280763682126523, + "grad_norm": 0.6883636103220163, + "learning_rate": 1.9904120467083907e-05, + "loss": 1.129, + "step": 1186 + }, + { + "epoch": 0.07286902605973172, + "grad_norm": 0.6861980383478783, + "learning_rate": 1.9903845591179304e-05, + "loss": 1.1348, + "step": 1187 + }, + { + "epoch": 0.07293041529819823, + "grad_norm": 0.6535656162123444, + "learning_rate": 1.9903570323722713e-05, + "loss": 1.1232, + "step": 1188 + }, + { + "epoch": 0.07299180453666472, + "grad_norm": 0.6985496503733047, + "learning_rate": 1.9903294664725023e-05, + "loss": 1.1286, + "step": 1189 + }, + { + "epoch": 0.07305319377513123, + "grad_norm": 0.673339520302694, + "learning_rate": 1.9903018614197124e-05, + "loss": 1.0911, + "step": 1190 + }, + { + "epoch": 0.07311458301359772, + "grad_norm": 0.6747924937256289, + "learning_rate": 1.9902742172149933e-05, + "loss": 1.1176, + "step": 1191 + }, + { + "epoch": 0.07317597225206421, + "grad_norm": 0.6781197284329273, + "learning_rate": 1.9902465338594382e-05, + "loss": 1.0621, + "step": 1192 + }, + { + "epoch": 0.07323736149053071, + "grad_norm": 0.7280516332121005, + "learning_rate": 1.9902188113541417e-05, + "loss": 1.1649, + "step": 1193 + }, + { + "epoch": 0.0732987507289972, + "grad_norm": 0.6711948761214023, + "learning_rate": 1.9901910497001993e-05, + "loss": 1.0235, + "step": 1194 + }, + { + "epoch": 0.0733601399674637, + "grad_norm": 0.6936214323264366, + "learning_rate": 1.990163248898709e-05, + "loss": 1.0633, + "step": 1195 + }, + { + "epoch": 0.0734215292059302, + "grad_norm": 0.703150500439566, + "learning_rate": 1.9901354089507692e-05, + "loss": 1.0917, + "step": 1196 + }, + { + "epoch": 0.0734829184443967, + "grad_norm": 0.6570469375314075, + "learning_rate": 1.990107529857481e-05, + "loss": 1.0887, + "step": 1197 + }, + { + "epoch": 0.0735443076828632, + "grad_norm": 0.7602470479560757, + "learning_rate": 1.9900796116199473e-05, + "loss": 1.1161, + "step": 1198 + }, + { + "epoch": 0.07360569692132969, + "grad_norm": 0.6994961383062325, + "learning_rate": 1.990051654239271e-05, + "loss": 1.044, + "step": 1199 + }, + { + "epoch": 0.07366708615979618, + "grad_norm": 0.7010593743640783, + "learning_rate": 1.990023657716558e-05, + "loss": 1.1104, + "step": 1200 + }, + { + "epoch": 0.07372847539826269, + "grad_norm": 0.7105241013830977, + "learning_rate": 1.9899956220529143e-05, + "loss": 1.1396, + "step": 1201 + }, + { + "epoch": 0.07378986463672918, + "grad_norm": 0.7113248748465393, + "learning_rate": 1.9899675472494487e-05, + "loss": 1.0744, + "step": 1202 + }, + { + "epoch": 0.07385125387519567, + "grad_norm": 0.6742523196921123, + "learning_rate": 1.9899394333072716e-05, + "loss": 1.0809, + "step": 1203 + }, + { + "epoch": 0.07391264311366218, + "grad_norm": 0.6777294640533121, + "learning_rate": 1.9899112802274937e-05, + "loss": 1.1084, + "step": 1204 + }, + { + "epoch": 0.07397403235212867, + "grad_norm": 0.8906727128537909, + "learning_rate": 1.989883088011229e-05, + "loss": 0.8171, + "step": 1205 + }, + { + "epoch": 0.07403542159059517, + "grad_norm": 0.7005369838618182, + "learning_rate": 1.989854856659591e-05, + "loss": 1.1049, + "step": 1206 + }, + { + "epoch": 0.07409681082906167, + "grad_norm": 0.6657432971889637, + "learning_rate": 1.9898265861736968e-05, + "loss": 1.0818, + "step": 1207 + }, + { + "epoch": 0.07415820006752816, + "grad_norm": 0.7027338347722327, + "learning_rate": 1.989798276554664e-05, + "loss": 1.083, + "step": 1208 + }, + { + "epoch": 0.07421958930599466, + "grad_norm": 0.6538221000260378, + "learning_rate": 1.989769927803611e-05, + "loss": 1.1013, + "step": 1209 + }, + { + "epoch": 0.07428097854446115, + "grad_norm": 0.67623321466795, + "learning_rate": 1.989741539921659e-05, + "loss": 1.0993, + "step": 1210 + }, + { + "epoch": 0.07434236778292766, + "grad_norm": 0.7074209966907702, + "learning_rate": 1.9897131129099305e-05, + "loss": 1.1035, + "step": 1211 + }, + { + "epoch": 0.07440375702139415, + "grad_norm": 0.6513998342372012, + "learning_rate": 1.9896846467695498e-05, + "loss": 1.0894, + "step": 1212 + }, + { + "epoch": 0.07446514625986064, + "grad_norm": 0.666818805494858, + "learning_rate": 1.9896561415016412e-05, + "loss": 1.0329, + "step": 1213 + }, + { + "epoch": 0.07452653549832715, + "grad_norm": 0.727428742129116, + "learning_rate": 1.9896275971073326e-05, + "loss": 1.132, + "step": 1214 + }, + { + "epoch": 0.07458792473679364, + "grad_norm": 0.6895607244929954, + "learning_rate": 1.989599013587752e-05, + "loss": 1.1348, + "step": 1215 + }, + { + "epoch": 0.07464931397526013, + "grad_norm": 0.640164539894167, + "learning_rate": 1.9895703909440297e-05, + "loss": 1.0897, + "step": 1216 + }, + { + "epoch": 0.07471070321372664, + "grad_norm": 0.6771501379472306, + "learning_rate": 1.9895417291772973e-05, + "loss": 1.1139, + "step": 1217 + }, + { + "epoch": 0.07477209245219313, + "grad_norm": 0.665542579461997, + "learning_rate": 1.9895130282886877e-05, + "loss": 1.0978, + "step": 1218 + }, + { + "epoch": 0.07483348169065963, + "grad_norm": 0.6500873773346818, + "learning_rate": 1.989484288279336e-05, + "loss": 1.0829, + "step": 1219 + }, + { + "epoch": 0.07489487092912613, + "grad_norm": 0.7020016957014867, + "learning_rate": 1.9894555091503785e-05, + "loss": 1.0949, + "step": 1220 + }, + { + "epoch": 0.07495626016759262, + "grad_norm": 0.6721564784808093, + "learning_rate": 1.9894266909029522e-05, + "loss": 1.1045, + "step": 1221 + }, + { + "epoch": 0.07501764940605912, + "grad_norm": 0.7020712752366058, + "learning_rate": 1.9893978335381973e-05, + "loss": 1.0621, + "step": 1222 + }, + { + "epoch": 0.07507903864452561, + "grad_norm": 0.7100175775858872, + "learning_rate": 1.9893689370572543e-05, + "loss": 1.1239, + "step": 1223 + }, + { + "epoch": 0.0751404278829921, + "grad_norm": 0.6543590794852634, + "learning_rate": 1.989340001461266e-05, + "loss": 1.092, + "step": 1224 + }, + { + "epoch": 0.07520181712145861, + "grad_norm": 0.6543028522505795, + "learning_rate": 1.9893110267513755e-05, + "loss": 1.0747, + "step": 1225 + }, + { + "epoch": 0.0752632063599251, + "grad_norm": 0.6694508848878663, + "learning_rate": 1.9892820129287292e-05, + "loss": 1.0922, + "step": 1226 + }, + { + "epoch": 0.07532459559839161, + "grad_norm": 0.636100047204753, + "learning_rate": 1.9892529599944738e-05, + "loss": 1.0039, + "step": 1227 + }, + { + "epoch": 0.0753859848368581, + "grad_norm": 0.6960003971768086, + "learning_rate": 1.9892238679497582e-05, + "loss": 1.1133, + "step": 1228 + }, + { + "epoch": 0.07544737407532459, + "grad_norm": 0.7316420725944748, + "learning_rate": 1.9891947367957323e-05, + "loss": 1.164, + "step": 1229 + }, + { + "epoch": 0.0755087633137911, + "grad_norm": 0.7103523109210728, + "learning_rate": 1.9891655665335478e-05, + "loss": 1.1286, + "step": 1230 + }, + { + "epoch": 0.07557015255225759, + "grad_norm": 0.6716599479159319, + "learning_rate": 1.989136357164358e-05, + "loss": 1.0416, + "step": 1231 + }, + { + "epoch": 0.07563154179072408, + "grad_norm": 0.6693866634865656, + "learning_rate": 1.989107108689318e-05, + "loss": 0.8689, + "step": 1232 + }, + { + "epoch": 0.07569293102919059, + "grad_norm": 0.6916343428005325, + "learning_rate": 1.9890778211095836e-05, + "loss": 1.0859, + "step": 1233 + }, + { + "epoch": 0.07575432026765708, + "grad_norm": 0.7207366642452433, + "learning_rate": 1.989048494426313e-05, + "loss": 1.1203, + "step": 1234 + }, + { + "epoch": 0.07581570950612358, + "grad_norm": 0.6581840648672491, + "learning_rate": 1.9890191286406654e-05, + "loss": 1.0563, + "step": 1235 + }, + { + "epoch": 0.07587709874459007, + "grad_norm": 0.717640598530229, + "learning_rate": 1.9889897237538023e-05, + "loss": 1.1403, + "step": 1236 + }, + { + "epoch": 0.07593848798305657, + "grad_norm": 0.7101334147568602, + "learning_rate": 1.988960279766886e-05, + "loss": 1.1299, + "step": 1237 + }, + { + "epoch": 0.07599987722152307, + "grad_norm": 0.7209425226034124, + "learning_rate": 1.98893079668108e-05, + "loss": 1.1058, + "step": 1238 + }, + { + "epoch": 0.07606126645998956, + "grad_norm": 0.6823036108695696, + "learning_rate": 1.9889012744975508e-05, + "loss": 1.071, + "step": 1239 + }, + { + "epoch": 0.07612265569845605, + "grad_norm": 0.6661713410414749, + "learning_rate": 1.9888717132174655e-05, + "loss": 1.0486, + "step": 1240 + }, + { + "epoch": 0.07618404493692256, + "grad_norm": 0.7074052720363125, + "learning_rate": 1.988842112841992e-05, + "loss": 1.0599, + "step": 1241 + }, + { + "epoch": 0.07624543417538905, + "grad_norm": 0.7091297016328018, + "learning_rate": 1.9888124733723015e-05, + "loss": 1.1082, + "step": 1242 + }, + { + "epoch": 0.07630682341385556, + "grad_norm": 0.6802820464044725, + "learning_rate": 1.988782794809565e-05, + "loss": 1.0723, + "step": 1243 + }, + { + "epoch": 0.07636821265232205, + "grad_norm": 0.6443787451486733, + "learning_rate": 1.9887530771549567e-05, + "loss": 1.0375, + "step": 1244 + }, + { + "epoch": 0.07642960189078854, + "grad_norm": 0.6341201227286372, + "learning_rate": 1.9887233204096504e-05, + "loss": 1.0622, + "step": 1245 + }, + { + "epoch": 0.07649099112925505, + "grad_norm": 0.7448995152839728, + "learning_rate": 1.988693524574824e-05, + "loss": 1.1788, + "step": 1246 + }, + { + "epoch": 0.07655238036772154, + "grad_norm": 0.7158397005462301, + "learning_rate": 1.988663689651654e-05, + "loss": 1.1202, + "step": 1247 + }, + { + "epoch": 0.07661376960618803, + "grad_norm": 0.669757354674869, + "learning_rate": 1.9886338156413206e-05, + "loss": 1.0617, + "step": 1248 + }, + { + "epoch": 0.07667515884465453, + "grad_norm": 0.6701615301518142, + "learning_rate": 1.9886039025450053e-05, + "loss": 1.0603, + "step": 1249 + }, + { + "epoch": 0.07673654808312103, + "grad_norm": 0.7000855116984185, + "learning_rate": 1.98857395036389e-05, + "loss": 1.0794, + "step": 1250 + }, + { + "epoch": 0.07679793732158753, + "grad_norm": 0.648663984074384, + "learning_rate": 1.9885439590991592e-05, + "loss": 1.0674, + "step": 1251 + }, + { + "epoch": 0.07685932656005402, + "grad_norm": 0.6725933266830767, + "learning_rate": 1.9885139287519988e-05, + "loss": 1.075, + "step": 1252 + }, + { + "epoch": 0.07692071579852051, + "grad_norm": 0.7142853265463477, + "learning_rate": 1.9884838593235957e-05, + "loss": 1.0973, + "step": 1253 + }, + { + "epoch": 0.07698210503698702, + "grad_norm": 0.6902679514169369, + "learning_rate": 1.988453750815139e-05, + "loss": 1.0782, + "step": 1254 + }, + { + "epoch": 0.07704349427545351, + "grad_norm": 0.6876998235902526, + "learning_rate": 1.9884236032278186e-05, + "loss": 1.1495, + "step": 1255 + }, + { + "epoch": 0.07710488351392002, + "grad_norm": 0.7129175842853513, + "learning_rate": 1.9883934165628268e-05, + "loss": 1.128, + "step": 1256 + }, + { + "epoch": 0.07716627275238651, + "grad_norm": 0.7085462050754693, + "learning_rate": 1.9883631908213573e-05, + "loss": 1.1456, + "step": 1257 + }, + { + "epoch": 0.077227661990853, + "grad_norm": 0.7004641917895098, + "learning_rate": 1.9883329260046046e-05, + "loss": 1.1297, + "step": 1258 + }, + { + "epoch": 0.0772890512293195, + "grad_norm": 0.7015884470138131, + "learning_rate": 1.988302622113765e-05, + "loss": 1.1224, + "step": 1259 + }, + { + "epoch": 0.077350440467786, + "grad_norm": 0.6555938895634458, + "learning_rate": 1.988272279150037e-05, + "loss": 1.035, + "step": 1260 + }, + { + "epoch": 0.07741182970625249, + "grad_norm": 0.7328026073666979, + "learning_rate": 1.9882418971146205e-05, + "loss": 1.082, + "step": 1261 + }, + { + "epoch": 0.077473218944719, + "grad_norm": 0.692497369233986, + "learning_rate": 1.9882114760087162e-05, + "loss": 1.1215, + "step": 1262 + }, + { + "epoch": 0.07753460818318549, + "grad_norm": 0.6599840064577794, + "learning_rate": 1.9881810158335266e-05, + "loss": 1.066, + "step": 1263 + }, + { + "epoch": 0.07759599742165199, + "grad_norm": 0.666019724089613, + "learning_rate": 1.9881505165902566e-05, + "loss": 1.0795, + "step": 1264 + }, + { + "epoch": 0.07765738666011848, + "grad_norm": 0.7326925821928183, + "learning_rate": 1.9881199782801117e-05, + "loss": 1.1111, + "step": 1265 + }, + { + "epoch": 0.07771877589858497, + "grad_norm": 0.6498928515385523, + "learning_rate": 1.9880894009042993e-05, + "loss": 1.0222, + "step": 1266 + }, + { + "epoch": 0.07778016513705148, + "grad_norm": 0.6987105751930327, + "learning_rate": 1.9880587844640278e-05, + "loss": 1.0634, + "step": 1267 + }, + { + "epoch": 0.07784155437551797, + "grad_norm": 0.6750939539372697, + "learning_rate": 1.9880281289605086e-05, + "loss": 1.0823, + "step": 1268 + }, + { + "epoch": 0.07790294361398446, + "grad_norm": 0.6640451746769649, + "learning_rate": 1.9879974343949527e-05, + "loss": 1.0275, + "step": 1269 + }, + { + "epoch": 0.07796433285245097, + "grad_norm": 0.662294306612269, + "learning_rate": 1.987966700768574e-05, + "loss": 1.044, + "step": 1270 + }, + { + "epoch": 0.07802572209091746, + "grad_norm": 0.7042470251359225, + "learning_rate": 1.987935928082588e-05, + "loss": 1.0586, + "step": 1271 + }, + { + "epoch": 0.07808711132938397, + "grad_norm": 0.6805166778420365, + "learning_rate": 1.9879051163382105e-05, + "loss": 1.0949, + "step": 1272 + }, + { + "epoch": 0.07814850056785046, + "grad_norm": 0.6915497583222754, + "learning_rate": 1.98787426553666e-05, + "loss": 1.1636, + "step": 1273 + }, + { + "epoch": 0.07820988980631695, + "grad_norm": 0.6629775228656147, + "learning_rate": 1.9878433756791568e-05, + "loss": 1.0638, + "step": 1274 + }, + { + "epoch": 0.07827127904478345, + "grad_norm": 0.6788124287821918, + "learning_rate": 1.9878124467669212e-05, + "loss": 1.0847, + "step": 1275 + }, + { + "epoch": 0.07833266828324995, + "grad_norm": 0.7028293777687599, + "learning_rate": 1.9877814788011762e-05, + "loss": 1.1235, + "step": 1276 + }, + { + "epoch": 0.07839405752171644, + "grad_norm": 0.6621964612796791, + "learning_rate": 1.9877504717831466e-05, + "loss": 1.107, + "step": 1277 + }, + { + "epoch": 0.07845544676018294, + "grad_norm": 0.7082503364992688, + "learning_rate": 1.9877194257140582e-05, + "loss": 1.1105, + "step": 1278 + }, + { + "epoch": 0.07851683599864943, + "grad_norm": 0.6674980410732266, + "learning_rate": 1.9876883405951378e-05, + "loss": 1.0783, + "step": 1279 + }, + { + "epoch": 0.07857822523711594, + "grad_norm": 0.6941684043931318, + "learning_rate": 1.987657216427615e-05, + "loss": 1.1108, + "step": 1280 + }, + { + "epoch": 0.07863961447558243, + "grad_norm": 0.7130976670089118, + "learning_rate": 1.98762605321272e-05, + "loss": 1.1114, + "step": 1281 + }, + { + "epoch": 0.07870100371404892, + "grad_norm": 0.6352938258815553, + "learning_rate": 1.987594850951685e-05, + "loss": 1.083, + "step": 1282 + }, + { + "epoch": 0.07876239295251543, + "grad_norm": 0.7050536046257111, + "learning_rate": 1.9875636096457437e-05, + "loss": 1.113, + "step": 1283 + }, + { + "epoch": 0.07882378219098192, + "grad_norm": 0.6888520705893915, + "learning_rate": 1.9875323292961302e-05, + "loss": 1.1008, + "step": 1284 + }, + { + "epoch": 0.07888517142944841, + "grad_norm": 0.7198183848737302, + "learning_rate": 1.987501009904083e-05, + "loss": 1.0972, + "step": 1285 + }, + { + "epoch": 0.07894656066791492, + "grad_norm": 0.6202798965157912, + "learning_rate": 1.987469651470839e-05, + "loss": 1.0331, + "step": 1286 + }, + { + "epoch": 0.07900794990638141, + "grad_norm": 0.676330980467933, + "learning_rate": 1.9874382539976383e-05, + "loss": 1.1084, + "step": 1287 + }, + { + "epoch": 0.07906933914484791, + "grad_norm": 0.679862807611879, + "learning_rate": 1.9874068174857222e-05, + "loss": 1.0936, + "step": 1288 + }, + { + "epoch": 0.0791307283833144, + "grad_norm": 0.660141554837642, + "learning_rate": 1.9873753419363336e-05, + "loss": 1.0753, + "step": 1289 + }, + { + "epoch": 0.0791921176217809, + "grad_norm": 0.6481050015964666, + "learning_rate": 1.9873438273507168e-05, + "loss": 1.087, + "step": 1290 + }, + { + "epoch": 0.0792535068602474, + "grad_norm": 0.6911096344091918, + "learning_rate": 1.987312273730118e-05, + "loss": 1.112, + "step": 1291 + }, + { + "epoch": 0.0793148960987139, + "grad_norm": 0.6312228523528657, + "learning_rate": 1.9872806810757847e-05, + "loss": 1.0378, + "step": 1292 + }, + { + "epoch": 0.07937628533718039, + "grad_norm": 0.6637829169702961, + "learning_rate": 1.987249049388965e-05, + "loss": 1.0554, + "step": 1293 + }, + { + "epoch": 0.07943767457564689, + "grad_norm": 0.6798116393849004, + "learning_rate": 1.987217378670911e-05, + "loss": 1.0917, + "step": 1294 + }, + { + "epoch": 0.07949906381411338, + "grad_norm": 0.6489974406193164, + "learning_rate": 1.9871856689228735e-05, + "loss": 1.0566, + "step": 1295 + }, + { + "epoch": 0.07956045305257989, + "grad_norm": 0.6502007204833166, + "learning_rate": 1.987153920146107e-05, + "loss": 1.1184, + "step": 1296 + }, + { + "epoch": 0.07962184229104638, + "grad_norm": 0.6741393645519193, + "learning_rate": 1.9871221323418658e-05, + "loss": 1.0805, + "step": 1297 + }, + { + "epoch": 0.07968323152951287, + "grad_norm": 0.6930388477647191, + "learning_rate": 1.9870903055114077e-05, + "loss": 1.0598, + "step": 1298 + }, + { + "epoch": 0.07974462076797938, + "grad_norm": 0.653811523070972, + "learning_rate": 1.9870584396559903e-05, + "loss": 1.1074, + "step": 1299 + }, + { + "epoch": 0.07980601000644587, + "grad_norm": 0.6829674326470295, + "learning_rate": 1.987026534776874e-05, + "loss": 1.1208, + "step": 1300 + }, + { + "epoch": 0.07986739924491237, + "grad_norm": 0.6349345937862585, + "learning_rate": 1.9869945908753193e-05, + "loss": 1.0396, + "step": 1301 + }, + { + "epoch": 0.07992878848337887, + "grad_norm": 0.6878358785578925, + "learning_rate": 1.98696260795259e-05, + "loss": 1.1037, + "step": 1302 + }, + { + "epoch": 0.07999017772184536, + "grad_norm": 0.6726757634521369, + "learning_rate": 1.9869305860099498e-05, + "loss": 1.0814, + "step": 1303 + }, + { + "epoch": 0.08005156696031186, + "grad_norm": 0.7103424875900444, + "learning_rate": 1.986898525048665e-05, + "loss": 1.0935, + "step": 1304 + }, + { + "epoch": 0.08011295619877835, + "grad_norm": 0.6737142189254659, + "learning_rate": 1.9868664250700034e-05, + "loss": 1.0483, + "step": 1305 + }, + { + "epoch": 0.08017434543724485, + "grad_norm": 0.7066946946342334, + "learning_rate": 1.9868342860752342e-05, + "loss": 1.0746, + "step": 1306 + }, + { + "epoch": 0.08023573467571135, + "grad_norm": 0.7109646117577534, + "learning_rate": 1.9868021080656274e-05, + "loss": 1.0903, + "step": 1307 + }, + { + "epoch": 0.08029712391417784, + "grad_norm": 0.7275024180304587, + "learning_rate": 1.986769891042455e-05, + "loss": 1.1297, + "step": 1308 + }, + { + "epoch": 0.08035851315264435, + "grad_norm": 0.7074365720767986, + "learning_rate": 1.986737635006992e-05, + "loss": 1.0511, + "step": 1309 + }, + { + "epoch": 0.08041990239111084, + "grad_norm": 0.6709777948642535, + "learning_rate": 1.9867053399605126e-05, + "loss": 1.0834, + "step": 1310 + }, + { + "epoch": 0.08048129162957733, + "grad_norm": 0.6489332161627046, + "learning_rate": 1.986673005904294e-05, + "loss": 1.0629, + "step": 1311 + }, + { + "epoch": 0.08054268086804384, + "grad_norm": 0.7850815039322419, + "learning_rate": 1.986640632839614e-05, + "loss": 1.1343, + "step": 1312 + }, + { + "epoch": 0.08060407010651033, + "grad_norm": 0.7162291221933411, + "learning_rate": 1.986608220767753e-05, + "loss": 1.119, + "step": 1313 + }, + { + "epoch": 0.08066545934497682, + "grad_norm": 0.6790680972780807, + "learning_rate": 1.986575769689992e-05, + "loss": 1.0587, + "step": 1314 + }, + { + "epoch": 0.08072684858344333, + "grad_norm": 0.7281130418720468, + "learning_rate": 1.986543279607615e-05, + "loss": 1.1105, + "step": 1315 + }, + { + "epoch": 0.08078823782190982, + "grad_norm": 0.725800923810406, + "learning_rate": 1.986510750521905e-05, + "loss": 1.11, + "step": 1316 + }, + { + "epoch": 0.08084962706037632, + "grad_norm": 0.632908587116752, + "learning_rate": 1.986478182434149e-05, + "loss": 1.0475, + "step": 1317 + }, + { + "epoch": 0.08091101629884281, + "grad_norm": 0.6543347050100792, + "learning_rate": 1.9864455753456345e-05, + "loss": 1.0493, + "step": 1318 + }, + { + "epoch": 0.0809724055373093, + "grad_norm": 0.7047320480982899, + "learning_rate": 1.9864129292576508e-05, + "loss": 1.1123, + "step": 1319 + }, + { + "epoch": 0.08103379477577581, + "grad_norm": 0.7236858376381492, + "learning_rate": 1.9863802441714878e-05, + "loss": 1.0885, + "step": 1320 + }, + { + "epoch": 0.0810951840142423, + "grad_norm": 0.6545010516870394, + "learning_rate": 1.9863475200884386e-05, + "loss": 1.1188, + "step": 1321 + }, + { + "epoch": 0.0811565732527088, + "grad_norm": 0.655768608977828, + "learning_rate": 1.9863147570097963e-05, + "loss": 1.0872, + "step": 1322 + }, + { + "epoch": 0.0812179624911753, + "grad_norm": 0.7182760536293469, + "learning_rate": 1.9862819549368566e-05, + "loss": 1.0914, + "step": 1323 + }, + { + "epoch": 0.08127935172964179, + "grad_norm": 0.6922718149616057, + "learning_rate": 1.986249113870916e-05, + "loss": 1.1046, + "step": 1324 + }, + { + "epoch": 0.0813407409681083, + "grad_norm": 0.6737482689748285, + "learning_rate": 1.9862162338132734e-05, + "loss": 1.032, + "step": 1325 + }, + { + "epoch": 0.08140213020657479, + "grad_norm": 0.6843065949012123, + "learning_rate": 1.9861833147652283e-05, + "loss": 1.1228, + "step": 1326 + }, + { + "epoch": 0.08146351944504128, + "grad_norm": 0.7475906702548317, + "learning_rate": 1.9861503567280822e-05, + "loss": 1.1291, + "step": 1327 + }, + { + "epoch": 0.08152490868350779, + "grad_norm": 0.6815067062732831, + "learning_rate": 1.986117359703138e-05, + "loss": 1.0917, + "step": 1328 + }, + { + "epoch": 0.08158629792197428, + "grad_norm": 0.7169673315326284, + "learning_rate": 1.986084323691701e-05, + "loss": 1.0962, + "step": 1329 + }, + { + "epoch": 0.08164768716044077, + "grad_norm": 0.641606474906938, + "learning_rate": 1.9860512486950764e-05, + "loss": 1.0435, + "step": 1330 + }, + { + "epoch": 0.08170907639890727, + "grad_norm": 0.6557365518258229, + "learning_rate": 1.9860181347145725e-05, + "loss": 1.0251, + "step": 1331 + }, + { + "epoch": 0.08177046563737377, + "grad_norm": 0.683838850850088, + "learning_rate": 1.9859849817514977e-05, + "loss": 1.1121, + "step": 1332 + }, + { + "epoch": 0.08183185487584027, + "grad_norm": 0.6711620334078024, + "learning_rate": 1.9859517898071634e-05, + "loss": 1.0566, + "step": 1333 + }, + { + "epoch": 0.08189324411430676, + "grad_norm": 0.7279589047164153, + "learning_rate": 1.9859185588828814e-05, + "loss": 1.1165, + "step": 1334 + }, + { + "epoch": 0.08195463335277325, + "grad_norm": 0.6434741446026196, + "learning_rate": 1.985885288979966e-05, + "loss": 1.0447, + "step": 1335 + }, + { + "epoch": 0.08201602259123976, + "grad_norm": 0.6864964356942505, + "learning_rate": 1.985851980099732e-05, + "loss": 1.061, + "step": 1336 + }, + { + "epoch": 0.08207741182970625, + "grad_norm": 0.6756015705624285, + "learning_rate": 1.9858186322434964e-05, + "loss": 1.0769, + "step": 1337 + }, + { + "epoch": 0.08213880106817274, + "grad_norm": 0.6504993835635161, + "learning_rate": 1.985785245412578e-05, + "loss": 1.0722, + "step": 1338 + }, + { + "epoch": 0.08220019030663925, + "grad_norm": 0.6788715624993804, + "learning_rate": 1.9857518196082964e-05, + "loss": 1.1193, + "step": 1339 + }, + { + "epoch": 0.08226157954510574, + "grad_norm": 0.6323721059744252, + "learning_rate": 1.9857183548319735e-05, + "loss": 1.0717, + "step": 1340 + }, + { + "epoch": 0.08232296878357225, + "grad_norm": 0.6938829011124276, + "learning_rate": 1.9856848510849315e-05, + "loss": 1.0769, + "step": 1341 + }, + { + "epoch": 0.08238435802203874, + "grad_norm": 0.6321963724765762, + "learning_rate": 1.9856513083684962e-05, + "loss": 1.0207, + "step": 1342 + }, + { + "epoch": 0.08244574726050523, + "grad_norm": 0.7051980891136295, + "learning_rate": 1.9856177266839924e-05, + "loss": 1.0867, + "step": 1343 + }, + { + "epoch": 0.08250713649897173, + "grad_norm": 0.7055727078541086, + "learning_rate": 1.985584106032749e-05, + "loss": 1.1143, + "step": 1344 + }, + { + "epoch": 0.08256852573743823, + "grad_norm": 0.6806766937729986, + "learning_rate": 1.985550446416094e-05, + "loss": 1.0192, + "step": 1345 + }, + { + "epoch": 0.08262991497590473, + "grad_norm": 0.7509973452768306, + "learning_rate": 1.985516747835359e-05, + "loss": 1.171, + "step": 1346 + }, + { + "epoch": 0.08269130421437122, + "grad_norm": 0.6623209874960058, + "learning_rate": 1.985483010291876e-05, + "loss": 1.0275, + "step": 1347 + }, + { + "epoch": 0.08275269345283771, + "grad_norm": 0.710743999240831, + "learning_rate": 1.985449233786979e-05, + "loss": 1.0858, + "step": 1348 + }, + { + "epoch": 0.08281408269130422, + "grad_norm": 0.6867397238881834, + "learning_rate": 1.985415418322003e-05, + "loss": 1.1041, + "step": 1349 + }, + { + "epoch": 0.08287547192977071, + "grad_norm": 0.6719360632282575, + "learning_rate": 1.9853815638982855e-05, + "loss": 1.0689, + "step": 1350 + }, + { + "epoch": 0.0829368611682372, + "grad_norm": 0.6762297783530292, + "learning_rate": 1.9853476705171642e-05, + "loss": 1.0745, + "step": 1351 + }, + { + "epoch": 0.08299825040670371, + "grad_norm": 0.6647345753028688, + "learning_rate": 1.98531373817998e-05, + "loss": 1.0806, + "step": 1352 + }, + { + "epoch": 0.0830596396451702, + "grad_norm": 0.6977504433803491, + "learning_rate": 1.9852797668880735e-05, + "loss": 1.1242, + "step": 1353 + }, + { + "epoch": 0.0831210288836367, + "grad_norm": 0.6959342000001993, + "learning_rate": 1.9852457566427882e-05, + "loss": 1.0828, + "step": 1354 + }, + { + "epoch": 0.0831824181221032, + "grad_norm": 0.6766571213985072, + "learning_rate": 1.9852117074454686e-05, + "loss": 1.0902, + "step": 1355 + }, + { + "epoch": 0.08324380736056969, + "grad_norm": 0.7016066993641292, + "learning_rate": 1.9851776192974613e-05, + "loss": 1.1328, + "step": 1356 + }, + { + "epoch": 0.0833051965990362, + "grad_norm": 0.6950899094534391, + "learning_rate": 1.985143492200113e-05, + "loss": 1.1323, + "step": 1357 + }, + { + "epoch": 0.08336658583750269, + "grad_norm": 0.6571739140317696, + "learning_rate": 1.985109326154774e-05, + "loss": 0.9996, + "step": 1358 + }, + { + "epoch": 0.08342797507596918, + "grad_norm": 0.675915395394673, + "learning_rate": 1.9850751211627945e-05, + "loss": 1.0499, + "step": 1359 + }, + { + "epoch": 0.08348936431443568, + "grad_norm": 0.6348880557550625, + "learning_rate": 1.985040877225527e-05, + "loss": 1.093, + "step": 1360 + }, + { + "epoch": 0.08355075355290217, + "grad_norm": 0.6474103655863352, + "learning_rate": 1.9850065943443253e-05, + "loss": 1.0948, + "step": 1361 + }, + { + "epoch": 0.08361214279136868, + "grad_norm": 0.7342553816715575, + "learning_rate": 1.9849722725205446e-05, + "loss": 1.1265, + "step": 1362 + }, + { + "epoch": 0.08367353202983517, + "grad_norm": 0.6290783624555605, + "learning_rate": 1.984937911755542e-05, + "loss": 1.0718, + "step": 1363 + }, + { + "epoch": 0.08373492126830166, + "grad_norm": 0.6113986601788274, + "learning_rate": 1.9849035120506756e-05, + "loss": 1.0483, + "step": 1364 + }, + { + "epoch": 0.08379631050676817, + "grad_norm": 0.7225623452831963, + "learning_rate": 1.9848690734073058e-05, + "loss": 1.0891, + "step": 1365 + }, + { + "epoch": 0.08385769974523466, + "grad_norm": 0.7089434984736036, + "learning_rate": 1.9848345958267944e-05, + "loss": 1.1009, + "step": 1366 + }, + { + "epoch": 0.08391908898370115, + "grad_norm": 0.7236254118045253, + "learning_rate": 1.9848000793105043e-05, + "loss": 1.0917, + "step": 1367 + }, + { + "epoch": 0.08398047822216766, + "grad_norm": 0.7020592626032717, + "learning_rate": 1.9847655238597997e-05, + "loss": 1.1479, + "step": 1368 + }, + { + "epoch": 0.08404186746063415, + "grad_norm": 0.6988354782643169, + "learning_rate": 1.9847309294760473e-05, + "loss": 1.1327, + "step": 1369 + }, + { + "epoch": 0.08410325669910065, + "grad_norm": 0.6845263959670228, + "learning_rate": 1.984696296160614e-05, + "loss": 1.1391, + "step": 1370 + }, + { + "epoch": 0.08416464593756715, + "grad_norm": 0.6679914072669327, + "learning_rate": 1.9846616239148702e-05, + "loss": 1.0878, + "step": 1371 + }, + { + "epoch": 0.08422603517603364, + "grad_norm": 0.7061419133143796, + "learning_rate": 1.9846269127401858e-05, + "loss": 1.1657, + "step": 1372 + }, + { + "epoch": 0.08428742441450014, + "grad_norm": 0.6545805617076057, + "learning_rate": 1.9845921626379333e-05, + "loss": 1.1126, + "step": 1373 + }, + { + "epoch": 0.08434881365296663, + "grad_norm": 0.6799555534798515, + "learning_rate": 1.984557373609487e-05, + "loss": 1.0623, + "step": 1374 + }, + { + "epoch": 0.08441020289143313, + "grad_norm": 0.6641302195447969, + "learning_rate": 1.9845225456562213e-05, + "loss": 1.0993, + "step": 1375 + }, + { + "epoch": 0.08447159212989963, + "grad_norm": 0.6279977972778701, + "learning_rate": 1.984487678779514e-05, + "loss": 1.0339, + "step": 1376 + }, + { + "epoch": 0.08453298136836612, + "grad_norm": 0.7624631167362479, + "learning_rate": 1.9844527729807436e-05, + "loss": 1.158, + "step": 1377 + }, + { + "epoch": 0.08459437060683263, + "grad_norm": 0.6871003867299504, + "learning_rate": 1.9844178282612897e-05, + "loss": 1.084, + "step": 1378 + }, + { + "epoch": 0.08465575984529912, + "grad_norm": 0.7056734462487091, + "learning_rate": 1.984382844622534e-05, + "loss": 1.1401, + "step": 1379 + }, + { + "epoch": 0.08471714908376561, + "grad_norm": 0.6729246912359819, + "learning_rate": 1.98434782206586e-05, + "loss": 1.0353, + "step": 1380 + }, + { + "epoch": 0.08477853832223212, + "grad_norm": 0.6939409691940995, + "learning_rate": 1.9843127605926513e-05, + "loss": 1.0709, + "step": 1381 + }, + { + "epoch": 0.08483992756069861, + "grad_norm": 0.7285644866909117, + "learning_rate": 1.9842776602042952e-05, + "loss": 1.1191, + "step": 1382 + }, + { + "epoch": 0.0849013167991651, + "grad_norm": 0.7088384235200776, + "learning_rate": 1.9842425209021785e-05, + "loss": 1.1172, + "step": 1383 + }, + { + "epoch": 0.0849627060376316, + "grad_norm": 0.7006751892717372, + "learning_rate": 1.984207342687691e-05, + "loss": 1.1061, + "step": 1384 + }, + { + "epoch": 0.0850240952760981, + "grad_norm": 0.6219489390790895, + "learning_rate": 1.9841721255622235e-05, + "loss": 1.0092, + "step": 1385 + }, + { + "epoch": 0.0850854845145646, + "grad_norm": 0.6671692138988189, + "learning_rate": 1.9841368695271682e-05, + "loss": 1.1134, + "step": 1386 + }, + { + "epoch": 0.0851468737530311, + "grad_norm": 0.7133594967349834, + "learning_rate": 1.9841015745839188e-05, + "loss": 1.0822, + "step": 1387 + }, + { + "epoch": 0.08520826299149759, + "grad_norm": 0.6941178356416575, + "learning_rate": 1.9840662407338707e-05, + "loss": 1.1221, + "step": 1388 + }, + { + "epoch": 0.08526965222996409, + "grad_norm": 0.6545155413423954, + "learning_rate": 1.9840308679784207e-05, + "loss": 1.0084, + "step": 1389 + }, + { + "epoch": 0.08533104146843058, + "grad_norm": 0.7066362436566641, + "learning_rate": 1.983995456318968e-05, + "loss": 1.1492, + "step": 1390 + }, + { + "epoch": 0.08539243070689709, + "grad_norm": 0.7416163431838715, + "learning_rate": 1.983960005756912e-05, + "loss": 1.1394, + "step": 1391 + }, + { + "epoch": 0.08545381994536358, + "grad_norm": 0.7060757238916422, + "learning_rate": 1.9839245162936543e-05, + "loss": 1.1365, + "step": 1392 + }, + { + "epoch": 0.08551520918383007, + "grad_norm": 0.6511953162933705, + "learning_rate": 1.983888987930598e-05, + "loss": 1.0405, + "step": 1393 + }, + { + "epoch": 0.08557659842229658, + "grad_norm": 0.740508158667697, + "learning_rate": 1.983853420669148e-05, + "loss": 1.1064, + "step": 1394 + }, + { + "epoch": 0.08563798766076307, + "grad_norm": 0.6920004713960293, + "learning_rate": 1.98381781451071e-05, + "loss": 1.1356, + "step": 1395 + }, + { + "epoch": 0.08569937689922956, + "grad_norm": 0.7433249719459694, + "learning_rate": 1.9837821694566924e-05, + "loss": 1.1815, + "step": 1396 + }, + { + "epoch": 0.08576076613769607, + "grad_norm": 0.696767344020618, + "learning_rate": 1.9837464855085035e-05, + "loss": 1.1239, + "step": 1397 + }, + { + "epoch": 0.08582215537616256, + "grad_norm": 0.6554708155609612, + "learning_rate": 1.983710762667555e-05, + "loss": 1.1266, + "step": 1398 + }, + { + "epoch": 0.08588354461462906, + "grad_norm": 0.7502510070744033, + "learning_rate": 1.9836750009352585e-05, + "loss": 1.1065, + "step": 1399 + }, + { + "epoch": 0.08594493385309555, + "grad_norm": 0.6702825651915627, + "learning_rate": 1.983639200313028e-05, + "loss": 1.0789, + "step": 1400 + }, + { + "epoch": 0.08600632309156205, + "grad_norm": 0.7008901126732915, + "learning_rate": 1.98360336080228e-05, + "loss": 1.1162, + "step": 1401 + }, + { + "epoch": 0.08606771233002855, + "grad_norm": 0.6459172364111131, + "learning_rate": 1.9835674824044293e-05, + "loss": 1.1031, + "step": 1402 + }, + { + "epoch": 0.08612910156849504, + "grad_norm": 0.755740616152835, + "learning_rate": 1.9835315651208963e-05, + "loss": 1.1534, + "step": 1403 + }, + { + "epoch": 0.08619049080696153, + "grad_norm": 0.6681157190343344, + "learning_rate": 1.9834956089530998e-05, + "loss": 1.0865, + "step": 1404 + }, + { + "epoch": 0.08625188004542804, + "grad_norm": 0.6810239227754487, + "learning_rate": 1.983459613902462e-05, + "loss": 1.0974, + "step": 1405 + }, + { + "epoch": 0.08631326928389453, + "grad_norm": 0.6795051653103429, + "learning_rate": 1.9834235799704056e-05, + "loss": 1.0997, + "step": 1406 + }, + { + "epoch": 0.08637465852236104, + "grad_norm": 0.6639100696344961, + "learning_rate": 1.9833875071583556e-05, + "loss": 1.0411, + "step": 1407 + }, + { + "epoch": 0.08643604776082753, + "grad_norm": 0.6347491755951824, + "learning_rate": 1.983351395467738e-05, + "loss": 1.0456, + "step": 1408 + }, + { + "epoch": 0.08649743699929402, + "grad_norm": 0.6380651279310441, + "learning_rate": 1.9833152448999796e-05, + "loss": 1.0433, + "step": 1409 + }, + { + "epoch": 0.08655882623776052, + "grad_norm": 0.6711280327408194, + "learning_rate": 1.9832790554565112e-05, + "loss": 1.0768, + "step": 1410 + }, + { + "epoch": 0.08662021547622702, + "grad_norm": 0.6798867691554195, + "learning_rate": 1.9832428271387625e-05, + "loss": 1.0705, + "step": 1411 + }, + { + "epoch": 0.08668160471469351, + "grad_norm": 0.6897507264526679, + "learning_rate": 1.9832065599481663e-05, + "loss": 1.0773, + "step": 1412 + }, + { + "epoch": 0.08674299395316001, + "grad_norm": 0.6824525846258331, + "learning_rate": 1.983170253886156e-05, + "loss": 1.0805, + "step": 1413 + }, + { + "epoch": 0.0868043831916265, + "grad_norm": 0.7675650820406114, + "learning_rate": 1.9831339089541673e-05, + "loss": 1.1879, + "step": 1414 + }, + { + "epoch": 0.08686577243009301, + "grad_norm": 0.7042479393398464, + "learning_rate": 1.983097525153637e-05, + "loss": 1.1305, + "step": 1415 + }, + { + "epoch": 0.0869271616685595, + "grad_norm": 0.6707784362587442, + "learning_rate": 1.9830611024860037e-05, + "loss": 1.0562, + "step": 1416 + }, + { + "epoch": 0.086988550907026, + "grad_norm": 0.6961226745811974, + "learning_rate": 1.983024640952707e-05, + "loss": 1.1017, + "step": 1417 + }, + { + "epoch": 0.0870499401454925, + "grad_norm": 0.7020307909166009, + "learning_rate": 1.9829881405551887e-05, + "loss": 1.1063, + "step": 1418 + }, + { + "epoch": 0.08711132938395899, + "grad_norm": 0.6347973658325522, + "learning_rate": 1.982951601294892e-05, + "loss": 1.0173, + "step": 1419 + }, + { + "epoch": 0.08717271862242548, + "grad_norm": 0.6858927660375337, + "learning_rate": 1.9829150231732612e-05, + "loss": 1.1454, + "step": 1420 + }, + { + "epoch": 0.08723410786089199, + "grad_norm": 0.7174716624697643, + "learning_rate": 1.9828784061917423e-05, + "loss": 1.1247, + "step": 1421 + }, + { + "epoch": 0.08729549709935848, + "grad_norm": 0.7163979785386497, + "learning_rate": 1.9828417503517836e-05, + "loss": 1.0547, + "step": 1422 + }, + { + "epoch": 0.08735688633782498, + "grad_norm": 0.6429185761920143, + "learning_rate": 1.9828050556548335e-05, + "loss": 1.0767, + "step": 1423 + }, + { + "epoch": 0.08741827557629148, + "grad_norm": 0.6396050573719158, + "learning_rate": 1.9827683221023432e-05, + "loss": 1.0252, + "step": 1424 + }, + { + "epoch": 0.08747966481475797, + "grad_norm": 0.7035129073289565, + "learning_rate": 1.9827315496957652e-05, + "loss": 1.0823, + "step": 1425 + }, + { + "epoch": 0.08754105405322447, + "grad_norm": 0.6659627933380661, + "learning_rate": 1.982694738436553e-05, + "loss": 1.0393, + "step": 1426 + }, + { + "epoch": 0.08760244329169097, + "grad_norm": 0.6730428974384626, + "learning_rate": 1.9826578883261618e-05, + "loss": 1.0745, + "step": 1427 + }, + { + "epoch": 0.08766383253015746, + "grad_norm": 0.703221803918432, + "learning_rate": 1.9826209993660484e-05, + "loss": 1.0675, + "step": 1428 + }, + { + "epoch": 0.08772522176862396, + "grad_norm": 0.7177103349632418, + "learning_rate": 1.9825840715576722e-05, + "loss": 1.1008, + "step": 1429 + }, + { + "epoch": 0.08778661100709045, + "grad_norm": 0.6996324464355298, + "learning_rate": 1.9825471049024918e-05, + "loss": 1.0919, + "step": 1430 + }, + { + "epoch": 0.08784800024555696, + "grad_norm": 0.6845376950075036, + "learning_rate": 1.9825100994019694e-05, + "loss": 1.1226, + "step": 1431 + }, + { + "epoch": 0.08790938948402345, + "grad_norm": 0.6899998701941675, + "learning_rate": 1.982473055057568e-05, + "loss": 1.0735, + "step": 1432 + }, + { + "epoch": 0.08797077872248994, + "grad_norm": 0.6585829535693053, + "learning_rate": 1.982435971870752e-05, + "loss": 1.0695, + "step": 1433 + }, + { + "epoch": 0.08803216796095645, + "grad_norm": 0.6599823278194163, + "learning_rate": 1.982398849842988e-05, + "loss": 1.0977, + "step": 1434 + }, + { + "epoch": 0.08809355719942294, + "grad_norm": 0.6637914800304112, + "learning_rate": 1.982361688975743e-05, + "loss": 1.0769, + "step": 1435 + }, + { + "epoch": 0.08815494643788944, + "grad_norm": 0.5964520794947993, + "learning_rate": 1.9823244892704863e-05, + "loss": 1.0262, + "step": 1436 + }, + { + "epoch": 0.08821633567635594, + "grad_norm": 0.6529024768502161, + "learning_rate": 1.982287250728689e-05, + "loss": 1.0878, + "step": 1437 + }, + { + "epoch": 0.08827772491482243, + "grad_norm": 0.6751338465987011, + "learning_rate": 1.982249973351823e-05, + "loss": 1.0753, + "step": 1438 + }, + { + "epoch": 0.08833911415328893, + "grad_norm": 0.7355963415883586, + "learning_rate": 1.9822126571413616e-05, + "loss": 1.101, + "step": 1439 + }, + { + "epoch": 0.08840050339175543, + "grad_norm": 0.6504811393388658, + "learning_rate": 1.9821753020987808e-05, + "loss": 1.0589, + "step": 1440 + }, + { + "epoch": 0.08846189263022192, + "grad_norm": 0.6694662809270664, + "learning_rate": 1.9821379082255575e-05, + "loss": 1.0548, + "step": 1441 + }, + { + "epoch": 0.08852328186868842, + "grad_norm": 0.7204307142460576, + "learning_rate": 1.98210047552317e-05, + "loss": 1.1446, + "step": 1442 + }, + { + "epoch": 0.08858467110715491, + "grad_norm": 0.6712386612464672, + "learning_rate": 1.9820630039930976e-05, + "loss": 1.0586, + "step": 1443 + }, + { + "epoch": 0.08864606034562142, + "grad_norm": 0.7027733041294053, + "learning_rate": 1.9820254936368223e-05, + "loss": 1.1056, + "step": 1444 + }, + { + "epoch": 0.08870744958408791, + "grad_norm": 0.6824264039323775, + "learning_rate": 1.9819879444558272e-05, + "loss": 1.0989, + "step": 1445 + }, + { + "epoch": 0.0887688388225544, + "grad_norm": 0.7083388652146014, + "learning_rate": 1.9819503564515964e-05, + "loss": 1.1399, + "step": 1446 + }, + { + "epoch": 0.08883022806102091, + "grad_norm": 0.6947879957096403, + "learning_rate": 1.9819127296256165e-05, + "loss": 1.0444, + "step": 1447 + }, + { + "epoch": 0.0888916172994874, + "grad_norm": 0.672225908787004, + "learning_rate": 1.9818750639793744e-05, + "loss": 1.1086, + "step": 1448 + }, + { + "epoch": 0.08895300653795389, + "grad_norm": 0.6696618048568708, + "learning_rate": 1.98183735951436e-05, + "loss": 1.0806, + "step": 1449 + }, + { + "epoch": 0.0890143957764204, + "grad_norm": 0.6757648388212889, + "learning_rate": 1.981799616232063e-05, + "loss": 1.1029, + "step": 1450 + }, + { + "epoch": 0.08907578501488689, + "grad_norm": 0.69597366126493, + "learning_rate": 1.9817618341339764e-05, + "loss": 1.1844, + "step": 1451 + }, + { + "epoch": 0.0891371742533534, + "grad_norm": 0.726481848759993, + "learning_rate": 1.9817240132215934e-05, + "loss": 1.0777, + "step": 1452 + }, + { + "epoch": 0.08919856349181988, + "grad_norm": 0.7372397339140822, + "learning_rate": 1.9816861534964102e-05, + "loss": 1.1164, + "step": 1453 + }, + { + "epoch": 0.08925995273028638, + "grad_norm": 0.644109053043591, + "learning_rate": 1.9816482549599225e-05, + "loss": 1.0813, + "step": 1454 + }, + { + "epoch": 0.08932134196875288, + "grad_norm": 0.702277768142161, + "learning_rate": 1.981610317613629e-05, + "loss": 1.0896, + "step": 1455 + }, + { + "epoch": 0.08938273120721937, + "grad_norm": 0.655061580794906, + "learning_rate": 1.9815723414590295e-05, + "loss": 1.0344, + "step": 1456 + }, + { + "epoch": 0.08944412044568587, + "grad_norm": 0.648525442978186, + "learning_rate": 1.981534326497626e-05, + "loss": 1.0839, + "step": 1457 + }, + { + "epoch": 0.08950550968415237, + "grad_norm": 0.7079219592630253, + "learning_rate": 1.9814962727309206e-05, + "loss": 1.1268, + "step": 1458 + }, + { + "epoch": 0.08956689892261886, + "grad_norm": 0.6554847063845534, + "learning_rate": 1.981458180160418e-05, + "loss": 1.0294, + "step": 1459 + }, + { + "epoch": 0.08962828816108537, + "grad_norm": 0.7211549492023124, + "learning_rate": 1.9814200487876247e-05, + "loss": 1.0722, + "step": 1460 + }, + { + "epoch": 0.08968967739955186, + "grad_norm": 0.6273663863995919, + "learning_rate": 1.9813818786140476e-05, + "loss": 0.9938, + "step": 1461 + }, + { + "epoch": 0.08975106663801835, + "grad_norm": 0.6417616229928915, + "learning_rate": 1.9813436696411964e-05, + "loss": 1.0279, + "step": 1462 + }, + { + "epoch": 0.08981245587648486, + "grad_norm": 0.6771649069489594, + "learning_rate": 1.981305421870581e-05, + "loss": 1.0559, + "step": 1463 + }, + { + "epoch": 0.08987384511495135, + "grad_norm": 0.6640860098308586, + "learning_rate": 1.981267135303714e-05, + "loss": 1.0913, + "step": 1464 + }, + { + "epoch": 0.08993523435341784, + "grad_norm": 0.6676451177827608, + "learning_rate": 1.981228809942109e-05, + "loss": 1.0468, + "step": 1465 + }, + { + "epoch": 0.08999662359188434, + "grad_norm": 0.664363334420688, + "learning_rate": 1.981190445787281e-05, + "loss": 1.1373, + "step": 1466 + }, + { + "epoch": 0.09005801283035084, + "grad_norm": 0.6423979260091903, + "learning_rate": 1.9811520428407472e-05, + "loss": 1.0535, + "step": 1467 + }, + { + "epoch": 0.09011940206881734, + "grad_norm": 0.7174891754252274, + "learning_rate": 1.9811136011040254e-05, + "loss": 1.0691, + "step": 1468 + }, + { + "epoch": 0.09018079130728383, + "grad_norm": 0.6847076466481411, + "learning_rate": 1.9810751205786352e-05, + "loss": 1.0385, + "step": 1469 + }, + { + "epoch": 0.09024218054575033, + "grad_norm": 0.698589939323995, + "learning_rate": 1.9810366012660987e-05, + "loss": 1.149, + "step": 1470 + }, + { + "epoch": 0.09030356978421683, + "grad_norm": 0.6963404970759796, + "learning_rate": 1.9809980431679388e-05, + "loss": 1.0799, + "step": 1471 + }, + { + "epoch": 0.09036495902268332, + "grad_norm": 0.7541008648098109, + "learning_rate": 1.9809594462856788e-05, + "loss": 1.1323, + "step": 1472 + }, + { + "epoch": 0.09042634826114981, + "grad_norm": 0.6755304860047896, + "learning_rate": 1.980920810620846e-05, + "loss": 1.0905, + "step": 1473 + }, + { + "epoch": 0.09048773749961632, + "grad_norm": 0.6875184747235094, + "learning_rate": 1.980882136174967e-05, + "loss": 1.1496, + "step": 1474 + }, + { + "epoch": 0.09054912673808281, + "grad_norm": 0.6976423246143635, + "learning_rate": 1.9808434229495704e-05, + "loss": 1.15, + "step": 1475 + }, + { + "epoch": 0.09061051597654932, + "grad_norm": 0.661392754280013, + "learning_rate": 1.980804670946188e-05, + "loss": 0.9886, + "step": 1476 + }, + { + "epoch": 0.09067190521501581, + "grad_norm": 0.6860335775171864, + "learning_rate": 1.9807658801663513e-05, + "loss": 1.1009, + "step": 1477 + }, + { + "epoch": 0.0907332944534823, + "grad_norm": 0.6597202467347331, + "learning_rate": 1.9807270506115936e-05, + "loss": 1.1023, + "step": 1478 + }, + { + "epoch": 0.0907946836919488, + "grad_norm": 0.6463165708086689, + "learning_rate": 1.9806881822834503e-05, + "loss": 1.075, + "step": 1479 + }, + { + "epoch": 0.0908560729304153, + "grad_norm": 0.6536856399427041, + "learning_rate": 1.980649275183458e-05, + "loss": 1.0765, + "step": 1480 + }, + { + "epoch": 0.0909174621688818, + "grad_norm": 0.6599503872857708, + "learning_rate": 1.9806103293131552e-05, + "loss": 1.1271, + "step": 1481 + }, + { + "epoch": 0.0909788514073483, + "grad_norm": 0.6690625606622247, + "learning_rate": 1.9805713446740814e-05, + "loss": 1.106, + "step": 1482 + }, + { + "epoch": 0.09104024064581479, + "grad_norm": 0.6268207302663262, + "learning_rate": 1.9805323212677777e-05, + "loss": 1.048, + "step": 1483 + }, + { + "epoch": 0.09110162988428129, + "grad_norm": 0.6210246594176962, + "learning_rate": 1.9804932590957874e-05, + "loss": 0.9917, + "step": 1484 + }, + { + "epoch": 0.09116301912274778, + "grad_norm": 0.7524858051228759, + "learning_rate": 1.980454158159654e-05, + "loss": 1.095, + "step": 1485 + }, + { + "epoch": 0.09122440836121427, + "grad_norm": 0.6525148193035898, + "learning_rate": 1.9804150184609244e-05, + "loss": 1.0692, + "step": 1486 + }, + { + "epoch": 0.09128579759968078, + "grad_norm": 0.6694583417972336, + "learning_rate": 1.9803758400011452e-05, + "loss": 1.0827, + "step": 1487 + }, + { + "epoch": 0.09134718683814727, + "grad_norm": 0.6607730834494454, + "learning_rate": 1.9803366227818657e-05, + "loss": 1.0983, + "step": 1488 + }, + { + "epoch": 0.09140857607661378, + "grad_norm": 0.6167057526349067, + "learning_rate": 1.9802973668046364e-05, + "loss": 1.0414, + "step": 1489 + }, + { + "epoch": 0.09146996531508027, + "grad_norm": 0.6880560155164281, + "learning_rate": 1.980258072071009e-05, + "loss": 1.1352, + "step": 1490 + }, + { + "epoch": 0.09153135455354676, + "grad_norm": 0.6851891067623528, + "learning_rate": 1.9802187385825374e-05, + "loss": 1.0388, + "step": 1491 + }, + { + "epoch": 0.09159274379201326, + "grad_norm": 0.6487668664053071, + "learning_rate": 1.9801793663407763e-05, + "loss": 1.0518, + "step": 1492 + }, + { + "epoch": 0.09165413303047976, + "grad_norm": 0.6812306094738328, + "learning_rate": 1.9801399553472826e-05, + "loss": 1.1217, + "step": 1493 + }, + { + "epoch": 0.09171552226894625, + "grad_norm": 0.6606893266641892, + "learning_rate": 1.980100505603614e-05, + "loss": 1.06, + "step": 1494 + }, + { + "epoch": 0.09177691150741275, + "grad_norm": 0.7092960651338106, + "learning_rate": 1.980061017111331e-05, + "loss": 1.0791, + "step": 1495 + }, + { + "epoch": 0.09183830074587924, + "grad_norm": 0.6477164730701566, + "learning_rate": 1.980021489871994e-05, + "loss": 1.0479, + "step": 1496 + }, + { + "epoch": 0.09189968998434575, + "grad_norm": 0.6529749998374129, + "learning_rate": 1.979981923887166e-05, + "loss": 1.0217, + "step": 1497 + }, + { + "epoch": 0.09196107922281224, + "grad_norm": 0.6474852748325008, + "learning_rate": 1.9799423191584113e-05, + "loss": 1.0336, + "step": 1498 + }, + { + "epoch": 0.09202246846127873, + "grad_norm": 0.6959626520967063, + "learning_rate": 1.9799026756872957e-05, + "loss": 1.1107, + "step": 1499 + }, + { + "epoch": 0.09208385769974524, + "grad_norm": 0.6875486650024424, + "learning_rate": 1.979862993475386e-05, + "loss": 1.0783, + "step": 1500 + }, + { + "epoch": 0.09214524693821173, + "grad_norm": 0.7151820508151217, + "learning_rate": 1.979823272524252e-05, + "loss": 1.1069, + "step": 1501 + }, + { + "epoch": 0.09220663617667822, + "grad_norm": 0.6998245610406829, + "learning_rate": 1.979783512835463e-05, + "loss": 1.077, + "step": 1502 + }, + { + "epoch": 0.09226802541514473, + "grad_norm": 0.6469047876805166, + "learning_rate": 1.979743714410592e-05, + "loss": 1.0732, + "step": 1503 + }, + { + "epoch": 0.09232941465361122, + "grad_norm": 0.6675342811906272, + "learning_rate": 1.979703877251212e-05, + "loss": 1.0707, + "step": 1504 + }, + { + "epoch": 0.09239080389207772, + "grad_norm": 0.5998506742160346, + "learning_rate": 1.9796640013588976e-05, + "loss": 0.9699, + "step": 1505 + }, + { + "epoch": 0.09245219313054422, + "grad_norm": 0.7276016949039296, + "learning_rate": 1.9796240867352256e-05, + "loss": 1.0995, + "step": 1506 + }, + { + "epoch": 0.09251358236901071, + "grad_norm": 0.6710977125435101, + "learning_rate": 1.979584133381774e-05, + "loss": 1.0974, + "step": 1507 + }, + { + "epoch": 0.09257497160747721, + "grad_norm": 0.5995111607188922, + "learning_rate": 1.979544141300123e-05, + "loss": 1.0402, + "step": 1508 + }, + { + "epoch": 0.0926363608459437, + "grad_norm": 0.714730143618666, + "learning_rate": 1.9795041104918527e-05, + "loss": 1.1303, + "step": 1509 + }, + { + "epoch": 0.0926977500844102, + "grad_norm": 0.6651290187613784, + "learning_rate": 1.9794640409585463e-05, + "loss": 1.0569, + "step": 1510 + }, + { + "epoch": 0.0927591393228767, + "grad_norm": 0.698043034269697, + "learning_rate": 1.9794239327017873e-05, + "loss": 1.132, + "step": 1511 + }, + { + "epoch": 0.0928205285613432, + "grad_norm": 0.6433203090893231, + "learning_rate": 1.9793837857231625e-05, + "loss": 1.0764, + "step": 1512 + }, + { + "epoch": 0.0928819177998097, + "grad_norm": 0.6490100685160684, + "learning_rate": 1.979343600024258e-05, + "loss": 1.0705, + "step": 1513 + }, + { + "epoch": 0.09294330703827619, + "grad_norm": 0.6766291211338387, + "learning_rate": 1.9793033756066635e-05, + "loss": 1.053, + "step": 1514 + }, + { + "epoch": 0.09300469627674268, + "grad_norm": 0.6826235695057074, + "learning_rate": 1.9792631124719688e-05, + "loss": 1.1059, + "step": 1515 + }, + { + "epoch": 0.09306608551520919, + "grad_norm": 0.6918934537947246, + "learning_rate": 1.979222810621766e-05, + "loss": 1.0668, + "step": 1516 + }, + { + "epoch": 0.09312747475367568, + "grad_norm": 0.6522311468853118, + "learning_rate": 1.979182470057648e-05, + "loss": 1.0863, + "step": 1517 + }, + { + "epoch": 0.09318886399214217, + "grad_norm": 0.6378302999055452, + "learning_rate": 1.97914209078121e-05, + "loss": 1.0668, + "step": 1518 + }, + { + "epoch": 0.09325025323060868, + "grad_norm": 0.6581153221807214, + "learning_rate": 1.9791016727940482e-05, + "loss": 1.055, + "step": 1519 + }, + { + "epoch": 0.09331164246907517, + "grad_norm": 0.6990674735441055, + "learning_rate": 1.9790612160977608e-05, + "loss": 1.0796, + "step": 1520 + }, + { + "epoch": 0.09337303170754167, + "grad_norm": 0.6298574976865817, + "learning_rate": 1.979020720693947e-05, + "loss": 1.0583, + "step": 1521 + }, + { + "epoch": 0.09343442094600816, + "grad_norm": 0.6683062209678141, + "learning_rate": 1.978980186584208e-05, + "loss": 1.1064, + "step": 1522 + }, + { + "epoch": 0.09349581018447466, + "grad_norm": 0.6080161178926998, + "learning_rate": 1.9789396137701465e-05, + "loss": 0.998, + "step": 1523 + }, + { + "epoch": 0.09355719942294116, + "grad_norm": 0.6378332271315269, + "learning_rate": 1.9788990022533664e-05, + "loss": 1.0548, + "step": 1524 + }, + { + "epoch": 0.09361858866140765, + "grad_norm": 0.633585676792397, + "learning_rate": 1.9788583520354727e-05, + "loss": 1.0417, + "step": 1525 + }, + { + "epoch": 0.09367997789987416, + "grad_norm": 0.5727414225481741, + "learning_rate": 1.9788176631180735e-05, + "loss": 0.9781, + "step": 1526 + }, + { + "epoch": 0.09374136713834065, + "grad_norm": 0.8097402881552433, + "learning_rate": 1.9787769355027767e-05, + "loss": 0.8263, + "step": 1527 + }, + { + "epoch": 0.09380275637680714, + "grad_norm": 0.6466656305482733, + "learning_rate": 1.9787361691911927e-05, + "loss": 1.0837, + "step": 1528 + }, + { + "epoch": 0.09386414561527365, + "grad_norm": 0.6767814246648258, + "learning_rate": 1.9786953641849336e-05, + "loss": 1.0869, + "step": 1529 + }, + { + "epoch": 0.09392553485374014, + "grad_norm": 0.7225580495958375, + "learning_rate": 1.9786545204856122e-05, + "loss": 1.1216, + "step": 1530 + }, + { + "epoch": 0.09398692409220663, + "grad_norm": 0.7292351810136534, + "learning_rate": 1.978613638094843e-05, + "loss": 1.1362, + "step": 1531 + }, + { + "epoch": 0.09404831333067314, + "grad_norm": 0.6895935978715966, + "learning_rate": 1.9785727170142434e-05, + "loss": 1.0769, + "step": 1532 + }, + { + "epoch": 0.09410970256913963, + "grad_norm": 0.6469392129403697, + "learning_rate": 1.9785317572454303e-05, + "loss": 1.0601, + "step": 1533 + }, + { + "epoch": 0.09417109180760613, + "grad_norm": 0.6810756241515765, + "learning_rate": 1.978490758790023e-05, + "loss": 1.0318, + "step": 1534 + }, + { + "epoch": 0.09423248104607262, + "grad_norm": 0.6796258078854075, + "learning_rate": 1.978449721649643e-05, + "loss": 1.0378, + "step": 1535 + }, + { + "epoch": 0.09429387028453912, + "grad_norm": 0.6548539003688316, + "learning_rate": 1.9784086458259123e-05, + "loss": 1.0907, + "step": 1536 + }, + { + "epoch": 0.09435525952300562, + "grad_norm": 0.6075934309840347, + "learning_rate": 1.9783675313204547e-05, + "loss": 1.0301, + "step": 1537 + }, + { + "epoch": 0.09441664876147211, + "grad_norm": 0.6508368885783509, + "learning_rate": 1.978326378134896e-05, + "loss": 1.0466, + "step": 1538 + }, + { + "epoch": 0.0944780379999386, + "grad_norm": 0.7079168706070067, + "learning_rate": 1.9782851862708633e-05, + "loss": 1.1039, + "step": 1539 + }, + { + "epoch": 0.09453942723840511, + "grad_norm": 0.6845945634988676, + "learning_rate": 1.9782439557299848e-05, + "loss": 1.1167, + "step": 1540 + }, + { + "epoch": 0.0946008164768716, + "grad_norm": 0.6884690884564774, + "learning_rate": 1.978202686513891e-05, + "loss": 1.0759, + "step": 1541 + }, + { + "epoch": 0.09466220571533811, + "grad_norm": 0.641745978150224, + "learning_rate": 1.9781613786242127e-05, + "loss": 1.0574, + "step": 1542 + }, + { + "epoch": 0.0947235949538046, + "grad_norm": 0.6676144641029957, + "learning_rate": 1.9781200320625836e-05, + "loss": 1.1122, + "step": 1543 + }, + { + "epoch": 0.09478498419227109, + "grad_norm": 0.6221778766343938, + "learning_rate": 1.9780786468306387e-05, + "loss": 0.9822, + "step": 1544 + }, + { + "epoch": 0.0948463734307376, + "grad_norm": 0.6842586303727637, + "learning_rate": 1.9780372229300135e-05, + "loss": 1.1065, + "step": 1545 + }, + { + "epoch": 0.09490776266920409, + "grad_norm": 0.6912507552126315, + "learning_rate": 1.977995760362346e-05, + "loss": 1.0855, + "step": 1546 + }, + { + "epoch": 0.09496915190767058, + "grad_norm": 0.6331346274814276, + "learning_rate": 1.9779542591292753e-05, + "loss": 1.0804, + "step": 1547 + }, + { + "epoch": 0.09503054114613708, + "grad_norm": 0.6846571922423504, + "learning_rate": 1.9779127192324427e-05, + "loss": 1.1213, + "step": 1548 + }, + { + "epoch": 0.09509193038460358, + "grad_norm": 0.6706159608972311, + "learning_rate": 1.9778711406734895e-05, + "loss": 1.0557, + "step": 1549 + }, + { + "epoch": 0.09515331962307008, + "grad_norm": 0.6404591143648865, + "learning_rate": 1.97782952345406e-05, + "loss": 1.0499, + "step": 1550 + }, + { + "epoch": 0.09521470886153657, + "grad_norm": 0.6165578138769072, + "learning_rate": 1.9777878675758002e-05, + "loss": 1.0919, + "step": 1551 + }, + { + "epoch": 0.09527609810000306, + "grad_norm": 0.7198403692883087, + "learning_rate": 1.9777461730403563e-05, + "loss": 1.1072, + "step": 1552 + }, + { + "epoch": 0.09533748733846957, + "grad_norm": 0.6573468162567877, + "learning_rate": 1.9777044398493766e-05, + "loss": 1.0585, + "step": 1553 + }, + { + "epoch": 0.09539887657693606, + "grad_norm": 0.646744765214212, + "learning_rate": 1.9776626680045115e-05, + "loss": 1.0897, + "step": 1554 + }, + { + "epoch": 0.09546026581540255, + "grad_norm": 0.7243888699275286, + "learning_rate": 1.9776208575074118e-05, + "loss": 1.1459, + "step": 1555 + }, + { + "epoch": 0.09552165505386906, + "grad_norm": 0.6501189235955964, + "learning_rate": 1.9775790083597314e-05, + "loss": 1.0558, + "step": 1556 + }, + { + "epoch": 0.09558304429233555, + "grad_norm": 0.6932354430502092, + "learning_rate": 1.977537120563124e-05, + "loss": 1.1067, + "step": 1557 + }, + { + "epoch": 0.09564443353080206, + "grad_norm": 0.686718183634412, + "learning_rate": 1.9774951941192462e-05, + "loss": 1.1147, + "step": 1558 + }, + { + "epoch": 0.09570582276926855, + "grad_norm": 0.6073034918139839, + "learning_rate": 1.9774532290297554e-05, + "loss": 1.0492, + "step": 1559 + }, + { + "epoch": 0.09576721200773504, + "grad_norm": 0.7443362391103888, + "learning_rate": 1.9774112252963104e-05, + "loss": 1.0344, + "step": 1560 + }, + { + "epoch": 0.09582860124620154, + "grad_norm": 0.6842483348725422, + "learning_rate": 1.977369182920572e-05, + "loss": 1.079, + "step": 1561 + }, + { + "epoch": 0.09588999048466804, + "grad_norm": 0.6634081295489329, + "learning_rate": 1.977327101904203e-05, + "loss": 1.0968, + "step": 1562 + }, + { + "epoch": 0.09595137972313453, + "grad_norm": 0.6882259205946252, + "learning_rate": 1.9772849822488662e-05, + "loss": 1.0776, + "step": 1563 + }, + { + "epoch": 0.09601276896160103, + "grad_norm": 0.6786736349950286, + "learning_rate": 1.9772428239562273e-05, + "loss": 1.0629, + "step": 1564 + }, + { + "epoch": 0.09607415820006752, + "grad_norm": 0.7089258701638588, + "learning_rate": 1.9772006270279526e-05, + "loss": 1.119, + "step": 1565 + }, + { + "epoch": 0.09613554743853403, + "grad_norm": 0.6682224173627127, + "learning_rate": 1.9771583914657113e-05, + "loss": 1.0733, + "step": 1566 + }, + { + "epoch": 0.09619693667700052, + "grad_norm": 0.6554683112350379, + "learning_rate": 1.977116117271172e-05, + "loss": 1.0726, + "step": 1567 + }, + { + "epoch": 0.09625832591546701, + "grad_norm": 0.6603473010893419, + "learning_rate": 1.9770738044460066e-05, + "loss": 1.1205, + "step": 1568 + }, + { + "epoch": 0.09631971515393352, + "grad_norm": 0.617755819815162, + "learning_rate": 1.9770314529918883e-05, + "loss": 1.0625, + "step": 1569 + }, + { + "epoch": 0.09638110439240001, + "grad_norm": 0.7003340852853016, + "learning_rate": 1.976989062910491e-05, + "loss": 1.0677, + "step": 1570 + }, + { + "epoch": 0.09644249363086652, + "grad_norm": 0.6844989014988917, + "learning_rate": 1.9769466342034907e-05, + "loss": 1.0902, + "step": 1571 + }, + { + "epoch": 0.09650388286933301, + "grad_norm": 0.672133631781731, + "learning_rate": 1.976904166872565e-05, + "loss": 1.0563, + "step": 1572 + }, + { + "epoch": 0.0965652721077995, + "grad_norm": 0.628700828299184, + "learning_rate": 1.976861660919393e-05, + "loss": 1.031, + "step": 1573 + }, + { + "epoch": 0.096626661346266, + "grad_norm": 0.6707534016959084, + "learning_rate": 1.976819116345654e-05, + "loss": 1.0884, + "step": 1574 + }, + { + "epoch": 0.0966880505847325, + "grad_norm": 0.7277224296656359, + "learning_rate": 1.9767765331530317e-05, + "loss": 1.1157, + "step": 1575 + }, + { + "epoch": 0.09674943982319899, + "grad_norm": 0.656954685695334, + "learning_rate": 1.9767339113432084e-05, + "loss": 1.0359, + "step": 1576 + }, + { + "epoch": 0.0968108290616655, + "grad_norm": 0.6912320195413862, + "learning_rate": 1.97669125091787e-05, + "loss": 1.0527, + "step": 1577 + }, + { + "epoch": 0.09687221830013198, + "grad_norm": 0.6642481340438577, + "learning_rate": 1.976648551878703e-05, + "loss": 1.097, + "step": 1578 + }, + { + "epoch": 0.09693360753859849, + "grad_norm": 0.679636948541939, + "learning_rate": 1.9766058142273948e-05, + "loss": 1.1095, + "step": 1579 + }, + { + "epoch": 0.09699499677706498, + "grad_norm": 0.6653121344644807, + "learning_rate": 1.9765630379656353e-05, + "loss": 1.103, + "step": 1580 + }, + { + "epoch": 0.09705638601553147, + "grad_norm": 0.665806221528902, + "learning_rate": 1.976520223095116e-05, + "loss": 1.0414, + "step": 1581 + }, + { + "epoch": 0.09711777525399798, + "grad_norm": 0.6287254109908779, + "learning_rate": 1.9764773696175302e-05, + "loss": 0.7743, + "step": 1582 + }, + { + "epoch": 0.09717916449246447, + "grad_norm": 0.6732398993635443, + "learning_rate": 1.9764344775345706e-05, + "loss": 1.0955, + "step": 1583 + }, + { + "epoch": 0.09724055373093096, + "grad_norm": 0.6363346403157867, + "learning_rate": 1.976391546847934e-05, + "loss": 1.0477, + "step": 1584 + }, + { + "epoch": 0.09730194296939747, + "grad_norm": 0.6768918108188828, + "learning_rate": 1.9763485775593176e-05, + "loss": 1.1097, + "step": 1585 + }, + { + "epoch": 0.09736333220786396, + "grad_norm": 0.6576467482170497, + "learning_rate": 1.97630556967042e-05, + "loss": 1.0746, + "step": 1586 + }, + { + "epoch": 0.09742472144633046, + "grad_norm": 0.6324758282165331, + "learning_rate": 1.9762625231829412e-05, + "loss": 1.0375, + "step": 1587 + }, + { + "epoch": 0.09748611068479696, + "grad_norm": 0.6308554672667904, + "learning_rate": 1.976219438098584e-05, + "loss": 1.0472, + "step": 1588 + }, + { + "epoch": 0.09754749992326345, + "grad_norm": 0.6654040027344059, + "learning_rate": 1.976176314419051e-05, + "loss": 1.0786, + "step": 1589 + }, + { + "epoch": 0.09760888916172995, + "grad_norm": 0.6763435970268867, + "learning_rate": 1.9761331521460474e-05, + "loss": 1.16, + "step": 1590 + }, + { + "epoch": 0.09767027840019644, + "grad_norm": 0.7131439024902984, + "learning_rate": 1.9760899512812794e-05, + "loss": 1.085, + "step": 1591 + }, + { + "epoch": 0.09773166763866294, + "grad_norm": 0.6674014703881015, + "learning_rate": 1.9760467118264554e-05, + "loss": 1.0596, + "step": 1592 + }, + { + "epoch": 0.09779305687712944, + "grad_norm": 0.6475917412970098, + "learning_rate": 1.9760034337832844e-05, + "loss": 1.009, + "step": 1593 + }, + { + "epoch": 0.09785444611559593, + "grad_norm": 0.6672266968433707, + "learning_rate": 1.9759601171534776e-05, + "loss": 1.0905, + "step": 1594 + }, + { + "epoch": 0.09791583535406244, + "grad_norm": 0.7158093921701296, + "learning_rate": 1.9759167619387474e-05, + "loss": 1.1205, + "step": 1595 + }, + { + "epoch": 0.09797722459252893, + "grad_norm": 0.6328266397230381, + "learning_rate": 1.9758733681408083e-05, + "loss": 1.0705, + "step": 1596 + }, + { + "epoch": 0.09803861383099542, + "grad_norm": 0.6886281888052316, + "learning_rate": 1.9758299357613757e-05, + "loss": 1.1022, + "step": 1597 + }, + { + "epoch": 0.09810000306946193, + "grad_norm": 0.736330241228606, + "learning_rate": 1.9757864648021666e-05, + "loss": 1.1228, + "step": 1598 + }, + { + "epoch": 0.09816139230792842, + "grad_norm": 0.6553195374741685, + "learning_rate": 1.9757429552648995e-05, + "loss": 1.0841, + "step": 1599 + }, + { + "epoch": 0.09822278154639491, + "grad_norm": 0.6373930754911287, + "learning_rate": 1.9756994071512946e-05, + "loss": 1.0415, + "step": 1600 + }, + { + "epoch": 0.09828417078486142, + "grad_norm": 0.6932171634439412, + "learning_rate": 1.975655820463074e-05, + "loss": 1.0904, + "step": 1601 + }, + { + "epoch": 0.09834556002332791, + "grad_norm": 0.7194510761146138, + "learning_rate": 1.9756121952019608e-05, + "loss": 1.1196, + "step": 1602 + }, + { + "epoch": 0.09840694926179441, + "grad_norm": 0.6557840947593196, + "learning_rate": 1.9755685313696796e-05, + "loss": 1.0659, + "step": 1603 + }, + { + "epoch": 0.0984683385002609, + "grad_norm": 0.6536755180956519, + "learning_rate": 1.9755248289679564e-05, + "loss": 1.0579, + "step": 1604 + }, + { + "epoch": 0.0985297277387274, + "grad_norm": 0.6446284289666224, + "learning_rate": 1.9754810879985192e-05, + "loss": 1.0464, + "step": 1605 + }, + { + "epoch": 0.0985911169771939, + "grad_norm": 0.6867657958003978, + "learning_rate": 1.9754373084630973e-05, + "loss": 1.0206, + "step": 1606 + }, + { + "epoch": 0.0986525062156604, + "grad_norm": 0.7000685189154718, + "learning_rate": 1.9753934903634217e-05, + "loss": 1.1208, + "step": 1607 + }, + { + "epoch": 0.09871389545412688, + "grad_norm": 0.6108040293091603, + "learning_rate": 1.9753496337012247e-05, + "loss": 0.9642, + "step": 1608 + }, + { + "epoch": 0.09877528469259339, + "grad_norm": 0.6753599568903506, + "learning_rate": 1.97530573847824e-05, + "loss": 1.0392, + "step": 1609 + }, + { + "epoch": 0.09883667393105988, + "grad_norm": 0.7113390210441279, + "learning_rate": 1.9752618046962035e-05, + "loss": 1.1124, + "step": 1610 + }, + { + "epoch": 0.09889806316952639, + "grad_norm": 0.6824292144161844, + "learning_rate": 1.9752178323568514e-05, + "loss": 1.1009, + "step": 1611 + }, + { + "epoch": 0.09895945240799288, + "grad_norm": 0.6661109006915189, + "learning_rate": 1.9751738214619226e-05, + "loss": 1.0567, + "step": 1612 + }, + { + "epoch": 0.09902084164645937, + "grad_norm": 0.6356888600586702, + "learning_rate": 1.9751297720131572e-05, + "loss": 1.0449, + "step": 1613 + }, + { + "epoch": 0.09908223088492588, + "grad_norm": 0.6617268229289587, + "learning_rate": 1.9750856840122968e-05, + "loss": 1.0745, + "step": 1614 + }, + { + "epoch": 0.09914362012339237, + "grad_norm": 0.6560472058372806, + "learning_rate": 1.975041557461084e-05, + "loss": 1.0767, + "step": 1615 + }, + { + "epoch": 0.09920500936185887, + "grad_norm": 0.6588989283626459, + "learning_rate": 1.9749973923612632e-05, + "loss": 1.1047, + "step": 1616 + }, + { + "epoch": 0.09926639860032536, + "grad_norm": 0.6773125256963219, + "learning_rate": 1.974953188714581e-05, + "loss": 1.0444, + "step": 1617 + }, + { + "epoch": 0.09932778783879186, + "grad_norm": 0.6331024115383699, + "learning_rate": 1.974908946522785e-05, + "loss": 1.0131, + "step": 1618 + }, + { + "epoch": 0.09938917707725836, + "grad_norm": 0.6841344348672144, + "learning_rate": 1.974864665787624e-05, + "loss": 1.0468, + "step": 1619 + }, + { + "epoch": 0.09945056631572485, + "grad_norm": 0.6711995887428673, + "learning_rate": 1.9748203465108488e-05, + "loss": 1.037, + "step": 1620 + }, + { + "epoch": 0.09951195555419134, + "grad_norm": 0.6198261975194627, + "learning_rate": 1.9747759886942116e-05, + "loss": 0.7774, + "step": 1621 + }, + { + "epoch": 0.09957334479265785, + "grad_norm": 0.6428817291880489, + "learning_rate": 1.9747315923394662e-05, + "loss": 1.0273, + "step": 1622 + }, + { + "epoch": 0.09963473403112434, + "grad_norm": 0.6647128965194282, + "learning_rate": 1.9746871574483677e-05, + "loss": 1.0321, + "step": 1623 + }, + { + "epoch": 0.09969612326959085, + "grad_norm": 0.6455451998298153, + "learning_rate": 1.9746426840226728e-05, + "loss": 1.0086, + "step": 1624 + }, + { + "epoch": 0.09975751250805734, + "grad_norm": 0.7151931213299797, + "learning_rate": 1.97459817206414e-05, + "loss": 1.0601, + "step": 1625 + }, + { + "epoch": 0.09981890174652383, + "grad_norm": 0.6253995506963189, + "learning_rate": 1.974553621574529e-05, + "loss": 1.0147, + "step": 1626 + }, + { + "epoch": 0.09988029098499034, + "grad_norm": 0.6356217973836809, + "learning_rate": 1.974509032555601e-05, + "loss": 1.0396, + "step": 1627 + }, + { + "epoch": 0.09994168022345683, + "grad_norm": 0.712972175133839, + "learning_rate": 1.9744644050091185e-05, + "loss": 1.1472, + "step": 1628 + }, + { + "epoch": 0.10000306946192332, + "grad_norm": 0.6997509044907965, + "learning_rate": 1.9744197389368467e-05, + "loss": 1.083, + "step": 1629 + }, + { + "epoch": 0.10006445870038982, + "grad_norm": 0.6518335367132762, + "learning_rate": 1.974375034340551e-05, + "loss": 1.0542, + "step": 1630 + }, + { + "epoch": 0.10012584793885632, + "grad_norm": 0.6473429183442037, + "learning_rate": 1.974330291221999e-05, + "loss": 1.0682, + "step": 1631 + }, + { + "epoch": 0.10018723717732282, + "grad_norm": 0.6607272790622764, + "learning_rate": 1.974285509582959e-05, + "loss": 1.0506, + "step": 1632 + }, + { + "epoch": 0.10024862641578931, + "grad_norm": 0.6786654561909413, + "learning_rate": 1.9742406894252024e-05, + "loss": 1.0429, + "step": 1633 + }, + { + "epoch": 0.1003100156542558, + "grad_norm": 0.6564715112489035, + "learning_rate": 1.9741958307505005e-05, + "loss": 1.0513, + "step": 1634 + }, + { + "epoch": 0.10037140489272231, + "grad_norm": 0.6693884608373423, + "learning_rate": 1.9741509335606273e-05, + "loss": 1.1266, + "step": 1635 + }, + { + "epoch": 0.1004327941311888, + "grad_norm": 0.6593423658496848, + "learning_rate": 1.9741059978573577e-05, + "loss": 1.0692, + "step": 1636 + }, + { + "epoch": 0.1004941833696553, + "grad_norm": 0.6029247326145943, + "learning_rate": 1.9740610236424676e-05, + "loss": 1.0514, + "step": 1637 + }, + { + "epoch": 0.1005555726081218, + "grad_norm": 0.6962802023264703, + "learning_rate": 1.974016010917736e-05, + "loss": 1.0833, + "step": 1638 + }, + { + "epoch": 0.10061696184658829, + "grad_norm": 0.6364651794711859, + "learning_rate": 1.9739709596849418e-05, + "loss": 1.0616, + "step": 1639 + }, + { + "epoch": 0.1006783510850548, + "grad_norm": 0.6367462001100417, + "learning_rate": 1.9739258699458667e-05, + "loss": 1.0267, + "step": 1640 + }, + { + "epoch": 0.10073974032352129, + "grad_norm": 0.682080963639909, + "learning_rate": 1.9738807417022927e-05, + "loss": 1.0113, + "step": 1641 + }, + { + "epoch": 0.10080112956198778, + "grad_norm": 0.6633808618954428, + "learning_rate": 1.9738355749560046e-05, + "loss": 1.0911, + "step": 1642 + }, + { + "epoch": 0.10086251880045428, + "grad_norm": 0.6295727346581277, + "learning_rate": 1.9737903697087876e-05, + "loss": 1.087, + "step": 1643 + }, + { + "epoch": 0.10092390803892078, + "grad_norm": 0.6548512870545472, + "learning_rate": 1.973745125962429e-05, + "loss": 1.059, + "step": 1644 + }, + { + "epoch": 0.10098529727738727, + "grad_norm": 0.6813268536124771, + "learning_rate": 1.9736998437187178e-05, + "loss": 1.0774, + "step": 1645 + }, + { + "epoch": 0.10104668651585377, + "grad_norm": 0.6461746680100586, + "learning_rate": 1.973654522979444e-05, + "loss": 1.056, + "step": 1646 + }, + { + "epoch": 0.10110807575432026, + "grad_norm": 0.6986882786158967, + "learning_rate": 1.9736091637463993e-05, + "loss": 1.0868, + "step": 1647 + }, + { + "epoch": 0.10116946499278677, + "grad_norm": 0.7028349982782078, + "learning_rate": 1.9735637660213775e-05, + "loss": 1.0379, + "step": 1648 + }, + { + "epoch": 0.10123085423125326, + "grad_norm": 0.7150215475563348, + "learning_rate": 1.9735183298061726e-05, + "loss": 1.0745, + "step": 1649 + }, + { + "epoch": 0.10129224346971975, + "grad_norm": 0.6891418417089598, + "learning_rate": 1.9734728551025818e-05, + "loss": 1.085, + "step": 1650 + }, + { + "epoch": 0.10135363270818626, + "grad_norm": 0.6561320201003523, + "learning_rate": 1.9734273419124023e-05, + "loss": 1.033, + "step": 1651 + }, + { + "epoch": 0.10141502194665275, + "grad_norm": 0.666729669282836, + "learning_rate": 1.9733817902374337e-05, + "loss": 1.0521, + "step": 1652 + }, + { + "epoch": 0.10147641118511924, + "grad_norm": 0.6479406891640596, + "learning_rate": 1.973336200079477e-05, + "loss": 1.02, + "step": 1653 + }, + { + "epoch": 0.10153780042358575, + "grad_norm": 0.6620928246688776, + "learning_rate": 1.973290571440335e-05, + "loss": 1.0473, + "step": 1654 + }, + { + "epoch": 0.10159918966205224, + "grad_norm": 0.7135407306868937, + "learning_rate": 1.9732449043218103e-05, + "loss": 1.1027, + "step": 1655 + }, + { + "epoch": 0.10166057890051874, + "grad_norm": 0.7428856327190166, + "learning_rate": 1.97319919872571e-05, + "loss": 1.0884, + "step": 1656 + }, + { + "epoch": 0.10172196813898524, + "grad_norm": 0.616525864179647, + "learning_rate": 1.97315345465384e-05, + "loss": 0.9996, + "step": 1657 + }, + { + "epoch": 0.10178335737745173, + "grad_norm": 0.7079097351735893, + "learning_rate": 1.973107672108009e-05, + "loss": 1.0997, + "step": 1658 + }, + { + "epoch": 0.10184474661591823, + "grad_norm": 0.6273623130515025, + "learning_rate": 1.973061851090027e-05, + "loss": 1.0738, + "step": 1659 + }, + { + "epoch": 0.10190613585438472, + "grad_norm": 0.656344538856186, + "learning_rate": 1.9730159916017063e-05, + "loss": 1.0852, + "step": 1660 + }, + { + "epoch": 0.10196752509285123, + "grad_norm": 0.6764415188701378, + "learning_rate": 1.9729700936448593e-05, + "loss": 1.1164, + "step": 1661 + }, + { + "epoch": 0.10202891433131772, + "grad_norm": 0.6587147458795213, + "learning_rate": 1.9729241572213005e-05, + "loss": 1.0864, + "step": 1662 + }, + { + "epoch": 0.10209030356978421, + "grad_norm": 0.6916995262824025, + "learning_rate": 1.9728781823328464e-05, + "loss": 1.0826, + "step": 1663 + }, + { + "epoch": 0.10215169280825072, + "grad_norm": 0.6782485528558928, + "learning_rate": 1.9728321689813142e-05, + "loss": 1.0914, + "step": 1664 + }, + { + "epoch": 0.10221308204671721, + "grad_norm": 0.6453213830020318, + "learning_rate": 1.972786117168523e-05, + "loss": 1.0433, + "step": 1665 + }, + { + "epoch": 0.1022744712851837, + "grad_norm": 0.6482273014283798, + "learning_rate": 1.9727400268962943e-05, + "loss": 1.0706, + "step": 1666 + }, + { + "epoch": 0.10233586052365021, + "grad_norm": 0.6368757914001425, + "learning_rate": 1.9726938981664497e-05, + "loss": 1.0082, + "step": 1667 + }, + { + "epoch": 0.1023972497621167, + "grad_norm": 0.6346345416956836, + "learning_rate": 1.9726477309808127e-05, + "loss": 1.0273, + "step": 1668 + }, + { + "epoch": 0.1024586390005832, + "grad_norm": 0.6698116694330823, + "learning_rate": 1.972601525341209e-05, + "loss": 1.0528, + "step": 1669 + }, + { + "epoch": 0.1025200282390497, + "grad_norm": 0.6406916688997675, + "learning_rate": 1.9725552812494652e-05, + "loss": 1.002, + "step": 1670 + }, + { + "epoch": 0.10258141747751619, + "grad_norm": 0.6851728850052049, + "learning_rate": 1.9725089987074096e-05, + "loss": 1.0755, + "step": 1671 + }, + { + "epoch": 0.10264280671598269, + "grad_norm": 0.6759117234486005, + "learning_rate": 1.972462677716872e-05, + "loss": 1.09, + "step": 1672 + }, + { + "epoch": 0.10270419595444918, + "grad_norm": 0.7019320662593123, + "learning_rate": 1.972416318279683e-05, + "loss": 1.0947, + "step": 1673 + }, + { + "epoch": 0.10276558519291568, + "grad_norm": 0.6275464666938428, + "learning_rate": 1.9723699203976768e-05, + "loss": 1.0359, + "step": 1674 + }, + { + "epoch": 0.10282697443138218, + "grad_norm": 0.600422227188617, + "learning_rate": 1.972323484072687e-05, + "loss": 0.9899, + "step": 1675 + }, + { + "epoch": 0.10288836366984867, + "grad_norm": 0.6702035613609182, + "learning_rate": 1.972277009306549e-05, + "loss": 1.0852, + "step": 1676 + }, + { + "epoch": 0.10294975290831518, + "grad_norm": 0.711859909361396, + "learning_rate": 1.9722304961011012e-05, + "loss": 1.1315, + "step": 1677 + }, + { + "epoch": 0.10301114214678167, + "grad_norm": 0.5914663651278892, + "learning_rate": 1.972183944458182e-05, + "loss": 0.9642, + "step": 1678 + }, + { + "epoch": 0.10307253138524816, + "grad_norm": 0.5657931666465181, + "learning_rate": 1.9721373543796318e-05, + "loss": 0.9716, + "step": 1679 + }, + { + "epoch": 0.10313392062371467, + "grad_norm": 0.6277887733683116, + "learning_rate": 1.9720907258672924e-05, + "loss": 0.9961, + "step": 1680 + }, + { + "epoch": 0.10319530986218116, + "grad_norm": 0.7492813732289968, + "learning_rate": 1.9720440589230075e-05, + "loss": 1.1848, + "step": 1681 + }, + { + "epoch": 0.10325669910064765, + "grad_norm": 0.6450135534212371, + "learning_rate": 1.9719973535486227e-05, + "loss": 1.0459, + "step": 1682 + }, + { + "epoch": 0.10331808833911416, + "grad_norm": 0.5733240738936843, + "learning_rate": 1.9719506097459834e-05, + "loss": 0.7701, + "step": 1683 + }, + { + "epoch": 0.10337947757758065, + "grad_norm": 0.675935808942954, + "learning_rate": 1.971903827516938e-05, + "loss": 1.0722, + "step": 1684 + }, + { + "epoch": 0.10344086681604715, + "grad_norm": 0.6766369187459362, + "learning_rate": 1.9718570068633364e-05, + "loss": 1.0529, + "step": 1685 + }, + { + "epoch": 0.10350225605451364, + "grad_norm": 0.7022336678047414, + "learning_rate": 1.9718101477870296e-05, + "loss": 1.1623, + "step": 1686 + }, + { + "epoch": 0.10356364529298014, + "grad_norm": 0.6299226831160681, + "learning_rate": 1.9717632502898697e-05, + "loss": 1.0387, + "step": 1687 + }, + { + "epoch": 0.10362503453144664, + "grad_norm": 0.700728202140647, + "learning_rate": 1.9717163143737114e-05, + "loss": 1.1421, + "step": 1688 + }, + { + "epoch": 0.10368642376991313, + "grad_norm": 0.6906354812657411, + "learning_rate": 1.97166934004041e-05, + "loss": 1.0526, + "step": 1689 + }, + { + "epoch": 0.10374781300837962, + "grad_norm": 0.638666216576867, + "learning_rate": 1.9716223272918233e-05, + "loss": 1.0282, + "step": 1690 + }, + { + "epoch": 0.10380920224684613, + "grad_norm": 0.6935437246399043, + "learning_rate": 1.9715752761298086e-05, + "loss": 1.0723, + "step": 1691 + }, + { + "epoch": 0.10387059148531262, + "grad_norm": 0.6085801539009389, + "learning_rate": 1.9715281865562273e-05, + "loss": 1.0399, + "step": 1692 + }, + { + "epoch": 0.10393198072377913, + "grad_norm": 0.6794655285413895, + "learning_rate": 1.9714810585729406e-05, + "loss": 1.1322, + "step": 1693 + }, + { + "epoch": 0.10399336996224562, + "grad_norm": 0.7076188391772694, + "learning_rate": 1.9714338921818116e-05, + "loss": 1.0404, + "step": 1694 + }, + { + "epoch": 0.10405475920071211, + "grad_norm": 0.6376213263934019, + "learning_rate": 1.9713866873847057e-05, + "loss": 1.0679, + "step": 1695 + }, + { + "epoch": 0.10411614843917862, + "grad_norm": 0.6802062808390388, + "learning_rate": 1.9713394441834883e-05, + "loss": 1.0905, + "step": 1696 + }, + { + "epoch": 0.10417753767764511, + "grad_norm": 0.64913339994702, + "learning_rate": 1.9712921625800277e-05, + "loss": 1.1173, + "step": 1697 + }, + { + "epoch": 0.1042389269161116, + "grad_norm": 0.717981657575148, + "learning_rate": 1.971244842576193e-05, + "loss": 1.0679, + "step": 1698 + }, + { + "epoch": 0.1043003161545781, + "grad_norm": 0.6651598403639382, + "learning_rate": 1.9711974841738553e-05, + "loss": 1.0596, + "step": 1699 + }, + { + "epoch": 0.1043617053930446, + "grad_norm": 0.6995269513648533, + "learning_rate": 1.9711500873748867e-05, + "loss": 1.0508, + "step": 1700 + }, + { + "epoch": 0.1044230946315111, + "grad_norm": 0.6482110991903767, + "learning_rate": 1.971102652181161e-05, + "loss": 1.0565, + "step": 1701 + }, + { + "epoch": 0.10448448386997759, + "grad_norm": 0.6828834971252803, + "learning_rate": 1.9710551785945534e-05, + "loss": 1.0905, + "step": 1702 + }, + { + "epoch": 0.10454587310844408, + "grad_norm": 0.7300746262517918, + "learning_rate": 1.9710076666169414e-05, + "loss": 1.152, + "step": 1703 + }, + { + "epoch": 0.10460726234691059, + "grad_norm": 0.6885461369346965, + "learning_rate": 1.970960116250203e-05, + "loss": 1.0517, + "step": 1704 + }, + { + "epoch": 0.10466865158537708, + "grad_norm": 0.643464767262659, + "learning_rate": 1.9709125274962178e-05, + "loss": 0.989, + "step": 1705 + }, + { + "epoch": 0.10473004082384359, + "grad_norm": 0.6446912450216997, + "learning_rate": 1.970864900356868e-05, + "loss": 1.0063, + "step": 1706 + }, + { + "epoch": 0.10479143006231008, + "grad_norm": 0.6757538385812738, + "learning_rate": 1.9708172348340357e-05, + "loss": 1.0703, + "step": 1707 + }, + { + "epoch": 0.10485281930077657, + "grad_norm": 0.7128364396601229, + "learning_rate": 1.970769530929606e-05, + "loss": 1.0693, + "step": 1708 + }, + { + "epoch": 0.10491420853924308, + "grad_norm": 0.6987423792563889, + "learning_rate": 1.970721788645465e-05, + "loss": 1.038, + "step": 1709 + }, + { + "epoch": 0.10497559777770957, + "grad_norm": 0.6511067320963313, + "learning_rate": 1.9706740079834995e-05, + "loss": 1.0408, + "step": 1710 + }, + { + "epoch": 0.10503698701617606, + "grad_norm": 0.6961763517262471, + "learning_rate": 1.970626188945599e-05, + "loss": 1.1345, + "step": 1711 + }, + { + "epoch": 0.10509837625464256, + "grad_norm": 0.6914620567193636, + "learning_rate": 1.9705783315336543e-05, + "loss": 1.0976, + "step": 1712 + }, + { + "epoch": 0.10515976549310906, + "grad_norm": 0.6465658423158713, + "learning_rate": 1.9705304357495568e-05, + "loss": 1.0948, + "step": 1713 + }, + { + "epoch": 0.10522115473157556, + "grad_norm": 0.6474492333313288, + "learning_rate": 1.9704825015952005e-05, + "loss": 1.0459, + "step": 1714 + }, + { + "epoch": 0.10528254397004205, + "grad_norm": 0.7072484095115057, + "learning_rate": 1.9704345290724805e-05, + "loss": 1.1555, + "step": 1715 + }, + { + "epoch": 0.10534393320850854, + "grad_norm": 0.696794931787843, + "learning_rate": 1.9703865181832933e-05, + "loss": 1.0777, + "step": 1716 + }, + { + "epoch": 0.10540532244697505, + "grad_norm": 0.6612679114027739, + "learning_rate": 1.970338468929537e-05, + "loss": 1.0504, + "step": 1717 + }, + { + "epoch": 0.10546671168544154, + "grad_norm": 0.7081985032024267, + "learning_rate": 1.970290381313111e-05, + "loss": 1.076, + "step": 1718 + }, + { + "epoch": 0.10552810092390803, + "grad_norm": 0.6224720904939659, + "learning_rate": 1.9702422553359174e-05, + "loss": 1.0405, + "step": 1719 + }, + { + "epoch": 0.10558949016237454, + "grad_norm": 0.6612388177877045, + "learning_rate": 1.970194090999858e-05, + "loss": 1.0624, + "step": 1720 + }, + { + "epoch": 0.10565087940084103, + "grad_norm": 0.6702562034097995, + "learning_rate": 1.9701458883068368e-05, + "loss": 1.033, + "step": 1721 + }, + { + "epoch": 0.10571226863930754, + "grad_norm": 0.6376421959372578, + "learning_rate": 1.97009764725876e-05, + "loss": 1.0103, + "step": 1722 + }, + { + "epoch": 0.10577365787777403, + "grad_norm": 0.7603658696339795, + "learning_rate": 1.9700493678575353e-05, + "loss": 1.1383, + "step": 1723 + }, + { + "epoch": 0.10583504711624052, + "grad_norm": 0.6600233774536512, + "learning_rate": 1.9700010501050704e-05, + "loss": 1.0692, + "step": 1724 + }, + { + "epoch": 0.10589643635470702, + "grad_norm": 0.7083394591462101, + "learning_rate": 1.969952694003276e-05, + "loss": 1.0416, + "step": 1725 + }, + { + "epoch": 0.10595782559317352, + "grad_norm": 0.6762695457155594, + "learning_rate": 1.9699042995540646e-05, + "loss": 1.0889, + "step": 1726 + }, + { + "epoch": 0.10601921483164001, + "grad_norm": 0.6671837135016261, + "learning_rate": 1.9698558667593483e-05, + "loss": 1.0593, + "step": 1727 + }, + { + "epoch": 0.10608060407010651, + "grad_norm": 0.6357683482782477, + "learning_rate": 1.9698073956210422e-05, + "loss": 1.0413, + "step": 1728 + }, + { + "epoch": 0.106141993308573, + "grad_norm": 0.6642522503510306, + "learning_rate": 1.9697588861410633e-05, + "loss": 1.0357, + "step": 1729 + }, + { + "epoch": 0.10620338254703951, + "grad_norm": 0.6675219985712313, + "learning_rate": 1.969710338321329e-05, + "loss": 1.1268, + "step": 1730 + }, + { + "epoch": 0.106264771785506, + "grad_norm": 0.669268189227579, + "learning_rate": 1.9696617521637584e-05, + "loss": 1.096, + "step": 1731 + }, + { + "epoch": 0.10632616102397249, + "grad_norm": 0.6303261737365393, + "learning_rate": 1.9696131276702727e-05, + "loss": 1.0151, + "step": 1732 + }, + { + "epoch": 0.106387550262439, + "grad_norm": 0.5965309622460534, + "learning_rate": 1.969564464842794e-05, + "loss": 0.739, + "step": 1733 + }, + { + "epoch": 0.10644893950090549, + "grad_norm": 0.686452170270794, + "learning_rate": 1.9695157636832468e-05, + "loss": 1.0805, + "step": 1734 + }, + { + "epoch": 0.10651032873937198, + "grad_norm": 0.6782706747447941, + "learning_rate": 1.9694670241935562e-05, + "loss": 1.089, + "step": 1735 + }, + { + "epoch": 0.10657171797783849, + "grad_norm": 0.6779300746277583, + "learning_rate": 1.9694182463756488e-05, + "loss": 1.0566, + "step": 1736 + }, + { + "epoch": 0.10663310721630498, + "grad_norm": 0.7026931637992899, + "learning_rate": 1.9693694302314534e-05, + "loss": 1.0778, + "step": 1737 + }, + { + "epoch": 0.10669449645477148, + "grad_norm": 0.6578008746002926, + "learning_rate": 1.9693205757628996e-05, + "loss": 1.0392, + "step": 1738 + }, + { + "epoch": 0.10675588569323798, + "grad_norm": 0.6649720025650901, + "learning_rate": 1.9692716829719197e-05, + "loss": 1.1275, + "step": 1739 + }, + { + "epoch": 0.10681727493170447, + "grad_norm": 0.6060724670633018, + "learning_rate": 1.9692227518604458e-05, + "loss": 1.0489, + "step": 1740 + }, + { + "epoch": 0.10687866417017097, + "grad_norm": 0.6462211171217932, + "learning_rate": 1.9691737824304127e-05, + "loss": 1.0613, + "step": 1741 + }, + { + "epoch": 0.10694005340863746, + "grad_norm": 0.7066114153252122, + "learning_rate": 1.9691247746837563e-05, + "loss": 1.0469, + "step": 1742 + }, + { + "epoch": 0.10700144264710396, + "grad_norm": 0.6594533879548483, + "learning_rate": 1.9690757286224146e-05, + "loss": 1.06, + "step": 1743 + }, + { + "epoch": 0.10706283188557046, + "grad_norm": 0.6631551590043091, + "learning_rate": 1.9690266442483263e-05, + "loss": 1.0682, + "step": 1744 + }, + { + "epoch": 0.10712422112403695, + "grad_norm": 0.6642268854647024, + "learning_rate": 1.968977521563432e-05, + "loss": 1.0623, + "step": 1745 + }, + { + "epoch": 0.10718561036250346, + "grad_norm": 0.6657506574130256, + "learning_rate": 1.9689283605696738e-05, + "loss": 1.0544, + "step": 1746 + }, + { + "epoch": 0.10724699960096995, + "grad_norm": 0.686139496261423, + "learning_rate": 1.9688791612689955e-05, + "loss": 1.0918, + "step": 1747 + }, + { + "epoch": 0.10730838883943644, + "grad_norm": 0.6370920886566801, + "learning_rate": 1.968829923663342e-05, + "loss": 1.0644, + "step": 1748 + }, + { + "epoch": 0.10736977807790295, + "grad_norm": 0.6767385582747146, + "learning_rate": 1.96878064775466e-05, + "loss": 1.1245, + "step": 1749 + }, + { + "epoch": 0.10743116731636944, + "grad_norm": 0.6340742446535826, + "learning_rate": 1.9687313335448973e-05, + "loss": 1.0433, + "step": 1750 + }, + { + "epoch": 0.10749255655483594, + "grad_norm": 0.6535664105626725, + "learning_rate": 1.9686819810360037e-05, + "loss": 1.1159, + "step": 1751 + }, + { + "epoch": 0.10755394579330244, + "grad_norm": 0.6473793161897706, + "learning_rate": 1.968632590229931e-05, + "loss": 1.019, + "step": 1752 + }, + { + "epoch": 0.10761533503176893, + "grad_norm": 0.6358078351790285, + "learning_rate": 1.9685831611286312e-05, + "loss": 0.9997, + "step": 1753 + }, + { + "epoch": 0.10767672427023543, + "grad_norm": 0.6818871106559742, + "learning_rate": 1.9685336937340586e-05, + "loss": 1.0826, + "step": 1754 + }, + { + "epoch": 0.10773811350870192, + "grad_norm": 0.6368192532864603, + "learning_rate": 1.9684841880481693e-05, + "loss": 1.0278, + "step": 1755 + }, + { + "epoch": 0.10779950274716842, + "grad_norm": 0.6855783185359837, + "learning_rate": 1.96843464407292e-05, + "loss": 1.0943, + "step": 1756 + }, + { + "epoch": 0.10786089198563492, + "grad_norm": 0.6944482355660173, + "learning_rate": 1.9683850618102696e-05, + "loss": 1.0724, + "step": 1757 + }, + { + "epoch": 0.10792228122410141, + "grad_norm": 0.642221502618615, + "learning_rate": 1.9683354412621786e-05, + "loss": 1.0721, + "step": 1758 + }, + { + "epoch": 0.10798367046256792, + "grad_norm": 0.6874159887851347, + "learning_rate": 1.9682857824306084e-05, + "loss": 1.0861, + "step": 1759 + }, + { + "epoch": 0.10804505970103441, + "grad_norm": 0.6163073160685565, + "learning_rate": 1.9682360853175227e-05, + "loss": 0.9984, + "step": 1760 + }, + { + "epoch": 0.1081064489395009, + "grad_norm": 0.7585335084622852, + "learning_rate": 1.968186349924886e-05, + "loss": 1.1894, + "step": 1761 + }, + { + "epoch": 0.10816783817796741, + "grad_norm": 0.688187965856527, + "learning_rate": 1.9681365762546644e-05, + "loss": 1.1201, + "step": 1762 + }, + { + "epoch": 0.1082292274164339, + "grad_norm": 0.698933936546462, + "learning_rate": 1.968086764308826e-05, + "loss": 1.0695, + "step": 1763 + }, + { + "epoch": 0.10829061665490039, + "grad_norm": 0.7013935282312594, + "learning_rate": 1.9680369140893405e-05, + "loss": 1.0917, + "step": 1764 + }, + { + "epoch": 0.1083520058933669, + "grad_norm": 0.6618273818572179, + "learning_rate": 1.9679870255981782e-05, + "loss": 1.0739, + "step": 1765 + }, + { + "epoch": 0.10841339513183339, + "grad_norm": 0.6664353939449226, + "learning_rate": 1.9679370988373115e-05, + "loss": 1.0777, + "step": 1766 + }, + { + "epoch": 0.10847478437029989, + "grad_norm": 0.6604318102832281, + "learning_rate": 1.9678871338087146e-05, + "loss": 1.028, + "step": 1767 + }, + { + "epoch": 0.10853617360876638, + "grad_norm": 0.658495422968217, + "learning_rate": 1.9678371305143625e-05, + "loss": 1.0294, + "step": 1768 + }, + { + "epoch": 0.10859756284723288, + "grad_norm": 0.7026693819186146, + "learning_rate": 1.9677870889562324e-05, + "loss": 1.0722, + "step": 1769 + }, + { + "epoch": 0.10865895208569938, + "grad_norm": 0.6363796820661601, + "learning_rate": 1.9677370091363024e-05, + "loss": 1.0382, + "step": 1770 + }, + { + "epoch": 0.10872034132416587, + "grad_norm": 0.668557044453682, + "learning_rate": 1.9676868910565528e-05, + "loss": 1.0221, + "step": 1771 + }, + { + "epoch": 0.10878173056263236, + "grad_norm": 0.691550425357689, + "learning_rate": 1.9676367347189647e-05, + "loss": 1.0856, + "step": 1772 + }, + { + "epoch": 0.10884311980109887, + "grad_norm": 0.6727595134799047, + "learning_rate": 1.967586540125521e-05, + "loss": 1.0791, + "step": 1773 + }, + { + "epoch": 0.10890450903956536, + "grad_norm": 0.641654897434445, + "learning_rate": 1.967536307278207e-05, + "loss": 1.0435, + "step": 1774 + }, + { + "epoch": 0.10896589827803187, + "grad_norm": 0.5905662463002433, + "learning_rate": 1.9674860361790073e-05, + "loss": 1.0424, + "step": 1775 + }, + { + "epoch": 0.10902728751649836, + "grad_norm": 0.6352890211506577, + "learning_rate": 1.9674357268299104e-05, + "loss": 0.9871, + "step": 1776 + }, + { + "epoch": 0.10908867675496485, + "grad_norm": 0.6472539604494693, + "learning_rate": 1.967385379232905e-05, + "loss": 1.0727, + "step": 1777 + }, + { + "epoch": 0.10915006599343136, + "grad_norm": 0.666032163932595, + "learning_rate": 1.9673349933899816e-05, + "loss": 1.0453, + "step": 1778 + }, + { + "epoch": 0.10921145523189785, + "grad_norm": 0.6878948117376131, + "learning_rate": 1.9672845693031325e-05, + "loss": 1.1271, + "step": 1779 + }, + { + "epoch": 0.10927284447036434, + "grad_norm": 0.6298278871090712, + "learning_rate": 1.9672341069743507e-05, + "loss": 1.0693, + "step": 1780 + }, + { + "epoch": 0.10933423370883084, + "grad_norm": 0.6038787017677917, + "learning_rate": 1.9671836064056316e-05, + "loss": 1.03, + "step": 1781 + }, + { + "epoch": 0.10939562294729734, + "grad_norm": 0.6756074964617869, + "learning_rate": 1.9671330675989715e-05, + "loss": 1.0929, + "step": 1782 + }, + { + "epoch": 0.10945701218576384, + "grad_norm": 0.6229245729971308, + "learning_rate": 1.967082490556369e-05, + "loss": 1.0783, + "step": 1783 + }, + { + "epoch": 0.10951840142423033, + "grad_norm": 0.6723178254988791, + "learning_rate": 1.967031875279823e-05, + "loss": 1.1093, + "step": 1784 + }, + { + "epoch": 0.10957979066269682, + "grad_norm": 0.6756035175428252, + "learning_rate": 1.966981221771335e-05, + "loss": 1.0579, + "step": 1785 + }, + { + "epoch": 0.10964117990116333, + "grad_norm": 0.6384779543139931, + "learning_rate": 1.9669305300329076e-05, + "loss": 1.0666, + "step": 1786 + }, + { + "epoch": 0.10970256913962982, + "grad_norm": 0.6597088407446464, + "learning_rate": 1.9668798000665448e-05, + "loss": 1.0136, + "step": 1787 + }, + { + "epoch": 0.10976395837809631, + "grad_norm": 0.6754859878724604, + "learning_rate": 1.9668290318742525e-05, + "loss": 1.0856, + "step": 1788 + }, + { + "epoch": 0.10982534761656282, + "grad_norm": 0.6892055707272048, + "learning_rate": 1.9667782254580373e-05, + "loss": 1.1113, + "step": 1789 + }, + { + "epoch": 0.10988673685502931, + "grad_norm": 0.6304759138899089, + "learning_rate": 1.9667273808199082e-05, + "loss": 1.0373, + "step": 1790 + }, + { + "epoch": 0.10994812609349582, + "grad_norm": 0.6667498002611777, + "learning_rate": 1.9666764979618755e-05, + "loss": 1.0835, + "step": 1791 + }, + { + "epoch": 0.11000951533196231, + "grad_norm": 0.693294307750499, + "learning_rate": 1.9666255768859503e-05, + "loss": 1.1546, + "step": 1792 + }, + { + "epoch": 0.1100709045704288, + "grad_norm": 0.6326292360486804, + "learning_rate": 1.966574617594147e-05, + "loss": 0.9991, + "step": 1793 + }, + { + "epoch": 0.1101322938088953, + "grad_norm": 0.6148424421691002, + "learning_rate": 1.9665236200884785e-05, + "loss": 1.0585, + "step": 1794 + }, + { + "epoch": 0.1101936830473618, + "grad_norm": 0.6817851150038332, + "learning_rate": 1.9664725843709624e-05, + "loss": 1.0673, + "step": 1795 + }, + { + "epoch": 0.1102550722858283, + "grad_norm": 0.6348570658971768, + "learning_rate": 1.966421510443616e-05, + "loss": 1.0875, + "step": 1796 + }, + { + "epoch": 0.11031646152429479, + "grad_norm": 0.6437990543367612, + "learning_rate": 1.9663703983084583e-05, + "loss": 1.049, + "step": 1797 + }, + { + "epoch": 0.11037785076276128, + "grad_norm": 0.6214185493169452, + "learning_rate": 1.96631924796751e-05, + "loss": 1.0253, + "step": 1798 + }, + { + "epoch": 0.11043924000122779, + "grad_norm": 0.6844008206030429, + "learning_rate": 1.9662680594227944e-05, + "loss": 1.0683, + "step": 1799 + }, + { + "epoch": 0.11050062923969428, + "grad_norm": 0.7026452743136326, + "learning_rate": 1.966216832676334e-05, + "loss": 1.0862, + "step": 1800 + }, + { + "epoch": 0.11056201847816077, + "grad_norm": 0.6919241061545108, + "learning_rate": 1.9661655677301543e-05, + "loss": 1.122, + "step": 1801 + }, + { + "epoch": 0.11062340771662728, + "grad_norm": 0.683184822346084, + "learning_rate": 1.9661142645862824e-05, + "loss": 1.0706, + "step": 1802 + }, + { + "epoch": 0.11068479695509377, + "grad_norm": 0.6172596699720789, + "learning_rate": 1.9660629232467466e-05, + "loss": 1.0005, + "step": 1803 + }, + { + "epoch": 0.11074618619356028, + "grad_norm": 0.5785835800846093, + "learning_rate": 1.9660115437135767e-05, + "loss": 1.048, + "step": 1804 + }, + { + "epoch": 0.11080757543202677, + "grad_norm": 0.7271383298952434, + "learning_rate": 1.9659601259888038e-05, + "loss": 1.0806, + "step": 1805 + }, + { + "epoch": 0.11086896467049326, + "grad_norm": 0.6366909690056385, + "learning_rate": 1.965908670074461e-05, + "loss": 1.0738, + "step": 1806 + }, + { + "epoch": 0.11093035390895976, + "grad_norm": 0.6812801166799909, + "learning_rate": 1.9658571759725818e-05, + "loss": 1.1338, + "step": 1807 + }, + { + "epoch": 0.11099174314742626, + "grad_norm": 0.6313060024166406, + "learning_rate": 1.9658056436852032e-05, + "loss": 0.9844, + "step": 1808 + }, + { + "epoch": 0.11105313238589275, + "grad_norm": 0.6946147641919466, + "learning_rate": 1.965754073214362e-05, + "loss": 1.0995, + "step": 1809 + }, + { + "epoch": 0.11111452162435925, + "grad_norm": 0.6631366939623939, + "learning_rate": 1.9657024645620968e-05, + "loss": 1.1044, + "step": 1810 + }, + { + "epoch": 0.11117591086282574, + "grad_norm": 0.5882574571415858, + "learning_rate": 1.9656508177304483e-05, + "loss": 1.0207, + "step": 1811 + }, + { + "epoch": 0.11123730010129225, + "grad_norm": 0.6231802548592107, + "learning_rate": 1.9655991327214586e-05, + "loss": 1.089, + "step": 1812 + }, + { + "epoch": 0.11129868933975874, + "grad_norm": 0.6795467975301593, + "learning_rate": 1.9655474095371706e-05, + "loss": 1.0485, + "step": 1813 + }, + { + "epoch": 0.11136007857822523, + "grad_norm": 0.6983984721764349, + "learning_rate": 1.965495648179629e-05, + "loss": 1.096, + "step": 1814 + }, + { + "epoch": 0.11142146781669174, + "grad_norm": 0.7015177411946432, + "learning_rate": 1.965443848650881e-05, + "loss": 1.1064, + "step": 1815 + }, + { + "epoch": 0.11148285705515823, + "grad_norm": 0.6124609343674413, + "learning_rate": 1.9653920109529742e-05, + "loss": 1.0379, + "step": 1816 + }, + { + "epoch": 0.11154424629362472, + "grad_norm": 0.6761865364625159, + "learning_rate": 1.9653401350879577e-05, + "loss": 1.0972, + "step": 1817 + }, + { + "epoch": 0.11160563553209123, + "grad_norm": 0.6610955444334832, + "learning_rate": 1.965288221057883e-05, + "loss": 1.0199, + "step": 1818 + }, + { + "epoch": 0.11166702477055772, + "grad_norm": 0.6420795105715655, + "learning_rate": 1.9652362688648016e-05, + "loss": 1.048, + "step": 1819 + }, + { + "epoch": 0.11172841400902422, + "grad_norm": 0.6217321261448014, + "learning_rate": 1.9651842785107685e-05, + "loss": 1.0435, + "step": 1820 + }, + { + "epoch": 0.11178980324749072, + "grad_norm": 0.6561896213398608, + "learning_rate": 1.9651322499978388e-05, + "loss": 0.9867, + "step": 1821 + }, + { + "epoch": 0.11185119248595721, + "grad_norm": 0.6502986275699549, + "learning_rate": 1.965080183328069e-05, + "loss": 1.109, + "step": 1822 + }, + { + "epoch": 0.11191258172442371, + "grad_norm": 0.6409043687726348, + "learning_rate": 1.9650280785035183e-05, + "loss": 1.0292, + "step": 1823 + }, + { + "epoch": 0.1119739709628902, + "grad_norm": 0.6225248690261957, + "learning_rate": 1.9649759355262458e-05, + "loss": 1.0563, + "step": 1824 + }, + { + "epoch": 0.1120353602013567, + "grad_norm": 0.6129869322544521, + "learning_rate": 1.964923754398314e-05, + "loss": 1.0377, + "step": 1825 + }, + { + "epoch": 0.1120967494398232, + "grad_norm": 0.705586311775994, + "learning_rate": 1.9648715351217853e-05, + "loss": 1.119, + "step": 1826 + }, + { + "epoch": 0.11215813867828969, + "grad_norm": 0.6591038277241175, + "learning_rate": 1.9648192776987243e-05, + "loss": 1.0716, + "step": 1827 + }, + { + "epoch": 0.1122195279167562, + "grad_norm": 0.6099461316065341, + "learning_rate": 1.964766982131197e-05, + "loss": 1.0649, + "step": 1828 + }, + { + "epoch": 0.11228091715522269, + "grad_norm": 0.6847513132959621, + "learning_rate": 1.964714648421271e-05, + "loss": 1.0674, + "step": 1829 + }, + { + "epoch": 0.11234230639368918, + "grad_norm": 0.6398888541505877, + "learning_rate": 1.9646622765710154e-05, + "loss": 1.0462, + "step": 1830 + }, + { + "epoch": 0.11240369563215569, + "grad_norm": 0.6989046112028227, + "learning_rate": 1.9646098665825003e-05, + "loss": 1.0685, + "step": 1831 + }, + { + "epoch": 0.11246508487062218, + "grad_norm": 0.644711796630837, + "learning_rate": 1.9645574184577982e-05, + "loss": 1.0207, + "step": 1832 + }, + { + "epoch": 0.11252647410908867, + "grad_norm": 0.6697507041520833, + "learning_rate": 1.9645049321989827e-05, + "loss": 1.043, + "step": 1833 + }, + { + "epoch": 0.11258786334755518, + "grad_norm": 0.6266530324016685, + "learning_rate": 1.9644524078081286e-05, + "loss": 1.0394, + "step": 1834 + }, + { + "epoch": 0.11264925258602167, + "grad_norm": 0.6301982816381373, + "learning_rate": 1.9643998452873126e-05, + "loss": 1.0533, + "step": 1835 + }, + { + "epoch": 0.11271064182448817, + "grad_norm": 0.6351229667347279, + "learning_rate": 1.964347244638613e-05, + "loss": 1.0429, + "step": 1836 + }, + { + "epoch": 0.11277203106295466, + "grad_norm": 0.6235586506248213, + "learning_rate": 1.9642946058641087e-05, + "loss": 1.0369, + "step": 1837 + }, + { + "epoch": 0.11283342030142116, + "grad_norm": 0.6412850261972394, + "learning_rate": 1.9642419289658812e-05, + "loss": 1.038, + "step": 1838 + }, + { + "epoch": 0.11289480953988766, + "grad_norm": 0.6719031617663972, + "learning_rate": 1.9641892139460133e-05, + "loss": 1.0559, + "step": 1839 + }, + { + "epoch": 0.11295619877835415, + "grad_norm": 0.6997964902767628, + "learning_rate": 1.964136460806589e-05, + "loss": 1.1345, + "step": 1840 + }, + { + "epoch": 0.11301758801682066, + "grad_norm": 0.6350224556015239, + "learning_rate": 1.9640836695496935e-05, + "loss": 1.0374, + "step": 1841 + }, + { + "epoch": 0.11307897725528715, + "grad_norm": 0.6644135860634752, + "learning_rate": 1.9640308401774145e-05, + "loss": 1.0277, + "step": 1842 + }, + { + "epoch": 0.11314036649375364, + "grad_norm": 0.6552741562185086, + "learning_rate": 1.9639779726918404e-05, + "loss": 1.0734, + "step": 1843 + }, + { + "epoch": 0.11320175573222015, + "grad_norm": 0.6752517347768893, + "learning_rate": 1.9639250670950613e-05, + "loss": 1.1162, + "step": 1844 + }, + { + "epoch": 0.11326314497068664, + "grad_norm": 0.6154531126925279, + "learning_rate": 1.9638721233891692e-05, + "loss": 0.9978, + "step": 1845 + }, + { + "epoch": 0.11332453420915313, + "grad_norm": 0.6434982889688481, + "learning_rate": 1.963819141576256e-05, + "loss": 1.052, + "step": 1846 + }, + { + "epoch": 0.11338592344761964, + "grad_norm": 0.6830796137520401, + "learning_rate": 1.9637661216584183e-05, + "loss": 1.0305, + "step": 1847 + }, + { + "epoch": 0.11344731268608613, + "grad_norm": 0.6566807333796397, + "learning_rate": 1.9637130636377508e-05, + "loss": 1.1044, + "step": 1848 + }, + { + "epoch": 0.11350870192455263, + "grad_norm": 0.6747972544421063, + "learning_rate": 1.9636599675163516e-05, + "loss": 1.0438, + "step": 1849 + }, + { + "epoch": 0.11357009116301912, + "grad_norm": 0.7103059373109292, + "learning_rate": 1.9636068332963196e-05, + "loss": 1.105, + "step": 1850 + }, + { + "epoch": 0.11363148040148562, + "grad_norm": 0.6971684459415275, + "learning_rate": 1.9635536609797562e-05, + "loss": 1.0776, + "step": 1851 + }, + { + "epoch": 0.11369286963995212, + "grad_norm": 0.6389318239942683, + "learning_rate": 1.9635004505687626e-05, + "loss": 1.0603, + "step": 1852 + }, + { + "epoch": 0.11375425887841861, + "grad_norm": 0.6578788439848239, + "learning_rate": 1.9634472020654438e-05, + "loss": 1.0418, + "step": 1853 + }, + { + "epoch": 0.1138156481168851, + "grad_norm": 0.6047962315759039, + "learning_rate": 1.9633939154719037e-05, + "loss": 1.0214, + "step": 1854 + }, + { + "epoch": 0.11387703735535161, + "grad_norm": 0.7318527932629812, + "learning_rate": 1.9633405907902494e-05, + "loss": 1.1124, + "step": 1855 + }, + { + "epoch": 0.1139384265938181, + "grad_norm": 0.6626334472611035, + "learning_rate": 1.9632872280225895e-05, + "loss": 1.0468, + "step": 1856 + }, + { + "epoch": 0.1139998158322846, + "grad_norm": 0.639980669606725, + "learning_rate": 1.9632338271710333e-05, + "loss": 1.08, + "step": 1857 + }, + { + "epoch": 0.1140612050707511, + "grad_norm": 0.6683394781079426, + "learning_rate": 1.9631803882376924e-05, + "loss": 1.0756, + "step": 1858 + }, + { + "epoch": 0.11412259430921759, + "grad_norm": 0.5998176586799651, + "learning_rate": 1.9631269112246795e-05, + "loss": 0.9965, + "step": 1859 + }, + { + "epoch": 0.1141839835476841, + "grad_norm": 0.5984420520866669, + "learning_rate": 1.963073396134108e-05, + "loss": 0.9913, + "step": 1860 + }, + { + "epoch": 0.11424537278615059, + "grad_norm": 0.6657031174219831, + "learning_rate": 1.9630198429680947e-05, + "loss": 1.0572, + "step": 1861 + }, + { + "epoch": 0.11430676202461708, + "grad_norm": 0.6675143788647575, + "learning_rate": 1.9629662517287563e-05, + "loss": 1.0643, + "step": 1862 + }, + { + "epoch": 0.11436815126308358, + "grad_norm": 0.6371651549446888, + "learning_rate": 1.9629126224182116e-05, + "loss": 1.0661, + "step": 1863 + }, + { + "epoch": 0.11442954050155008, + "grad_norm": 0.7360620523207374, + "learning_rate": 1.962858955038581e-05, + "loss": 1.1347, + "step": 1864 + }, + { + "epoch": 0.11449092974001658, + "grad_norm": 0.7083669694296537, + "learning_rate": 1.9628052495919862e-05, + "loss": 1.1154, + "step": 1865 + }, + { + "epoch": 0.11455231897848307, + "grad_norm": 0.694137420573908, + "learning_rate": 1.9627515060805503e-05, + "loss": 1.0923, + "step": 1866 + }, + { + "epoch": 0.11461370821694956, + "grad_norm": 0.6668717923745492, + "learning_rate": 1.9626977245063983e-05, + "loss": 1.0536, + "step": 1867 + }, + { + "epoch": 0.11467509745541607, + "grad_norm": 0.6686677389610787, + "learning_rate": 1.9626439048716564e-05, + "loss": 1.0541, + "step": 1868 + }, + { + "epoch": 0.11473648669388256, + "grad_norm": 0.6429315215914408, + "learning_rate": 1.9625900471784525e-05, + "loss": 1.0601, + "step": 1869 + }, + { + "epoch": 0.11479787593234905, + "grad_norm": 0.683595942941552, + "learning_rate": 1.9625361514289153e-05, + "loss": 1.0468, + "step": 1870 + }, + { + "epoch": 0.11485926517081556, + "grad_norm": 0.6969961107854227, + "learning_rate": 1.9624822176251763e-05, + "loss": 1.0755, + "step": 1871 + }, + { + "epoch": 0.11492065440928205, + "grad_norm": 0.6138981251123783, + "learning_rate": 1.962428245769368e-05, + "loss": 1.0093, + "step": 1872 + }, + { + "epoch": 0.11498204364774856, + "grad_norm": 0.6261285447164688, + "learning_rate": 1.962374235863623e-05, + "loss": 1.0508, + "step": 1873 + }, + { + "epoch": 0.11504343288621505, + "grad_norm": 0.6398888223358671, + "learning_rate": 1.9623201879100776e-05, + "loss": 1.0883, + "step": 1874 + }, + { + "epoch": 0.11510482212468154, + "grad_norm": 0.6474518796570424, + "learning_rate": 1.962266101910868e-05, + "loss": 1.0569, + "step": 1875 + }, + { + "epoch": 0.11516621136314804, + "grad_norm": 0.6720248129126767, + "learning_rate": 1.962211977868133e-05, + "loss": 1.0859, + "step": 1876 + }, + { + "epoch": 0.11522760060161454, + "grad_norm": 0.6453806492883474, + "learning_rate": 1.9621578157840126e-05, + "loss": 1.0739, + "step": 1877 + }, + { + "epoch": 0.11528898984008103, + "grad_norm": 0.6301708176044991, + "learning_rate": 1.9621036156606474e-05, + "loss": 1.0528, + "step": 1878 + }, + { + "epoch": 0.11535037907854753, + "grad_norm": 0.64504863960437, + "learning_rate": 1.962049377500181e-05, + "loss": 1.077, + "step": 1879 + }, + { + "epoch": 0.11541176831701402, + "grad_norm": 0.6197632953786444, + "learning_rate": 1.9619951013047568e-05, + "loss": 1.0458, + "step": 1880 + }, + { + "epoch": 0.11547315755548053, + "grad_norm": 0.5749405257272451, + "learning_rate": 1.9619407870765214e-05, + "loss": 0.8151, + "step": 1881 + }, + { + "epoch": 0.11553454679394702, + "grad_norm": 0.662529171028436, + "learning_rate": 1.9618864348176218e-05, + "loss": 1.0845, + "step": 1882 + }, + { + "epoch": 0.11559593603241351, + "grad_norm": 0.6607093758507789, + "learning_rate": 1.961832044530207e-05, + "loss": 1.1281, + "step": 1883 + }, + { + "epoch": 0.11565732527088002, + "grad_norm": 0.6838715347701932, + "learning_rate": 1.961777616216427e-05, + "loss": 1.0812, + "step": 1884 + }, + { + "epoch": 0.11571871450934651, + "grad_norm": 0.6903969572752241, + "learning_rate": 1.961723149878434e-05, + "loss": 1.0472, + "step": 1885 + }, + { + "epoch": 0.11578010374781302, + "grad_norm": 0.6089097594902004, + "learning_rate": 1.9616686455183817e-05, + "loss": 0.9886, + "step": 1886 + }, + { + "epoch": 0.1158414929862795, + "grad_norm": 0.6674606827272447, + "learning_rate": 1.9616141031384237e-05, + "loss": 1.0905, + "step": 1887 + }, + { + "epoch": 0.115902882224746, + "grad_norm": 0.5823229334008551, + "learning_rate": 1.9615595227407176e-05, + "loss": 1.0213, + "step": 1888 + }, + { + "epoch": 0.1159642714632125, + "grad_norm": 0.6526243482158463, + "learning_rate": 1.9615049043274207e-05, + "loss": 1.0602, + "step": 1889 + }, + { + "epoch": 0.116025660701679, + "grad_norm": 0.6508300635610895, + "learning_rate": 1.9614502479006922e-05, + "loss": 1.0744, + "step": 1890 + }, + { + "epoch": 0.11608704994014549, + "grad_norm": 0.6748546412206035, + "learning_rate": 1.9613955534626938e-05, + "loss": 1.0877, + "step": 1891 + }, + { + "epoch": 0.11614843917861199, + "grad_norm": 0.639859717752849, + "learning_rate": 1.9613408210155867e-05, + "loss": 1.0685, + "step": 1892 + }, + { + "epoch": 0.11620982841707848, + "grad_norm": 0.6183443043836783, + "learning_rate": 1.9612860505615356e-05, + "loss": 0.9993, + "step": 1893 + }, + { + "epoch": 0.11627121765554499, + "grad_norm": 0.6966367944240418, + "learning_rate": 1.9612312421027052e-05, + "loss": 1.0264, + "step": 1894 + }, + { + "epoch": 0.11633260689401148, + "grad_norm": 0.6326611190316397, + "learning_rate": 1.9611763956412632e-05, + "loss": 1.0369, + "step": 1895 + }, + { + "epoch": 0.11639399613247797, + "grad_norm": 0.6826096556574496, + "learning_rate": 1.9611215111793774e-05, + "loss": 1.0179, + "step": 1896 + }, + { + "epoch": 0.11645538537094448, + "grad_norm": 0.6277136152753776, + "learning_rate": 1.9610665887192178e-05, + "loss": 1.1019, + "step": 1897 + }, + { + "epoch": 0.11651677460941097, + "grad_norm": 0.6201019854835564, + "learning_rate": 1.961011628262956e-05, + "loss": 1.01, + "step": 1898 + }, + { + "epoch": 0.11657816384787746, + "grad_norm": 0.6231591698392173, + "learning_rate": 1.9609566298127645e-05, + "loss": 1.0361, + "step": 1899 + }, + { + "epoch": 0.11663955308634397, + "grad_norm": 0.6241497477499282, + "learning_rate": 1.9609015933708178e-05, + "loss": 1.0156, + "step": 1900 + }, + { + "epoch": 0.11670094232481046, + "grad_norm": 0.704629456906848, + "learning_rate": 1.960846518939292e-05, + "loss": 1.0714, + "step": 1901 + }, + { + "epoch": 0.11676233156327696, + "grad_norm": 0.6189047313469099, + "learning_rate": 1.960791406520364e-05, + "loss": 1.0231, + "step": 1902 + }, + { + "epoch": 0.11682372080174346, + "grad_norm": 0.6719266580335608, + "learning_rate": 1.9607362561162137e-05, + "loss": 1.0551, + "step": 1903 + }, + { + "epoch": 0.11688511004020995, + "grad_norm": 0.6713054112837376, + "learning_rate": 1.9606810677290205e-05, + "loss": 1.0938, + "step": 1904 + }, + { + "epoch": 0.11694649927867645, + "grad_norm": 0.6469533527501932, + "learning_rate": 1.9606258413609662e-05, + "loss": 1.0726, + "step": 1905 + }, + { + "epoch": 0.11700788851714294, + "grad_norm": 0.6757817566892824, + "learning_rate": 1.960570577014235e-05, + "loss": 1.0321, + "step": 1906 + }, + { + "epoch": 0.11706927775560944, + "grad_norm": 0.7394437492979102, + "learning_rate": 1.9605152746910114e-05, + "loss": 1.108, + "step": 1907 + }, + { + "epoch": 0.11713066699407594, + "grad_norm": 0.6695063275779202, + "learning_rate": 1.9604599343934817e-05, + "loss": 1.0903, + "step": 1908 + }, + { + "epoch": 0.11719205623254243, + "grad_norm": 0.613012955135097, + "learning_rate": 1.960404556123834e-05, + "loss": 1.0357, + "step": 1909 + }, + { + "epoch": 0.11725344547100894, + "grad_norm": 0.6745600383598245, + "learning_rate": 1.9603491398842575e-05, + "loss": 1.0958, + "step": 1910 + }, + { + "epoch": 0.11731483470947543, + "grad_norm": 0.6259422211711424, + "learning_rate": 1.9602936856769432e-05, + "loss": 1.0376, + "step": 1911 + }, + { + "epoch": 0.11737622394794192, + "grad_norm": 0.6355628219558473, + "learning_rate": 1.9602381935040835e-05, + "loss": 1.0533, + "step": 1912 + }, + { + "epoch": 0.11743761318640843, + "grad_norm": 0.6194979089958219, + "learning_rate": 1.9601826633678725e-05, + "loss": 1.0168, + "step": 1913 + }, + { + "epoch": 0.11749900242487492, + "grad_norm": 0.6698115888105222, + "learning_rate": 1.960127095270505e-05, + "loss": 1.0035, + "step": 1914 + }, + { + "epoch": 0.11756039166334141, + "grad_norm": 0.656744089968906, + "learning_rate": 1.9600714892141787e-05, + "loss": 1.095, + "step": 1915 + }, + { + "epoch": 0.11762178090180792, + "grad_norm": 0.678794372811007, + "learning_rate": 1.9600158452010914e-05, + "loss": 1.064, + "step": 1916 + }, + { + "epoch": 0.1176831701402744, + "grad_norm": 0.6704908863767824, + "learning_rate": 1.959960163233443e-05, + "loss": 1.0828, + "step": 1917 + }, + { + "epoch": 0.11774455937874091, + "grad_norm": 0.6583022816582024, + "learning_rate": 1.9599044433134353e-05, + "loss": 1.0833, + "step": 1918 + }, + { + "epoch": 0.1178059486172074, + "grad_norm": 0.6644485217222019, + "learning_rate": 1.9598486854432712e-05, + "loss": 1.0786, + "step": 1919 + }, + { + "epoch": 0.1178673378556739, + "grad_norm": 0.6182453263963419, + "learning_rate": 1.959792889625155e-05, + "loss": 1.0496, + "step": 1920 + }, + { + "epoch": 0.1179287270941404, + "grad_norm": 0.7437755573315429, + "learning_rate": 1.9597370558612924e-05, + "loss": 1.1082, + "step": 1921 + }, + { + "epoch": 0.11799011633260689, + "grad_norm": 0.6708388604413922, + "learning_rate": 1.9596811841538907e-05, + "loss": 1.0634, + "step": 1922 + }, + { + "epoch": 0.11805150557107338, + "grad_norm": 0.6375260171024288, + "learning_rate": 1.9596252745051593e-05, + "loss": 1.0609, + "step": 1923 + }, + { + "epoch": 0.11811289480953989, + "grad_norm": 0.6282377546295369, + "learning_rate": 1.959569326917308e-05, + "loss": 1.025, + "step": 1924 + }, + { + "epoch": 0.11817428404800638, + "grad_norm": 0.6429294670642507, + "learning_rate": 1.9595133413925494e-05, + "loss": 1.0882, + "step": 1925 + }, + { + "epoch": 0.11823567328647289, + "grad_norm": 0.6197450954315249, + "learning_rate": 1.959457317933097e-05, + "loss": 1.029, + "step": 1926 + }, + { + "epoch": 0.11829706252493938, + "grad_norm": 0.6495793961421903, + "learning_rate": 1.9594012565411645e-05, + "loss": 1.0243, + "step": 1927 + }, + { + "epoch": 0.11835845176340587, + "grad_norm": 0.6849657071621369, + "learning_rate": 1.9593451572189696e-05, + "loss": 1.085, + "step": 1928 + }, + { + "epoch": 0.11841984100187238, + "grad_norm": 0.6811841430707201, + "learning_rate": 1.9592890199687295e-05, + "loss": 1.063, + "step": 1929 + }, + { + "epoch": 0.11848123024033887, + "grad_norm": 0.634660383097605, + "learning_rate": 1.9592328447926637e-05, + "loss": 1.1234, + "step": 1930 + }, + { + "epoch": 0.11854261947880537, + "grad_norm": 0.6513379199282409, + "learning_rate": 1.9591766316929935e-05, + "loss": 0.8425, + "step": 1931 + }, + { + "epoch": 0.11860400871727186, + "grad_norm": 0.6547364737351696, + "learning_rate": 1.9591203806719408e-05, + "loss": 0.985, + "step": 1932 + }, + { + "epoch": 0.11866539795573836, + "grad_norm": 0.6264008122094146, + "learning_rate": 1.9590640917317296e-05, + "loss": 1.0235, + "step": 1933 + }, + { + "epoch": 0.11872678719420486, + "grad_norm": 0.651759404718605, + "learning_rate": 1.959007764874586e-05, + "loss": 1.0268, + "step": 1934 + }, + { + "epoch": 0.11878817643267135, + "grad_norm": 0.686679563882004, + "learning_rate": 1.9589514001027357e-05, + "loss": 1.1151, + "step": 1935 + }, + { + "epoch": 0.11884956567113784, + "grad_norm": 0.6166043845977632, + "learning_rate": 1.958894997418408e-05, + "loss": 1.0059, + "step": 1936 + }, + { + "epoch": 0.11891095490960435, + "grad_norm": 0.6565504905803514, + "learning_rate": 1.9588385568238323e-05, + "loss": 1.081, + "step": 1937 + }, + { + "epoch": 0.11897234414807084, + "grad_norm": 0.6871258681045519, + "learning_rate": 1.9587820783212403e-05, + "loss": 1.1034, + "step": 1938 + }, + { + "epoch": 0.11903373338653735, + "grad_norm": 0.6299017470014698, + "learning_rate": 1.9587255619128648e-05, + "loss": 1.0609, + "step": 1939 + }, + { + "epoch": 0.11909512262500384, + "grad_norm": 0.6247299255884637, + "learning_rate": 1.9586690076009405e-05, + "loss": 1.0001, + "step": 1940 + }, + { + "epoch": 0.11915651186347033, + "grad_norm": 0.6707735302319325, + "learning_rate": 1.9586124153877027e-05, + "loss": 1.0769, + "step": 1941 + }, + { + "epoch": 0.11921790110193684, + "grad_norm": 0.6670676867666356, + "learning_rate": 1.9585557852753893e-05, + "loss": 1.1017, + "step": 1942 + }, + { + "epoch": 0.11927929034040333, + "grad_norm": 0.5651814688922324, + "learning_rate": 1.958499117266239e-05, + "loss": 1.0181, + "step": 1943 + }, + { + "epoch": 0.11934067957886982, + "grad_norm": 0.6690584372927738, + "learning_rate": 1.958442411362492e-05, + "loss": 1.0646, + "step": 1944 + }, + { + "epoch": 0.11940206881733632, + "grad_norm": 0.6704014643051305, + "learning_rate": 1.9583856675663905e-05, + "loss": 1.1046, + "step": 1945 + }, + { + "epoch": 0.11946345805580282, + "grad_norm": 0.6720291100324671, + "learning_rate": 1.9583288858801775e-05, + "loss": 1.1193, + "step": 1946 + }, + { + "epoch": 0.11952484729426932, + "grad_norm": 0.6464446102602475, + "learning_rate": 1.9582720663060982e-05, + "loss": 1.0386, + "step": 1947 + }, + { + "epoch": 0.11958623653273581, + "grad_norm": 0.6750450715454116, + "learning_rate": 1.958215208846399e-05, + "loss": 1.0457, + "step": 1948 + }, + { + "epoch": 0.1196476257712023, + "grad_norm": 0.6207605052624571, + "learning_rate": 1.958158313503328e-05, + "loss": 1.0496, + "step": 1949 + }, + { + "epoch": 0.11970901500966881, + "grad_norm": 0.6447568030765828, + "learning_rate": 1.958101380279134e-05, + "loss": 1.0442, + "step": 1950 + }, + { + "epoch": 0.1197704042481353, + "grad_norm": 0.7164163550376458, + "learning_rate": 1.9580444091760682e-05, + "loss": 1.1256, + "step": 1951 + }, + { + "epoch": 0.11983179348660179, + "grad_norm": 0.624157795495926, + "learning_rate": 1.957987400196383e-05, + "loss": 0.9944, + "step": 1952 + }, + { + "epoch": 0.1198931827250683, + "grad_norm": 0.6497503980853285, + "learning_rate": 1.957930353342332e-05, + "loss": 1.0408, + "step": 1953 + }, + { + "epoch": 0.11995457196353479, + "grad_norm": 0.6395621684037343, + "learning_rate": 1.957873268616171e-05, + "loss": 1.0285, + "step": 1954 + }, + { + "epoch": 0.1200159612020013, + "grad_norm": 0.6760937405167025, + "learning_rate": 1.9578161460201564e-05, + "loss": 1.0698, + "step": 1955 + }, + { + "epoch": 0.12007735044046779, + "grad_norm": 0.6838104163080541, + "learning_rate": 1.957758985556547e-05, + "loss": 1.0863, + "step": 1956 + }, + { + "epoch": 0.12013873967893428, + "grad_norm": 0.6827405881679873, + "learning_rate": 1.9577017872276022e-05, + "loss": 1.0749, + "step": 1957 + }, + { + "epoch": 0.12020012891740078, + "grad_norm": 0.6494088437719625, + "learning_rate": 1.9576445510355837e-05, + "loss": 1.0626, + "step": 1958 + }, + { + "epoch": 0.12026151815586728, + "grad_norm": 0.6619638225395111, + "learning_rate": 1.957587276982754e-05, + "loss": 1.0763, + "step": 1959 + }, + { + "epoch": 0.12032290739433377, + "grad_norm": 0.6537232645368045, + "learning_rate": 1.9575299650713783e-05, + "loss": 1.0004, + "step": 1960 + }, + { + "epoch": 0.12038429663280027, + "grad_norm": 0.6922241057773088, + "learning_rate": 1.9574726153037216e-05, + "loss": 1.0683, + "step": 1961 + }, + { + "epoch": 0.12044568587126676, + "grad_norm": 0.6542008738108696, + "learning_rate": 1.9574152276820513e-05, + "loss": 1.0032, + "step": 1962 + }, + { + "epoch": 0.12050707510973327, + "grad_norm": 0.6618792507849897, + "learning_rate": 1.9573578022086365e-05, + "loss": 1.0501, + "step": 1963 + }, + { + "epoch": 0.12056846434819976, + "grad_norm": 0.6487700013615715, + "learning_rate": 1.9573003388857476e-05, + "loss": 0.75, + "step": 1964 + }, + { + "epoch": 0.12062985358666625, + "grad_norm": 0.623069855868633, + "learning_rate": 1.957242837715656e-05, + "loss": 1.0342, + "step": 1965 + }, + { + "epoch": 0.12069124282513276, + "grad_norm": 0.6223324344220776, + "learning_rate": 1.9571852987006358e-05, + "loss": 0.9922, + "step": 1966 + }, + { + "epoch": 0.12075263206359925, + "grad_norm": 0.6841867851983701, + "learning_rate": 1.957127721842961e-05, + "loss": 1.1076, + "step": 1967 + }, + { + "epoch": 0.12081402130206574, + "grad_norm": 0.6185108811805364, + "learning_rate": 1.9570701071449084e-05, + "loss": 1.0416, + "step": 1968 + }, + { + "epoch": 0.12087541054053225, + "grad_norm": 0.6399707221812938, + "learning_rate": 1.9570124546087555e-05, + "loss": 1.006, + "step": 1969 + }, + { + "epoch": 0.12093679977899874, + "grad_norm": 0.6849631850477909, + "learning_rate": 1.956954764236782e-05, + "loss": 1.0715, + "step": 1970 + }, + { + "epoch": 0.12099818901746524, + "grad_norm": 0.6868612837625426, + "learning_rate": 1.9568970360312688e-05, + "loss": 1.0822, + "step": 1971 + }, + { + "epoch": 0.12105957825593174, + "grad_norm": 0.679246033707021, + "learning_rate": 1.9568392699944977e-05, + "loss": 1.0677, + "step": 1972 + }, + { + "epoch": 0.12112096749439823, + "grad_norm": 0.6453634967973472, + "learning_rate": 1.9567814661287527e-05, + "loss": 1.0493, + "step": 1973 + }, + { + "epoch": 0.12118235673286473, + "grad_norm": 0.6509959402101978, + "learning_rate": 1.9567236244363188e-05, + "loss": 1.0506, + "step": 1974 + }, + { + "epoch": 0.12124374597133122, + "grad_norm": 0.6289458739233429, + "learning_rate": 1.9566657449194832e-05, + "loss": 1.0187, + "step": 1975 + }, + { + "epoch": 0.12130513520979773, + "grad_norm": 0.6692122657689065, + "learning_rate": 1.9566078275805344e-05, + "loss": 1.0698, + "step": 1976 + }, + { + "epoch": 0.12136652444826422, + "grad_norm": 0.7018075879715904, + "learning_rate": 1.9565498724217617e-05, + "loss": 1.0339, + "step": 1977 + }, + { + "epoch": 0.12142791368673071, + "grad_norm": 0.7217670201634833, + "learning_rate": 1.956491879445457e-05, + "loss": 1.0459, + "step": 1978 + }, + { + "epoch": 0.12148930292519722, + "grad_norm": 0.6340143881342591, + "learning_rate": 1.956433848653912e-05, + "loss": 1.0368, + "step": 1979 + }, + { + "epoch": 0.12155069216366371, + "grad_norm": 0.6664819116255364, + "learning_rate": 1.9563757800494216e-05, + "loss": 1.023, + "step": 1980 + }, + { + "epoch": 0.1216120814021302, + "grad_norm": 0.6647722609512741, + "learning_rate": 1.956317673634282e-05, + "loss": 1.0189, + "step": 1981 + }, + { + "epoch": 0.1216734706405967, + "grad_norm": 0.64764642165414, + "learning_rate": 1.95625952941079e-05, + "loss": 1.0524, + "step": 1982 + }, + { + "epoch": 0.1217348598790632, + "grad_norm": 0.7027013264316109, + "learning_rate": 1.956201347381244e-05, + "loss": 1.0642, + "step": 1983 + }, + { + "epoch": 0.1217962491175297, + "grad_norm": 0.7009708737900316, + "learning_rate": 1.9561431275479448e-05, + "loss": 1.0627, + "step": 1984 + }, + { + "epoch": 0.1218576383559962, + "grad_norm": 0.6920309450968118, + "learning_rate": 1.9560848699131937e-05, + "loss": 1.0667, + "step": 1985 + }, + { + "epoch": 0.12191902759446269, + "grad_norm": 0.6584963387951692, + "learning_rate": 1.9560265744792944e-05, + "loss": 1.0603, + "step": 1986 + }, + { + "epoch": 0.12198041683292919, + "grad_norm": 0.7114920699546503, + "learning_rate": 1.9559682412485515e-05, + "loss": 1.0816, + "step": 1987 + }, + { + "epoch": 0.12204180607139568, + "grad_norm": 0.6126404372485326, + "learning_rate": 1.955909870223271e-05, + "loss": 1.0021, + "step": 1988 + }, + { + "epoch": 0.12210319530986218, + "grad_norm": 0.6270229399723151, + "learning_rate": 1.955851461405761e-05, + "loss": 1.0053, + "step": 1989 + }, + { + "epoch": 0.12216458454832868, + "grad_norm": 0.6457606075877107, + "learning_rate": 1.9557930147983303e-05, + "loss": 1.0629, + "step": 1990 + }, + { + "epoch": 0.12222597378679517, + "grad_norm": 0.6572773283671037, + "learning_rate": 1.9557345304032898e-05, + "loss": 1.0194, + "step": 1991 + }, + { + "epoch": 0.12228736302526168, + "grad_norm": 0.6436183686934034, + "learning_rate": 1.9556760082229517e-05, + "loss": 1.0549, + "step": 1992 + }, + { + "epoch": 0.12234875226372817, + "grad_norm": 0.690862665967229, + "learning_rate": 1.9556174482596296e-05, + "loss": 1.0951, + "step": 1993 + }, + { + "epoch": 0.12241014150219466, + "grad_norm": 0.7103415611749009, + "learning_rate": 1.955558850515639e-05, + "loss": 1.0926, + "step": 1994 + }, + { + "epoch": 0.12247153074066117, + "grad_norm": 0.5877713718450229, + "learning_rate": 1.955500214993296e-05, + "loss": 1.0294, + "step": 1995 + }, + { + "epoch": 0.12253291997912766, + "grad_norm": 0.6762916209008383, + "learning_rate": 1.9554415416949195e-05, + "loss": 1.0763, + "step": 1996 + }, + { + "epoch": 0.12259430921759415, + "grad_norm": 0.7004192216660686, + "learning_rate": 1.9553828306228288e-05, + "loss": 1.1204, + "step": 1997 + }, + { + "epoch": 0.12265569845606066, + "grad_norm": 0.7302834633392845, + "learning_rate": 1.9553240817793445e-05, + "loss": 1.0896, + "step": 1998 + }, + { + "epoch": 0.12271708769452715, + "grad_norm": 0.6077680715637219, + "learning_rate": 1.95526529516679e-05, + "loss": 1.0353, + "step": 1999 + }, + { + "epoch": 0.12277847693299365, + "grad_norm": 0.6497708890181638, + "learning_rate": 1.9552064707874897e-05, + "loss": 1.049, + "step": 2000 + }, + { + "epoch": 0.12283986617146014, + "grad_norm": 0.6330457395925089, + "learning_rate": 1.9551476086437685e-05, + "loss": 1.0432, + "step": 2001 + }, + { + "epoch": 0.12290125540992664, + "grad_norm": 0.65830015728857, + "learning_rate": 1.9550887087379543e-05, + "loss": 1.0784, + "step": 2002 + }, + { + "epoch": 0.12296264464839314, + "grad_norm": 0.661835502225516, + "learning_rate": 1.9550297710723747e-05, + "loss": 1.0941, + "step": 2003 + }, + { + "epoch": 0.12302403388685963, + "grad_norm": 0.9848917645670259, + "learning_rate": 1.9549707956493605e-05, + "loss": 0.8222, + "step": 2004 + }, + { + "epoch": 0.12308542312532612, + "grad_norm": 0.6250349371006906, + "learning_rate": 1.9549117824712435e-05, + "loss": 1.0696, + "step": 2005 + }, + { + "epoch": 0.12314681236379263, + "grad_norm": 0.647355660032091, + "learning_rate": 1.954852731540356e-05, + "loss": 0.99, + "step": 2006 + }, + { + "epoch": 0.12320820160225912, + "grad_norm": 0.6757169346266542, + "learning_rate": 1.9547936428590335e-05, + "loss": 1.0823, + "step": 2007 + }, + { + "epoch": 0.12326959084072563, + "grad_norm": 0.7187142762398493, + "learning_rate": 1.9547345164296116e-05, + "loss": 1.0739, + "step": 2008 + }, + { + "epoch": 0.12333098007919212, + "grad_norm": 0.6566760131208907, + "learning_rate": 1.954675352254428e-05, + "loss": 1.0727, + "step": 2009 + }, + { + "epoch": 0.12339236931765861, + "grad_norm": 0.6862359353990475, + "learning_rate": 1.954616150335822e-05, + "loss": 1.1153, + "step": 2010 + }, + { + "epoch": 0.12345375855612511, + "grad_norm": 0.6401822876243388, + "learning_rate": 1.9545569106761334e-05, + "loss": 1.0082, + "step": 2011 + }, + { + "epoch": 0.1235151477945916, + "grad_norm": 0.6235323837264527, + "learning_rate": 1.954497633277705e-05, + "loss": 1.0344, + "step": 2012 + }, + { + "epoch": 0.1235765370330581, + "grad_norm": 0.6353907996330412, + "learning_rate": 1.9544383181428805e-05, + "loss": 1.0523, + "step": 2013 + }, + { + "epoch": 0.1236379262715246, + "grad_norm": 0.6324139298401074, + "learning_rate": 1.9543789652740043e-05, + "loss": 1.0301, + "step": 2014 + }, + { + "epoch": 0.1236993155099911, + "grad_norm": 0.659804577492112, + "learning_rate": 1.954319574673423e-05, + "loss": 1.0621, + "step": 2015 + }, + { + "epoch": 0.1237607047484576, + "grad_norm": 0.9144269647378866, + "learning_rate": 1.954260146343485e-05, + "loss": 0.7754, + "step": 2016 + }, + { + "epoch": 0.12382209398692409, + "grad_norm": 0.6696059803576969, + "learning_rate": 1.95420068028654e-05, + "loss": 1.0553, + "step": 2017 + }, + { + "epoch": 0.12388348322539058, + "grad_norm": 0.6248758621742418, + "learning_rate": 1.9541411765049383e-05, + "loss": 1.0622, + "step": 2018 + }, + { + "epoch": 0.12394487246385709, + "grad_norm": 0.6497162846111315, + "learning_rate": 1.954081635001033e-05, + "loss": 1.0524, + "step": 2019 + }, + { + "epoch": 0.12400626170232358, + "grad_norm": 0.5859985336005865, + "learning_rate": 1.954022055777178e-05, + "loss": 0.7963, + "step": 2020 + }, + { + "epoch": 0.12406765094079009, + "grad_norm": 0.669430198947167, + "learning_rate": 1.9539624388357282e-05, + "loss": 1.1291, + "step": 2021 + }, + { + "epoch": 0.12412904017925658, + "grad_norm": 0.7223228814991333, + "learning_rate": 1.953902784179041e-05, + "loss": 1.0515, + "step": 2022 + }, + { + "epoch": 0.12419042941772307, + "grad_norm": 0.6597708085979928, + "learning_rate": 1.9538430918094757e-05, + "loss": 1.0565, + "step": 2023 + }, + { + "epoch": 0.12425181865618957, + "grad_norm": 0.6455359339284538, + "learning_rate": 1.953783361729391e-05, + "loss": 1.0553, + "step": 2024 + }, + { + "epoch": 0.12431320789465607, + "grad_norm": 0.6650413173971816, + "learning_rate": 1.9537235939411488e-05, + "loss": 1.0395, + "step": 2025 + }, + { + "epoch": 0.12437459713312256, + "grad_norm": 0.6704680251949752, + "learning_rate": 1.953663788447112e-05, + "loss": 1.0393, + "step": 2026 + }, + { + "epoch": 0.12443598637158906, + "grad_norm": 0.6686898551211115, + "learning_rate": 1.9536039452496453e-05, + "loss": 1.0722, + "step": 2027 + }, + { + "epoch": 0.12449737561005556, + "grad_norm": 0.6483376568662281, + "learning_rate": 1.9535440643511142e-05, + "loss": 0.9953, + "step": 2028 + }, + { + "epoch": 0.12455876484852206, + "grad_norm": 0.6846784707365917, + "learning_rate": 1.9534841457538863e-05, + "loss": 1.0432, + "step": 2029 + }, + { + "epoch": 0.12462015408698855, + "grad_norm": 0.6365525520950996, + "learning_rate": 1.9534241894603306e-05, + "loss": 1.0456, + "step": 2030 + }, + { + "epoch": 0.12468154332545504, + "grad_norm": 0.6276165265064703, + "learning_rate": 1.9533641954728176e-05, + "loss": 1.0918, + "step": 2031 + }, + { + "epoch": 0.12474293256392155, + "grad_norm": 0.711772314625832, + "learning_rate": 1.953304163793719e-05, + "loss": 1.0701, + "step": 2032 + }, + { + "epoch": 0.12480432180238804, + "grad_norm": 0.6175527903903266, + "learning_rate": 1.953244094425408e-05, + "loss": 1.0615, + "step": 2033 + }, + { + "epoch": 0.12486571104085453, + "grad_norm": 0.6589998928204739, + "learning_rate": 1.9531839873702594e-05, + "loss": 1.0497, + "step": 2034 + }, + { + "epoch": 0.12492710027932104, + "grad_norm": 0.6689892808100009, + "learning_rate": 1.95312384263065e-05, + "loss": 1.0427, + "step": 2035 + }, + { + "epoch": 0.12498848951778753, + "grad_norm": 0.6480343825400595, + "learning_rate": 1.9530636602089577e-05, + "loss": 1.0598, + "step": 2036 + }, + { + "epoch": 0.12504987875625403, + "grad_norm": 0.6345709462552178, + "learning_rate": 1.9530034401075614e-05, + "loss": 1.0579, + "step": 2037 + }, + { + "epoch": 0.12511126799472053, + "grad_norm": 0.619459078801304, + "learning_rate": 1.952943182328842e-05, + "loss": 1.0492, + "step": 2038 + }, + { + "epoch": 0.12517265723318702, + "grad_norm": 0.6131116326660624, + "learning_rate": 1.952882886875182e-05, + "loss": 1.0477, + "step": 2039 + }, + { + "epoch": 0.1252340464716535, + "grad_norm": 0.626412190233174, + "learning_rate": 1.9528225537489648e-05, + "loss": 1.0499, + "step": 2040 + }, + { + "epoch": 0.12529543571012003, + "grad_norm": 0.6174737969766576, + "learning_rate": 1.9527621829525766e-05, + "loss": 1.0536, + "step": 2041 + }, + { + "epoch": 0.12535682494858652, + "grad_norm": 0.6295336392246361, + "learning_rate": 1.952701774488403e-05, + "loss": 1.0699, + "step": 2042 + }, + { + "epoch": 0.125418214187053, + "grad_norm": 0.6968432570916597, + "learning_rate": 1.9526413283588334e-05, + "loss": 1.0464, + "step": 2043 + }, + { + "epoch": 0.1254796034255195, + "grad_norm": 0.6681616924171264, + "learning_rate": 1.9525808445662564e-05, + "loss": 1.082, + "step": 2044 + }, + { + "epoch": 0.125540992663986, + "grad_norm": 0.5980404247694973, + "learning_rate": 1.952520323113064e-05, + "loss": 1.0169, + "step": 2045 + }, + { + "epoch": 0.1256023819024525, + "grad_norm": 0.6758884489127195, + "learning_rate": 1.952459764001649e-05, + "loss": 1.1028, + "step": 2046 + }, + { + "epoch": 0.125663771140919, + "grad_norm": 0.6288237757056161, + "learning_rate": 1.9523991672344057e-05, + "loss": 1.0362, + "step": 2047 + }, + { + "epoch": 0.1257251603793855, + "grad_norm": 0.6365464156394199, + "learning_rate": 1.952338532813729e-05, + "loss": 1.0689, + "step": 2048 + }, + { + "epoch": 0.125786549617852, + "grad_norm": 0.6770039193881284, + "learning_rate": 1.952277860742017e-05, + "loss": 1.1256, + "step": 2049 + }, + { + "epoch": 0.12584793885631848, + "grad_norm": 0.6533187751291486, + "learning_rate": 1.9522171510216677e-05, + "loss": 1.0591, + "step": 2050 + }, + { + "epoch": 0.12590932809478497, + "grad_norm": 0.6010333759536537, + "learning_rate": 1.9521564036550818e-05, + "loss": 1.0053, + "step": 2051 + }, + { + "epoch": 0.1259707173332515, + "grad_norm": 0.5743317252618152, + "learning_rate": 1.9520956186446607e-05, + "loss": 0.9774, + "step": 2052 + }, + { + "epoch": 0.12603210657171798, + "grad_norm": 0.6539444189677168, + "learning_rate": 1.9520347959928075e-05, + "loss": 1.0488, + "step": 2053 + }, + { + "epoch": 0.12609349581018447, + "grad_norm": 0.6077204459002038, + "learning_rate": 1.9519739357019273e-05, + "loss": 1.0315, + "step": 2054 + }, + { + "epoch": 0.12615488504865097, + "grad_norm": 0.61623526872307, + "learning_rate": 1.9519130377744256e-05, + "loss": 1.044, + "step": 2055 + }, + { + "epoch": 0.12621627428711746, + "grad_norm": 0.6742412415408119, + "learning_rate": 1.9518521022127106e-05, + "loss": 1.0327, + "step": 2056 + }, + { + "epoch": 0.12627766352558398, + "grad_norm": 0.6739909383384154, + "learning_rate": 1.951791129019191e-05, + "loss": 1.0672, + "step": 2057 + }, + { + "epoch": 0.12633905276405047, + "grad_norm": 0.6483211476281605, + "learning_rate": 1.9517301181962775e-05, + "loss": 1.1065, + "step": 2058 + }, + { + "epoch": 0.12640044200251696, + "grad_norm": 0.6361133538692608, + "learning_rate": 1.9516690697463824e-05, + "loss": 1.0197, + "step": 2059 + }, + { + "epoch": 0.12646183124098345, + "grad_norm": 0.6890175679601748, + "learning_rate": 1.951607983671919e-05, + "loss": 1.1196, + "step": 2060 + }, + { + "epoch": 0.12652322047944994, + "grad_norm": 0.6000533514929275, + "learning_rate": 1.9515468599753024e-05, + "loss": 1.0472, + "step": 2061 + }, + { + "epoch": 0.12658460971791646, + "grad_norm": 0.8111259012718448, + "learning_rate": 1.951485698658949e-05, + "loss": 1.0522, + "step": 2062 + }, + { + "epoch": 0.12664599895638295, + "grad_norm": 0.667433130761097, + "learning_rate": 1.951424499725277e-05, + "loss": 1.078, + "step": 2063 + }, + { + "epoch": 0.12670738819484945, + "grad_norm": 0.6414377438699247, + "learning_rate": 1.9513632631767062e-05, + "loss": 1.0483, + "step": 2064 + }, + { + "epoch": 0.12676877743331594, + "grad_norm": 0.6119435544361184, + "learning_rate": 1.9513019890156573e-05, + "loss": 1.0232, + "step": 2065 + }, + { + "epoch": 0.12683016667178243, + "grad_norm": 0.679539887497363, + "learning_rate": 1.951240677244553e-05, + "loss": 1.1017, + "step": 2066 + }, + { + "epoch": 0.12689155591024892, + "grad_norm": 0.7375395080593599, + "learning_rate": 1.9511793278658172e-05, + "loss": 1.102, + "step": 2067 + }, + { + "epoch": 0.12695294514871544, + "grad_norm": 0.644973149529972, + "learning_rate": 1.951117940881875e-05, + "loss": 1.0562, + "step": 2068 + }, + { + "epoch": 0.12701433438718193, + "grad_norm": 0.7036509117003446, + "learning_rate": 1.9510565162951538e-05, + "loss": 0.7843, + "step": 2069 + }, + { + "epoch": 0.12707572362564842, + "grad_norm": 0.7327874885345103, + "learning_rate": 1.950995054108082e-05, + "loss": 1.0438, + "step": 2070 + }, + { + "epoch": 0.12713711286411492, + "grad_norm": 0.6687458075195108, + "learning_rate": 1.950933554323089e-05, + "loss": 0.9971, + "step": 2071 + }, + { + "epoch": 0.1271985021025814, + "grad_norm": 0.6643841816383422, + "learning_rate": 1.950872016942607e-05, + "loss": 1.0465, + "step": 2072 + }, + { + "epoch": 0.12725989134104793, + "grad_norm": 0.6963724684246266, + "learning_rate": 1.9508104419690685e-05, + "loss": 1.0786, + "step": 2073 + }, + { + "epoch": 0.12732128057951442, + "grad_norm": 0.6473352590883991, + "learning_rate": 1.950748829404908e-05, + "loss": 1.0162, + "step": 2074 + }, + { + "epoch": 0.1273826698179809, + "grad_norm": 0.6614757039084458, + "learning_rate": 1.9506871792525613e-05, + "loss": 1.072, + "step": 2075 + }, + { + "epoch": 0.1274440590564474, + "grad_norm": 0.6526528822408899, + "learning_rate": 1.9506254915144656e-05, + "loss": 1.025, + "step": 2076 + }, + { + "epoch": 0.1275054482949139, + "grad_norm": 0.6801029288240208, + "learning_rate": 1.95056376619306e-05, + "loss": 1.0446, + "step": 2077 + }, + { + "epoch": 0.1275668375333804, + "grad_norm": 0.6555607068878372, + "learning_rate": 1.950502003290785e-05, + "loss": 1.0542, + "step": 2078 + }, + { + "epoch": 0.1276282267718469, + "grad_norm": 0.6512722224889482, + "learning_rate": 1.950440202810082e-05, + "loss": 1.0675, + "step": 2079 + }, + { + "epoch": 0.1276896160103134, + "grad_norm": 0.6524853487813023, + "learning_rate": 1.9503783647533945e-05, + "loss": 1.0743, + "step": 2080 + }, + { + "epoch": 0.1277510052487799, + "grad_norm": 0.7395655526954698, + "learning_rate": 1.950316489123167e-05, + "loss": 1.0875, + "step": 2081 + }, + { + "epoch": 0.12781239448724638, + "grad_norm": 0.6504807267527309, + "learning_rate": 1.950254575921846e-05, + "loss": 1.0728, + "step": 2082 + }, + { + "epoch": 0.12787378372571287, + "grad_norm": 0.6218228915856724, + "learning_rate": 1.95019262515188e-05, + "loss": 1.0689, + "step": 2083 + }, + { + "epoch": 0.1279351729641794, + "grad_norm": 0.6610310944853409, + "learning_rate": 1.950130636815717e-05, + "loss": 1.0844, + "step": 2084 + }, + { + "epoch": 0.12799656220264588, + "grad_norm": 0.6147263631358629, + "learning_rate": 1.950068610915808e-05, + "loss": 1.0132, + "step": 2085 + }, + { + "epoch": 0.12805795144111237, + "grad_norm": 0.6262660457843078, + "learning_rate": 1.950006547454606e-05, + "loss": 1.026, + "step": 2086 + }, + { + "epoch": 0.12811934067957886, + "grad_norm": 0.7002535196223657, + "learning_rate": 1.949944446434564e-05, + "loss": 1.064, + "step": 2087 + }, + { + "epoch": 0.12818072991804536, + "grad_norm": 0.700126105624822, + "learning_rate": 1.9498823078581374e-05, + "loss": 1.0507, + "step": 2088 + }, + { + "epoch": 0.12824211915651187, + "grad_norm": 0.6260997466547924, + "learning_rate": 1.949820131727783e-05, + "loss": 1.0, + "step": 2089 + }, + { + "epoch": 0.12830350839497837, + "grad_norm": 0.6751901816316019, + "learning_rate": 1.9497579180459584e-05, + "loss": 1.0438, + "step": 2090 + }, + { + "epoch": 0.12836489763344486, + "grad_norm": 0.6685994315503737, + "learning_rate": 1.949695666815124e-05, + "loss": 1.0621, + "step": 2091 + }, + { + "epoch": 0.12842628687191135, + "grad_norm": 0.672683950723216, + "learning_rate": 1.9496333780377402e-05, + "loss": 1.0869, + "step": 2092 + }, + { + "epoch": 0.12848767611037784, + "grad_norm": 0.7577951105403329, + "learning_rate": 1.9495710517162703e-05, + "loss": 1.108, + "step": 2093 + }, + { + "epoch": 0.12854906534884436, + "grad_norm": 0.6486973130176933, + "learning_rate": 1.949508687853178e-05, + "loss": 1.0582, + "step": 2094 + }, + { + "epoch": 0.12861045458731085, + "grad_norm": 0.6702061317790606, + "learning_rate": 1.949446286450929e-05, + "loss": 1.0239, + "step": 2095 + }, + { + "epoch": 0.12867184382577734, + "grad_norm": 0.6997079342827043, + "learning_rate": 1.9493838475119903e-05, + "loss": 1.0834, + "step": 2096 + }, + { + "epoch": 0.12873323306424383, + "grad_norm": 0.6791542629952094, + "learning_rate": 1.9493213710388302e-05, + "loss": 1.0792, + "step": 2097 + }, + { + "epoch": 0.12879462230271033, + "grad_norm": 0.6580507989985408, + "learning_rate": 1.949258857033919e-05, + "loss": 1.087, + "step": 2098 + }, + { + "epoch": 0.12885601154117682, + "grad_norm": 0.6003701101526526, + "learning_rate": 1.949196305499728e-05, + "loss": 1.0081, + "step": 2099 + }, + { + "epoch": 0.12891740077964334, + "grad_norm": 0.640660802558352, + "learning_rate": 1.9491337164387308e-05, + "loss": 1.0343, + "step": 2100 + }, + { + "epoch": 0.12897879001810983, + "grad_norm": 0.6750483250388992, + "learning_rate": 1.9490710898534014e-05, + "loss": 1.0764, + "step": 2101 + }, + { + "epoch": 0.12904017925657632, + "grad_norm": 0.6443596388714039, + "learning_rate": 1.9490084257462157e-05, + "loss": 0.9988, + "step": 2102 + }, + { + "epoch": 0.1291015684950428, + "grad_norm": 0.6272480451349954, + "learning_rate": 1.9489457241196517e-05, + "loss": 1.025, + "step": 2103 + }, + { + "epoch": 0.1291629577335093, + "grad_norm": 0.5871125997096324, + "learning_rate": 1.9488829849761875e-05, + "loss": 0.9827, + "step": 2104 + }, + { + "epoch": 0.12922434697197582, + "grad_norm": 0.6664737010904778, + "learning_rate": 1.948820208318304e-05, + "loss": 1.0242, + "step": 2105 + }, + { + "epoch": 0.12928573621044231, + "grad_norm": 0.674356661389267, + "learning_rate": 1.948757394148483e-05, + "loss": 1.0974, + "step": 2106 + }, + { + "epoch": 0.1293471254489088, + "grad_norm": 0.665112386900836, + "learning_rate": 1.948694542469208e-05, + "loss": 1.0726, + "step": 2107 + }, + { + "epoch": 0.1294085146873753, + "grad_norm": 0.6652156841123542, + "learning_rate": 1.9486316532829637e-05, + "loss": 1.0928, + "step": 2108 + }, + { + "epoch": 0.1294699039258418, + "grad_norm": 0.7417010539734685, + "learning_rate": 1.948568726592236e-05, + "loss": 1.0956, + "step": 2109 + }, + { + "epoch": 0.1295312931643083, + "grad_norm": 0.6232359510746549, + "learning_rate": 1.948505762399514e-05, + "loss": 1.0401, + "step": 2110 + }, + { + "epoch": 0.1295926824027748, + "grad_norm": 0.711371729533449, + "learning_rate": 1.9484427607072857e-05, + "loss": 1.031, + "step": 2111 + }, + { + "epoch": 0.1296540716412413, + "grad_norm": 0.6006979821406989, + "learning_rate": 1.948379721518043e-05, + "loss": 1.0091, + "step": 2112 + }, + { + "epoch": 0.12971546087970778, + "grad_norm": 0.6526035745551062, + "learning_rate": 1.9483166448342773e-05, + "loss": 1.0411, + "step": 2113 + }, + { + "epoch": 0.12977685011817428, + "grad_norm": 0.6609910805058397, + "learning_rate": 1.9482535306584826e-05, + "loss": 1.0413, + "step": 2114 + }, + { + "epoch": 0.1298382393566408, + "grad_norm": 0.6070660431607634, + "learning_rate": 1.948190378993154e-05, + "loss": 0.9822, + "step": 2115 + }, + { + "epoch": 0.12989962859510729, + "grad_norm": 0.7041212627730479, + "learning_rate": 1.948127189840789e-05, + "loss": 1.113, + "step": 2116 + }, + { + "epoch": 0.12996101783357378, + "grad_norm": 0.6140348326101174, + "learning_rate": 1.9480639632038853e-05, + "loss": 1.0299, + "step": 2117 + }, + { + "epoch": 0.13002240707204027, + "grad_norm": 0.7176202217660693, + "learning_rate": 1.948000699084942e-05, + "loss": 1.0869, + "step": 2118 + }, + { + "epoch": 0.13008379631050676, + "grad_norm": 0.6686920445171377, + "learning_rate": 1.947937397486461e-05, + "loss": 1.057, + "step": 2119 + }, + { + "epoch": 0.13014518554897325, + "grad_norm": 0.6492011199160097, + "learning_rate": 1.9478740584109448e-05, + "loss": 1.0543, + "step": 2120 + }, + { + "epoch": 0.13020657478743977, + "grad_norm": 0.6515146449315571, + "learning_rate": 1.9478106818608973e-05, + "loss": 0.8686, + "step": 2121 + }, + { + "epoch": 0.13026796402590626, + "grad_norm": 0.7151488231735574, + "learning_rate": 1.9477472678388248e-05, + "loss": 1.1051, + "step": 2122 + }, + { + "epoch": 0.13032935326437275, + "grad_norm": 0.6202841936653359, + "learning_rate": 1.9476838163472334e-05, + "loss": 1.0016, + "step": 2123 + }, + { + "epoch": 0.13039074250283925, + "grad_norm": 0.7007846243587591, + "learning_rate": 1.947620327388632e-05, + "loss": 1.0607, + "step": 2124 + }, + { + "epoch": 0.13045213174130574, + "grad_norm": 0.66786599048417, + "learning_rate": 1.9475568009655314e-05, + "loss": 1.0283, + "step": 2125 + }, + { + "epoch": 0.13051352097977226, + "grad_norm": 0.6752579092686591, + "learning_rate": 1.9474932370804424e-05, + "loss": 1.0591, + "step": 2126 + }, + { + "epoch": 0.13057491021823875, + "grad_norm": 0.6471198555094931, + "learning_rate": 1.947429635735878e-05, + "loss": 1.0529, + "step": 2127 + }, + { + "epoch": 0.13063629945670524, + "grad_norm": 0.6529137199251183, + "learning_rate": 1.947365996934353e-05, + "loss": 1.0542, + "step": 2128 + }, + { + "epoch": 0.13069768869517173, + "grad_norm": 0.6463970328278776, + "learning_rate": 1.9473023206783834e-05, + "loss": 1.0167, + "step": 2129 + }, + { + "epoch": 0.13075907793363822, + "grad_norm": 0.6515187834690777, + "learning_rate": 1.9472386069704864e-05, + "loss": 1.0302, + "step": 2130 + }, + { + "epoch": 0.13082046717210474, + "grad_norm": 0.6987873638233718, + "learning_rate": 1.9471748558131808e-05, + "loss": 1.0821, + "step": 2131 + }, + { + "epoch": 0.13088185641057123, + "grad_norm": 0.6675816987404859, + "learning_rate": 1.9471110672089877e-05, + "loss": 1.0601, + "step": 2132 + }, + { + "epoch": 0.13094324564903773, + "grad_norm": 0.6676725392695786, + "learning_rate": 1.9470472411604286e-05, + "loss": 1.0424, + "step": 2133 + }, + { + "epoch": 0.13100463488750422, + "grad_norm": 0.6304622377712776, + "learning_rate": 1.9469833776700266e-05, + "loss": 0.7622, + "step": 2134 + }, + { + "epoch": 0.1310660241259707, + "grad_norm": 0.6788127330235699, + "learning_rate": 1.9469194767403072e-05, + "loss": 1.0787, + "step": 2135 + }, + { + "epoch": 0.1311274133644372, + "grad_norm": 0.6516970689418227, + "learning_rate": 1.9468555383737962e-05, + "loss": 1.046, + "step": 2136 + }, + { + "epoch": 0.13118880260290372, + "grad_norm": 0.6350619226627289, + "learning_rate": 1.9467915625730216e-05, + "loss": 1.0723, + "step": 2137 + }, + { + "epoch": 0.1312501918413702, + "grad_norm": 0.6487062673673677, + "learning_rate": 1.946727549340513e-05, + "loss": 1.0431, + "step": 2138 + }, + { + "epoch": 0.1313115810798367, + "grad_norm": 0.6263548821667644, + "learning_rate": 1.9466634986788007e-05, + "loss": 0.9991, + "step": 2139 + }, + { + "epoch": 0.1313729703183032, + "grad_norm": 0.6146007580026798, + "learning_rate": 1.946599410590417e-05, + "loss": 0.9785, + "step": 2140 + }, + { + "epoch": 0.1314343595567697, + "grad_norm": 0.6023828819442926, + "learning_rate": 1.946535285077896e-05, + "loss": 0.8244, + "step": 2141 + }, + { + "epoch": 0.1314957487952362, + "grad_norm": 0.725689595805044, + "learning_rate": 1.946471122143773e-05, + "loss": 1.086, + "step": 2142 + }, + { + "epoch": 0.1315571380337027, + "grad_norm": 0.6505690344672251, + "learning_rate": 1.946406921790584e-05, + "loss": 1.0014, + "step": 2143 + }, + { + "epoch": 0.1316185272721692, + "grad_norm": 0.6667481021316803, + "learning_rate": 1.9463426840208682e-05, + "loss": 1.0258, + "step": 2144 + }, + { + "epoch": 0.13167991651063568, + "grad_norm": 0.6272068186175093, + "learning_rate": 1.946278408837164e-05, + "loss": 1.0506, + "step": 2145 + }, + { + "epoch": 0.13174130574910217, + "grad_norm": 0.620079722438038, + "learning_rate": 1.946214096242014e-05, + "loss": 0.9876, + "step": 2146 + }, + { + "epoch": 0.1318026949875687, + "grad_norm": 0.6173501323983864, + "learning_rate": 1.9461497462379597e-05, + "loss": 1.0293, + "step": 2147 + }, + { + "epoch": 0.13186408422603518, + "grad_norm": 0.6374617121486531, + "learning_rate": 1.9460853588275454e-05, + "loss": 1.0498, + "step": 2148 + }, + { + "epoch": 0.13192547346450167, + "grad_norm": 0.6117761260400422, + "learning_rate": 1.9460209340133173e-05, + "loss": 1.0301, + "step": 2149 + }, + { + "epoch": 0.13198686270296817, + "grad_norm": 0.6112529200269715, + "learning_rate": 1.9459564717978215e-05, + "loss": 1.0517, + "step": 2150 + }, + { + "epoch": 0.13204825194143466, + "grad_norm": 0.6688563486412807, + "learning_rate": 1.945891972183607e-05, + "loss": 1.0241, + "step": 2151 + }, + { + "epoch": 0.13210964117990118, + "grad_norm": 0.6933640257202425, + "learning_rate": 1.9458274351732243e-05, + "loss": 1.1008, + "step": 2152 + }, + { + "epoch": 0.13217103041836767, + "grad_norm": 0.6221057229500788, + "learning_rate": 1.9457628607692243e-05, + "loss": 1.026, + "step": 2153 + }, + { + "epoch": 0.13223241965683416, + "grad_norm": 0.6076559426493027, + "learning_rate": 1.9456982489741603e-05, + "loss": 0.7251, + "step": 2154 + }, + { + "epoch": 0.13229380889530065, + "grad_norm": 0.7030745118245655, + "learning_rate": 1.945633599790586e-05, + "loss": 1.0917, + "step": 2155 + }, + { + "epoch": 0.13235519813376714, + "grad_norm": 0.6835369325369329, + "learning_rate": 1.9455689132210585e-05, + "loss": 1.0668, + "step": 2156 + }, + { + "epoch": 0.13241658737223364, + "grad_norm": 0.6735524343905539, + "learning_rate": 1.9455041892681343e-05, + "loss": 1.0304, + "step": 2157 + }, + { + "epoch": 0.13247797661070015, + "grad_norm": 0.6496179529211357, + "learning_rate": 1.9454394279343726e-05, + "loss": 1.0483, + "step": 2158 + }, + { + "epoch": 0.13253936584916665, + "grad_norm": 0.6614503805631319, + "learning_rate": 1.9453746292223337e-05, + "loss": 1.0581, + "step": 2159 + }, + { + "epoch": 0.13260075508763314, + "grad_norm": 0.6002876955567961, + "learning_rate": 1.9453097931345797e-05, + "loss": 1.0297, + "step": 2160 + }, + { + "epoch": 0.13266214432609963, + "grad_norm": 0.7015948630000531, + "learning_rate": 1.9452449196736735e-05, + "loss": 1.1095, + "step": 2161 + }, + { + "epoch": 0.13272353356456612, + "grad_norm": 0.6595062859783177, + "learning_rate": 1.9451800088421802e-05, + "loss": 1.0389, + "step": 2162 + }, + { + "epoch": 0.13278492280303264, + "grad_norm": 0.6193483631259593, + "learning_rate": 1.945115060642666e-05, + "loss": 1.04, + "step": 2163 + }, + { + "epoch": 0.13284631204149913, + "grad_norm": 0.8901328150041377, + "learning_rate": 1.9450500750776987e-05, + "loss": 1.0553, + "step": 2164 + }, + { + "epoch": 0.13290770127996562, + "grad_norm": 0.5666738126839932, + "learning_rate": 1.944985052149847e-05, + "loss": 0.9832, + "step": 2165 + }, + { + "epoch": 0.13296909051843211, + "grad_norm": 0.6214079601731378, + "learning_rate": 1.9449199918616827e-05, + "loss": 1.0252, + "step": 2166 + }, + { + "epoch": 0.1330304797568986, + "grad_norm": 0.614878860300171, + "learning_rate": 1.944854894215777e-05, + "loss": 0.9829, + "step": 2167 + }, + { + "epoch": 0.13309186899536513, + "grad_norm": 0.6514595770927464, + "learning_rate": 1.9447897592147038e-05, + "loss": 1.0355, + "step": 2168 + }, + { + "epoch": 0.13315325823383162, + "grad_norm": 0.6813427735029771, + "learning_rate": 1.9447245868610385e-05, + "loss": 1.0722, + "step": 2169 + }, + { + "epoch": 0.1332146474722981, + "grad_norm": 0.6501729505856476, + "learning_rate": 1.9446593771573572e-05, + "loss": 1.0596, + "step": 2170 + }, + { + "epoch": 0.1332760367107646, + "grad_norm": 0.6630614215598346, + "learning_rate": 1.944594130106239e-05, + "loss": 1.0375, + "step": 2171 + }, + { + "epoch": 0.1333374259492311, + "grad_norm": 0.6087893683313073, + "learning_rate": 1.944528845710262e-05, + "loss": 1.0448, + "step": 2172 + }, + { + "epoch": 0.13339881518769758, + "grad_norm": 0.6549616238668505, + "learning_rate": 1.9444635239720084e-05, + "loss": 1.053, + "step": 2173 + }, + { + "epoch": 0.1334602044261641, + "grad_norm": 0.6344866614430694, + "learning_rate": 1.9443981648940605e-05, + "loss": 1.0713, + "step": 2174 + }, + { + "epoch": 0.1335215936646306, + "grad_norm": 0.6157152267818109, + "learning_rate": 1.944332768479002e-05, + "loss": 0.9866, + "step": 2175 + }, + { + "epoch": 0.13358298290309709, + "grad_norm": 0.6391622408258663, + "learning_rate": 1.9442673347294187e-05, + "loss": 1.0451, + "step": 2176 + }, + { + "epoch": 0.13364437214156358, + "grad_norm": 0.6814699132829393, + "learning_rate": 1.9442018636478968e-05, + "loss": 1.0724, + "step": 2177 + }, + { + "epoch": 0.13370576138003007, + "grad_norm": 0.6685482571648959, + "learning_rate": 1.944136355237026e-05, + "loss": 1.0263, + "step": 2178 + }, + { + "epoch": 0.1337671506184966, + "grad_norm": 0.6264214934960247, + "learning_rate": 1.9440708094993952e-05, + "loss": 0.973, + "step": 2179 + }, + { + "epoch": 0.13382853985696308, + "grad_norm": 0.6520027661203299, + "learning_rate": 1.944005226437596e-05, + "loss": 1.0205, + "step": 2180 + }, + { + "epoch": 0.13388992909542957, + "grad_norm": 0.6626773374761099, + "learning_rate": 1.9439396060542213e-05, + "loss": 1.0336, + "step": 2181 + }, + { + "epoch": 0.13395131833389606, + "grad_norm": 0.6624782916849483, + "learning_rate": 1.9438739483518655e-05, + "loss": 1.0504, + "step": 2182 + }, + { + "epoch": 0.13401270757236255, + "grad_norm": 0.6438527195511329, + "learning_rate": 1.9438082533331243e-05, + "loss": 0.9969, + "step": 2183 + }, + { + "epoch": 0.13407409681082907, + "grad_norm": 0.6442771545239769, + "learning_rate": 1.9437425210005946e-05, + "loss": 1.079, + "step": 2184 + }, + { + "epoch": 0.13413548604929557, + "grad_norm": 0.6947137107443355, + "learning_rate": 1.943676751356876e-05, + "loss": 1.1211, + "step": 2185 + }, + { + "epoch": 0.13419687528776206, + "grad_norm": 0.6907134920789729, + "learning_rate": 1.9436109444045686e-05, + "loss": 1.0684, + "step": 2186 + }, + { + "epoch": 0.13425826452622855, + "grad_norm": 0.6891377446006857, + "learning_rate": 1.943545100146273e-05, + "loss": 1.0656, + "step": 2187 + }, + { + "epoch": 0.13431965376469504, + "grad_norm": 0.6547380977225008, + "learning_rate": 1.9434792185845937e-05, + "loss": 1.0207, + "step": 2188 + }, + { + "epoch": 0.13438104300316153, + "grad_norm": 0.6454762455541797, + "learning_rate": 1.9434132997221347e-05, + "loss": 1.0449, + "step": 2189 + }, + { + "epoch": 0.13444243224162805, + "grad_norm": 0.6807179625306878, + "learning_rate": 1.9433473435615024e-05, + "loss": 1.0235, + "step": 2190 + }, + { + "epoch": 0.13450382148009454, + "grad_norm": 0.6557628371544373, + "learning_rate": 1.943281350105304e-05, + "loss": 1.0858, + "step": 2191 + }, + { + "epoch": 0.13456521071856103, + "grad_norm": 0.5867408147046542, + "learning_rate": 1.9432153193561487e-05, + "loss": 1.0186, + "step": 2192 + }, + { + "epoch": 0.13462659995702753, + "grad_norm": 0.5758243057803611, + "learning_rate": 1.943149251316647e-05, + "loss": 0.996, + "step": 2193 + }, + { + "epoch": 0.13468798919549402, + "grad_norm": 0.6697319610368605, + "learning_rate": 1.9430831459894115e-05, + "loss": 1.0644, + "step": 2194 + }, + { + "epoch": 0.13474937843396054, + "grad_norm": 0.6634455361952204, + "learning_rate": 1.9430170033770553e-05, + "loss": 1.0655, + "step": 2195 + }, + { + "epoch": 0.13481076767242703, + "grad_norm": 0.6775993623865675, + "learning_rate": 1.9429508234821934e-05, + "loss": 1.0799, + "step": 2196 + }, + { + "epoch": 0.13487215691089352, + "grad_norm": 0.6204659369107881, + "learning_rate": 1.9428846063074415e-05, + "loss": 1.0576, + "step": 2197 + }, + { + "epoch": 0.13493354614936, + "grad_norm": 0.6208501567780712, + "learning_rate": 1.942818351855419e-05, + "loss": 1.0015, + "step": 2198 + }, + { + "epoch": 0.1349949353878265, + "grad_norm": 0.6363572816206443, + "learning_rate": 1.942752060128744e-05, + "loss": 1.079, + "step": 2199 + }, + { + "epoch": 0.13505632462629302, + "grad_norm": 0.6269875820069688, + "learning_rate": 1.942685731130038e-05, + "loss": 1.0407, + "step": 2200 + }, + { + "epoch": 0.13511771386475951, + "grad_norm": 0.664518023798119, + "learning_rate": 1.9426193648619235e-05, + "loss": 1.1036, + "step": 2201 + }, + { + "epoch": 0.135179103103226, + "grad_norm": 0.6683080855772929, + "learning_rate": 1.9425529613270236e-05, + "loss": 1.0621, + "step": 2202 + }, + { + "epoch": 0.1352404923416925, + "grad_norm": 0.6376126600745561, + "learning_rate": 1.9424865205279643e-05, + "loss": 1.0455, + "step": 2203 + }, + { + "epoch": 0.135301881580159, + "grad_norm": 0.594072775375165, + "learning_rate": 1.9424200424673723e-05, + "loss": 0.9777, + "step": 2204 + }, + { + "epoch": 0.1353632708186255, + "grad_norm": 0.6083890993279174, + "learning_rate": 1.942353527147875e-05, + "loss": 0.9789, + "step": 2205 + }, + { + "epoch": 0.135424660057092, + "grad_norm": 0.6983657497885034, + "learning_rate": 1.9422869745721032e-05, + "loss": 1.1115, + "step": 2206 + }, + { + "epoch": 0.1354860492955585, + "grad_norm": 0.634717050956026, + "learning_rate": 1.9422203847426872e-05, + "loss": 1.0248, + "step": 2207 + }, + { + "epoch": 0.13554743853402498, + "grad_norm": 0.7065347287468314, + "learning_rate": 1.9421537576622603e-05, + "loss": 1.1015, + "step": 2208 + }, + { + "epoch": 0.13560882777249147, + "grad_norm": 0.6601377448542122, + "learning_rate": 1.9420870933334563e-05, + "loss": 1.0954, + "step": 2209 + }, + { + "epoch": 0.13567021701095797, + "grad_norm": 0.6211950253574523, + "learning_rate": 1.942020391758911e-05, + "loss": 0.9827, + "step": 2210 + }, + { + "epoch": 0.13573160624942449, + "grad_norm": 0.6756940789162362, + "learning_rate": 1.9419536529412612e-05, + "loss": 1.0676, + "step": 2211 + }, + { + "epoch": 0.13579299548789098, + "grad_norm": 0.6603762252846681, + "learning_rate": 1.9418868768831454e-05, + "loss": 1.0246, + "step": 2212 + }, + { + "epoch": 0.13585438472635747, + "grad_norm": 0.6531260826185225, + "learning_rate": 1.941820063587204e-05, + "loss": 1.0551, + "step": 2213 + }, + { + "epoch": 0.13591577396482396, + "grad_norm": 0.6625499104074294, + "learning_rate": 1.9417532130560784e-05, + "loss": 1.0666, + "step": 2214 + }, + { + "epoch": 0.13597716320329045, + "grad_norm": 0.6907996739221449, + "learning_rate": 1.9416863252924112e-05, + "loss": 1.0484, + "step": 2215 + }, + { + "epoch": 0.13603855244175697, + "grad_norm": 0.6446160435572101, + "learning_rate": 1.941619400298847e-05, + "loss": 1.0275, + "step": 2216 + }, + { + "epoch": 0.13609994168022346, + "grad_norm": 0.6348143880561704, + "learning_rate": 1.941552438078032e-05, + "loss": 1.0293, + "step": 2217 + }, + { + "epoch": 0.13616133091868995, + "grad_norm": 0.6133024820716715, + "learning_rate": 1.941485438632613e-05, + "loss": 1.0599, + "step": 2218 + }, + { + "epoch": 0.13622272015715645, + "grad_norm": 0.6219468222761804, + "learning_rate": 1.94141840196524e-05, + "loss": 1.026, + "step": 2219 + }, + { + "epoch": 0.13628410939562294, + "grad_norm": 0.6491382222372944, + "learning_rate": 1.941351328078562e-05, + "loss": 1.0039, + "step": 2220 + }, + { + "epoch": 0.13634549863408946, + "grad_norm": 0.6305406652557549, + "learning_rate": 1.941284216975231e-05, + "loss": 1.0617, + "step": 2221 + }, + { + "epoch": 0.13640688787255595, + "grad_norm": 0.6025441335356244, + "learning_rate": 1.941217068657901e-05, + "loss": 1.0384, + "step": 2222 + }, + { + "epoch": 0.13646827711102244, + "grad_norm": 0.6900739445758773, + "learning_rate": 1.9411498831292263e-05, + "loss": 1.0831, + "step": 2223 + }, + { + "epoch": 0.13652966634948893, + "grad_norm": 0.6346049773965359, + "learning_rate": 1.9410826603918626e-05, + "loss": 0.8016, + "step": 2224 + }, + { + "epoch": 0.13659105558795542, + "grad_norm": 0.658803834163219, + "learning_rate": 1.9410154004484684e-05, + "loss": 1.0439, + "step": 2225 + }, + { + "epoch": 0.13665244482642191, + "grad_norm": 0.6222874535242581, + "learning_rate": 1.9409481033017025e-05, + "loss": 1.0054, + "step": 2226 + }, + { + "epoch": 0.13671383406488843, + "grad_norm": 0.7424513947253568, + "learning_rate": 1.9408807689542257e-05, + "loss": 1.0663, + "step": 2227 + }, + { + "epoch": 0.13677522330335493, + "grad_norm": 0.65762540810017, + "learning_rate": 1.9408133974086997e-05, + "loss": 1.0514, + "step": 2228 + }, + { + "epoch": 0.13683661254182142, + "grad_norm": 0.6726141888276879, + "learning_rate": 1.9407459886677885e-05, + "loss": 1.009, + "step": 2229 + }, + { + "epoch": 0.1368980017802879, + "grad_norm": 0.6581811802252054, + "learning_rate": 1.9406785427341567e-05, + "loss": 1.0411, + "step": 2230 + }, + { + "epoch": 0.1369593910187544, + "grad_norm": 0.6127318140542404, + "learning_rate": 1.940611059610471e-05, + "loss": 1.0145, + "step": 2231 + }, + { + "epoch": 0.13702078025722092, + "grad_norm": 0.645295216489361, + "learning_rate": 1.9405435392993995e-05, + "loss": 1.0204, + "step": 2232 + }, + { + "epoch": 0.1370821694956874, + "grad_norm": 0.6833719439561324, + "learning_rate": 1.940475981803611e-05, + "loss": 1.0773, + "step": 2233 + }, + { + "epoch": 0.1371435587341539, + "grad_norm": 0.6990478494770109, + "learning_rate": 1.9404083871257774e-05, + "loss": 1.0524, + "step": 2234 + }, + { + "epoch": 0.1372049479726204, + "grad_norm": 0.6357954851483404, + "learning_rate": 1.940340755268571e-05, + "loss": 1.014, + "step": 2235 + }, + { + "epoch": 0.1372663372110869, + "grad_norm": 0.6597348725204174, + "learning_rate": 1.9402730862346647e-05, + "loss": 0.9976, + "step": 2236 + }, + { + "epoch": 0.1373277264495534, + "grad_norm": 0.6012235255699381, + "learning_rate": 1.9402053800267343e-05, + "loss": 1.0001, + "step": 2237 + }, + { + "epoch": 0.1373891156880199, + "grad_norm": 0.6468278678470862, + "learning_rate": 1.940137636647457e-05, + "loss": 1.0486, + "step": 2238 + }, + { + "epoch": 0.1374505049264864, + "grad_norm": 0.6437188053718162, + "learning_rate": 1.9400698560995105e-05, + "loss": 0.9818, + "step": 2239 + }, + { + "epoch": 0.13751189416495288, + "grad_norm": 0.6999144820427821, + "learning_rate": 1.9400020383855747e-05, + "loss": 1.0939, + "step": 2240 + }, + { + "epoch": 0.13757328340341937, + "grad_norm": 0.7085497307684188, + "learning_rate": 1.939934183508331e-05, + "loss": 1.069, + "step": 2241 + }, + { + "epoch": 0.1376346726418859, + "grad_norm": 0.6898995433878238, + "learning_rate": 1.939866291470462e-05, + "loss": 1.127, + "step": 2242 + }, + { + "epoch": 0.13769606188035238, + "grad_norm": 0.5782490199946504, + "learning_rate": 1.9397983622746514e-05, + "loss": 0.9774, + "step": 2243 + }, + { + "epoch": 0.13775745111881887, + "grad_norm": 0.6423922289183048, + "learning_rate": 1.939730395923585e-05, + "loss": 1.0642, + "step": 2244 + }, + { + "epoch": 0.13781884035728537, + "grad_norm": 0.6549460018563348, + "learning_rate": 1.939662392419951e-05, + "loss": 1.0308, + "step": 2245 + }, + { + "epoch": 0.13788022959575186, + "grad_norm": 0.6382827689970153, + "learning_rate": 1.9395943517664358e-05, + "loss": 1.0626, + "step": 2246 + }, + { + "epoch": 0.13794161883421835, + "grad_norm": 0.6326953854345957, + "learning_rate": 1.939526273965731e-05, + "loss": 1.0375, + "step": 2247 + }, + { + "epoch": 0.13800300807268487, + "grad_norm": 0.5900955787047674, + "learning_rate": 1.9394581590205277e-05, + "loss": 0.9936, + "step": 2248 + }, + { + "epoch": 0.13806439731115136, + "grad_norm": 0.6513993323558223, + "learning_rate": 1.939390006933519e-05, + "loss": 1.044, + "step": 2249 + }, + { + "epoch": 0.13812578654961785, + "grad_norm": 0.6499980504719527, + "learning_rate": 1.9393218177073988e-05, + "loss": 1.0038, + "step": 2250 + }, + { + "epoch": 0.13818717578808434, + "grad_norm": 0.6405772639446126, + "learning_rate": 1.9392535913448635e-05, + "loss": 1.0066, + "step": 2251 + }, + { + "epoch": 0.13824856502655083, + "grad_norm": 0.6492622609968575, + "learning_rate": 1.93918532784861e-05, + "loss": 1.0094, + "step": 2252 + }, + { + "epoch": 0.13830995426501735, + "grad_norm": 0.5928286104493238, + "learning_rate": 1.9391170272213377e-05, + "loss": 1.0106, + "step": 2253 + }, + { + "epoch": 0.13837134350348385, + "grad_norm": 0.6754880704852047, + "learning_rate": 1.9390486894657465e-05, + "loss": 1.0714, + "step": 2254 + }, + { + "epoch": 0.13843273274195034, + "grad_norm": 0.674137574956232, + "learning_rate": 1.9389803145845382e-05, + "loss": 1.0326, + "step": 2255 + }, + { + "epoch": 0.13849412198041683, + "grad_norm": 0.6659235669905181, + "learning_rate": 1.9389119025804156e-05, + "loss": 1.111, + "step": 2256 + }, + { + "epoch": 0.13855551121888332, + "grad_norm": 0.6372324106157625, + "learning_rate": 1.938843453456084e-05, + "loss": 1.019, + "step": 2257 + }, + { + "epoch": 0.13861690045734984, + "grad_norm": 0.651213581477942, + "learning_rate": 1.93877496721425e-05, + "loss": 1.0322, + "step": 2258 + }, + { + "epoch": 0.13867828969581633, + "grad_norm": 0.6965691754403734, + "learning_rate": 1.9387064438576205e-05, + "loss": 1.0411, + "step": 2259 + }, + { + "epoch": 0.13873967893428282, + "grad_norm": 0.6289085787189879, + "learning_rate": 1.9386378833889043e-05, + "loss": 1.0069, + "step": 2260 + }, + { + "epoch": 0.13880106817274931, + "grad_norm": 0.6364907382621118, + "learning_rate": 1.938569285810812e-05, + "loss": 1.0375, + "step": 2261 + }, + { + "epoch": 0.1388624574112158, + "grad_norm": 0.641646553661949, + "learning_rate": 1.938500651126057e-05, + "loss": 1.0329, + "step": 2262 + }, + { + "epoch": 0.1389238466496823, + "grad_norm": 0.6879111027921717, + "learning_rate": 1.9384319793373514e-05, + "loss": 1.0758, + "step": 2263 + }, + { + "epoch": 0.13898523588814882, + "grad_norm": 0.6275562945808291, + "learning_rate": 1.9383632704474103e-05, + "loss": 1.0668, + "step": 2264 + }, + { + "epoch": 0.1390466251266153, + "grad_norm": 0.6690375791703473, + "learning_rate": 1.9382945244589505e-05, + "loss": 1.0222, + "step": 2265 + }, + { + "epoch": 0.1391080143650818, + "grad_norm": 0.6548113482440122, + "learning_rate": 1.9382257413746902e-05, + "loss": 1.0591, + "step": 2266 + }, + { + "epoch": 0.1391694036035483, + "grad_norm": 0.6247375175707723, + "learning_rate": 1.938156921197348e-05, + "loss": 0.9621, + "step": 2267 + }, + { + "epoch": 0.13923079284201478, + "grad_norm": 0.6903340246420189, + "learning_rate": 1.9380880639296455e-05, + "loss": 1.031, + "step": 2268 + }, + { + "epoch": 0.1392921820804813, + "grad_norm": 0.6443621928646522, + "learning_rate": 1.9380191695743037e-05, + "loss": 1.0255, + "step": 2269 + }, + { + "epoch": 0.1393535713189478, + "grad_norm": 0.6820883709658864, + "learning_rate": 1.937950238134048e-05, + "loss": 1.0797, + "step": 2270 + }, + { + "epoch": 0.13941496055741429, + "grad_norm": 0.6539805239944122, + "learning_rate": 1.9378812696116028e-05, + "loss": 1.0261, + "step": 2271 + }, + { + "epoch": 0.13947634979588078, + "grad_norm": 0.6326862559193317, + "learning_rate": 1.9378122640096947e-05, + "loss": 0.9882, + "step": 2272 + }, + { + "epoch": 0.13953773903434727, + "grad_norm": 0.7308955449293528, + "learning_rate": 1.9377432213310522e-05, + "loss": 1.1125, + "step": 2273 + }, + { + "epoch": 0.1395991282728138, + "grad_norm": 0.6236370850859027, + "learning_rate": 1.9376741415784045e-05, + "loss": 1.0015, + "step": 2274 + }, + { + "epoch": 0.13966051751128028, + "grad_norm": 0.6592084072719357, + "learning_rate": 1.9376050247544832e-05, + "loss": 1.0261, + "step": 2275 + }, + { + "epoch": 0.13972190674974677, + "grad_norm": 0.6565367782186076, + "learning_rate": 1.9375358708620204e-05, + "loss": 1.0355, + "step": 2276 + }, + { + "epoch": 0.13978329598821326, + "grad_norm": 0.6492200799644595, + "learning_rate": 1.9374666799037505e-05, + "loss": 1.0476, + "step": 2277 + }, + { + "epoch": 0.13984468522667975, + "grad_norm": 0.6229677490854304, + "learning_rate": 1.937397451882409e-05, + "loss": 1.0108, + "step": 2278 + }, + { + "epoch": 0.13990607446514625, + "grad_norm": 0.6900922236968072, + "learning_rate": 1.937328186800732e-05, + "loss": 1.1168, + "step": 2279 + }, + { + "epoch": 0.13996746370361277, + "grad_norm": 0.6262160778849483, + "learning_rate": 1.937258884661459e-05, + "loss": 0.9801, + "step": 2280 + }, + { + "epoch": 0.14002885294207926, + "grad_norm": 0.695304873081682, + "learning_rate": 1.9371895454673296e-05, + "loss": 1.0502, + "step": 2281 + }, + { + "epoch": 0.14009024218054575, + "grad_norm": 0.7213200625313525, + "learning_rate": 1.9371201692210847e-05, + "loss": 1.0578, + "step": 2282 + }, + { + "epoch": 0.14015163141901224, + "grad_norm": 0.6503954633632947, + "learning_rate": 1.937050755925468e-05, + "loss": 1.0273, + "step": 2283 + }, + { + "epoch": 0.14021302065747873, + "grad_norm": 0.6585088364051558, + "learning_rate": 1.936981305583223e-05, + "loss": 1.1302, + "step": 2284 + }, + { + "epoch": 0.14027440989594525, + "grad_norm": 0.6213711365685272, + "learning_rate": 1.936911818197095e-05, + "loss": 1.0299, + "step": 2285 + }, + { + "epoch": 0.14033579913441174, + "grad_norm": 0.6326077169952068, + "learning_rate": 1.9368422937698327e-05, + "loss": 1.0646, + "step": 2286 + }, + { + "epoch": 0.14039718837287823, + "grad_norm": 0.6109662218018749, + "learning_rate": 1.9367727323041837e-05, + "loss": 1.0, + "step": 2287 + }, + { + "epoch": 0.14045857761134473, + "grad_norm": 0.596803261067223, + "learning_rate": 1.936703133802898e-05, + "loss": 1.0036, + "step": 2288 + }, + { + "epoch": 0.14051996684981122, + "grad_norm": 0.6547803616950026, + "learning_rate": 1.936633498268728e-05, + "loss": 1.0447, + "step": 2289 + }, + { + "epoch": 0.14058135608827774, + "grad_norm": 0.6183101375824617, + "learning_rate": 1.9365638257044264e-05, + "loss": 1.0167, + "step": 2290 + }, + { + "epoch": 0.14064274532674423, + "grad_norm": 0.6281680282270098, + "learning_rate": 1.9364941161127473e-05, + "loss": 1.0232, + "step": 2291 + }, + { + "epoch": 0.14070413456521072, + "grad_norm": 0.6028063496294621, + "learning_rate": 1.9364243694964476e-05, + "loss": 1.051, + "step": 2292 + }, + { + "epoch": 0.1407655238036772, + "grad_norm": 0.616864908244225, + "learning_rate": 1.9363545858582836e-05, + "loss": 1.0675, + "step": 2293 + }, + { + "epoch": 0.1408269130421437, + "grad_norm": 0.6367705792105868, + "learning_rate": 1.9362847652010153e-05, + "loss": 1.0657, + "step": 2294 + }, + { + "epoch": 0.14088830228061022, + "grad_norm": 0.6909218710729942, + "learning_rate": 1.9362149075274025e-05, + "loss": 1.0047, + "step": 2295 + }, + { + "epoch": 0.14094969151907671, + "grad_norm": 0.66362717917607, + "learning_rate": 1.936145012840207e-05, + "loss": 1.0313, + "step": 2296 + }, + { + "epoch": 0.1410110807575432, + "grad_norm": 0.6771345092438271, + "learning_rate": 1.9360750811421923e-05, + "loss": 1.0362, + "step": 2297 + }, + { + "epoch": 0.1410724699960097, + "grad_norm": 0.6823612962090947, + "learning_rate": 1.9360051124361236e-05, + "loss": 1.0811, + "step": 2298 + }, + { + "epoch": 0.1411338592344762, + "grad_norm": 0.6929515957380811, + "learning_rate": 1.9359351067247662e-05, + "loss": 1.0504, + "step": 2299 + }, + { + "epoch": 0.14119524847294268, + "grad_norm": 0.6581470685868669, + "learning_rate": 1.9358650640108888e-05, + "loss": 1.0063, + "step": 2300 + }, + { + "epoch": 0.1412566377114092, + "grad_norm": 0.7042514062900911, + "learning_rate": 1.9357949842972597e-05, + "loss": 1.0849, + "step": 2301 + }, + { + "epoch": 0.1413180269498757, + "grad_norm": 0.6481168177916891, + "learning_rate": 1.9357248675866497e-05, + "loss": 1.0554, + "step": 2302 + }, + { + "epoch": 0.14137941618834218, + "grad_norm": 0.6913609515019165, + "learning_rate": 1.9356547138818314e-05, + "loss": 1.0967, + "step": 2303 + }, + { + "epoch": 0.14144080542680867, + "grad_norm": 0.7015185058693422, + "learning_rate": 1.9355845231855782e-05, + "loss": 1.0999, + "step": 2304 + }, + { + "epoch": 0.14150219466527517, + "grad_norm": 0.7144850275195465, + "learning_rate": 1.9355142955006645e-05, + "loss": 1.1053, + "step": 2305 + }, + { + "epoch": 0.14156358390374169, + "grad_norm": 0.6053764975504287, + "learning_rate": 1.9354440308298676e-05, + "loss": 1.032, + "step": 2306 + }, + { + "epoch": 0.14162497314220818, + "grad_norm": 0.6713284550598371, + "learning_rate": 1.935373729175965e-05, + "loss": 1.0563, + "step": 2307 + }, + { + "epoch": 0.14168636238067467, + "grad_norm": 0.6682658739768413, + "learning_rate": 1.935303390541736e-05, + "loss": 1.0412, + "step": 2308 + }, + { + "epoch": 0.14174775161914116, + "grad_norm": 0.6502411013348062, + "learning_rate": 1.9352330149299613e-05, + "loss": 1.0411, + "step": 2309 + }, + { + "epoch": 0.14180914085760765, + "grad_norm": 0.66948587139552, + "learning_rate": 1.935162602343424e-05, + "loss": 0.9934, + "step": 2310 + }, + { + "epoch": 0.14187053009607417, + "grad_norm": 0.6856081953649383, + "learning_rate": 1.9350921527849075e-05, + "loss": 1.0393, + "step": 2311 + }, + { + "epoch": 0.14193191933454066, + "grad_norm": 0.6664375290642277, + "learning_rate": 1.9350216662571967e-05, + "loss": 1.0334, + "step": 2312 + }, + { + "epoch": 0.14199330857300715, + "grad_norm": 0.6447116415191673, + "learning_rate": 1.9349511427630785e-05, + "loss": 1.0121, + "step": 2313 + }, + { + "epoch": 0.14205469781147365, + "grad_norm": 0.6023764792427241, + "learning_rate": 1.9348805823053415e-05, + "loss": 0.9814, + "step": 2314 + }, + { + "epoch": 0.14211608704994014, + "grad_norm": 0.6323605633650967, + "learning_rate": 1.934809984886775e-05, + "loss": 1.0585, + "step": 2315 + }, + { + "epoch": 0.14217747628840663, + "grad_norm": 0.6101933215850548, + "learning_rate": 1.9347393505101696e-05, + "loss": 1.005, + "step": 2316 + }, + { + "epoch": 0.14223886552687315, + "grad_norm": 0.6288097347032535, + "learning_rate": 1.9346686791783188e-05, + "loss": 1.0185, + "step": 2317 + }, + { + "epoch": 0.14230025476533964, + "grad_norm": 0.6972876379537799, + "learning_rate": 1.934597970894016e-05, + "loss": 1.0414, + "step": 2318 + }, + { + "epoch": 0.14236164400380613, + "grad_norm": 0.6725521669054308, + "learning_rate": 1.9345272256600567e-05, + "loss": 1.0485, + "step": 2319 + }, + { + "epoch": 0.14242303324227262, + "grad_norm": 0.6931894470880194, + "learning_rate": 1.9344564434792382e-05, + "loss": 0.9975, + "step": 2320 + }, + { + "epoch": 0.14248442248073911, + "grad_norm": 0.6846145546466801, + "learning_rate": 1.9343856243543584e-05, + "loss": 1.0516, + "step": 2321 + }, + { + "epoch": 0.14254581171920563, + "grad_norm": 0.6561077667575634, + "learning_rate": 1.9343147682882177e-05, + "loss": 1.0545, + "step": 2322 + }, + { + "epoch": 0.14260720095767213, + "grad_norm": 0.6616453079609981, + "learning_rate": 1.934243875283617e-05, + "loss": 1.088, + "step": 2323 + }, + { + "epoch": 0.14266859019613862, + "grad_norm": 0.5956046225354135, + "learning_rate": 1.934172945343359e-05, + "loss": 1.0387, + "step": 2324 + }, + { + "epoch": 0.1427299794346051, + "grad_norm": 0.6122330649544179, + "learning_rate": 1.9341019784702485e-05, + "loss": 0.9896, + "step": 2325 + }, + { + "epoch": 0.1427913686730716, + "grad_norm": 0.6871743079324415, + "learning_rate": 1.9340309746670907e-05, + "loss": 1.0412, + "step": 2326 + }, + { + "epoch": 0.14285275791153812, + "grad_norm": 0.7819279491642153, + "learning_rate": 1.9339599339366933e-05, + "loss": 1.0409, + "step": 2327 + }, + { + "epoch": 0.1429141471500046, + "grad_norm": 0.6540173218681172, + "learning_rate": 1.933888856281864e-05, + "loss": 1.0373, + "step": 2328 + }, + { + "epoch": 0.1429755363884711, + "grad_norm": 0.6702614072855673, + "learning_rate": 1.9338177417054135e-05, + "loss": 0.9919, + "step": 2329 + }, + { + "epoch": 0.1430369256269376, + "grad_norm": 0.6481742711486255, + "learning_rate": 1.9337465902101534e-05, + "loss": 1.0125, + "step": 2330 + }, + { + "epoch": 0.14309831486540409, + "grad_norm": 0.7263701289438785, + "learning_rate": 1.933675401798897e-05, + "loss": 1.0937, + "step": 2331 + }, + { + "epoch": 0.1431597041038706, + "grad_norm": 0.6823287681559965, + "learning_rate": 1.933604176474458e-05, + "loss": 1.0498, + "step": 2332 + }, + { + "epoch": 0.1432210933423371, + "grad_norm": 0.66993767382102, + "learning_rate": 1.9335329142396522e-05, + "loss": 1.0621, + "step": 2333 + }, + { + "epoch": 0.1432824825808036, + "grad_norm": 0.6776445596386246, + "learning_rate": 1.9334616150972977e-05, + "loss": 1.1161, + "step": 2334 + }, + { + "epoch": 0.14334387181927008, + "grad_norm": 0.6475955495783515, + "learning_rate": 1.933390279050213e-05, + "loss": 1.0294, + "step": 2335 + }, + { + "epoch": 0.14340526105773657, + "grad_norm": 0.6304683101304341, + "learning_rate": 1.9333189061012186e-05, + "loss": 1.026, + "step": 2336 + }, + { + "epoch": 0.14346665029620306, + "grad_norm": 0.6205596982269116, + "learning_rate": 1.9332474962531362e-05, + "loss": 1.0359, + "step": 2337 + }, + { + "epoch": 0.14352803953466958, + "grad_norm": 0.5926670739984975, + "learning_rate": 1.933176049508789e-05, + "loss": 0.9859, + "step": 2338 + }, + { + "epoch": 0.14358942877313607, + "grad_norm": 0.6445204492999345, + "learning_rate": 1.933104565871001e-05, + "loss": 1.0546, + "step": 2339 + }, + { + "epoch": 0.14365081801160257, + "grad_norm": 0.5845130614865603, + "learning_rate": 1.9330330453425995e-05, + "loss": 1.0095, + "step": 2340 + }, + { + "epoch": 0.14371220725006906, + "grad_norm": 0.5808018302247066, + "learning_rate": 1.932961487926411e-05, + "loss": 0.9743, + "step": 2341 + }, + { + "epoch": 0.14377359648853555, + "grad_norm": 0.6553888919962648, + "learning_rate": 1.9328898936252654e-05, + "loss": 1.045, + "step": 2342 + }, + { + "epoch": 0.14383498572700207, + "grad_norm": 0.6349243024558245, + "learning_rate": 1.932818262441993e-05, + "loss": 1.0481, + "step": 2343 + }, + { + "epoch": 0.14389637496546856, + "grad_norm": 0.6359221063887937, + "learning_rate": 1.9327465943794252e-05, + "loss": 1.0501, + "step": 2344 + }, + { + "epoch": 0.14395776420393505, + "grad_norm": 0.6377346289914488, + "learning_rate": 1.9326748894403963e-05, + "loss": 1.0364, + "step": 2345 + }, + { + "epoch": 0.14401915344240154, + "grad_norm": 0.6798724581539481, + "learning_rate": 1.9326031476277403e-05, + "loss": 1.0746, + "step": 2346 + }, + { + "epoch": 0.14408054268086803, + "grad_norm": 0.6540643076827193, + "learning_rate": 1.932531368944294e-05, + "loss": 0.9784, + "step": 2347 + }, + { + "epoch": 0.14414193191933455, + "grad_norm": 0.6057577140872974, + "learning_rate": 1.9324595533928954e-05, + "loss": 1.0739, + "step": 2348 + }, + { + "epoch": 0.14420332115780105, + "grad_norm": 0.6160726018960525, + "learning_rate": 1.9323877009763834e-05, + "loss": 1.0029, + "step": 2349 + }, + { + "epoch": 0.14426471039626754, + "grad_norm": 0.6886544254602401, + "learning_rate": 1.932315811697599e-05, + "loss": 1.0849, + "step": 2350 + }, + { + "epoch": 0.14432609963473403, + "grad_norm": 0.6674566988006292, + "learning_rate": 1.932243885559384e-05, + "loss": 0.8033, + "step": 2351 + }, + { + "epoch": 0.14438748887320052, + "grad_norm": 0.663545936413544, + "learning_rate": 1.932171922564582e-05, + "loss": 1.0617, + "step": 2352 + }, + { + "epoch": 0.144448878111667, + "grad_norm": 0.6731292027788266, + "learning_rate": 1.9320999227160387e-05, + "loss": 1.072, + "step": 2353 + }, + { + "epoch": 0.14451026735013353, + "grad_norm": 0.6715843447683376, + "learning_rate": 1.9320278860166e-05, + "loss": 1.0679, + "step": 2354 + }, + { + "epoch": 0.14457165658860002, + "grad_norm": 0.6433241569142086, + "learning_rate": 1.9319558124691143e-05, + "loss": 1.0135, + "step": 2355 + }, + { + "epoch": 0.14463304582706651, + "grad_norm": 0.6535007965105676, + "learning_rate": 1.9318837020764305e-05, + "loss": 1.0369, + "step": 2356 + }, + { + "epoch": 0.144694435065533, + "grad_norm": 0.6571644403977026, + "learning_rate": 1.9318115548414004e-05, + "loss": 1.0314, + "step": 2357 + }, + { + "epoch": 0.1447558243039995, + "grad_norm": 0.6306870439305933, + "learning_rate": 1.9317393707668753e-05, + "loss": 1.0413, + "step": 2358 + }, + { + "epoch": 0.14481721354246602, + "grad_norm": 0.6290860493088216, + "learning_rate": 1.9316671498557103e-05, + "loss": 1.0355, + "step": 2359 + }, + { + "epoch": 0.1448786027809325, + "grad_norm": 0.638249507247941, + "learning_rate": 1.9315948921107592e-05, + "loss": 1.0769, + "step": 2360 + }, + { + "epoch": 0.144939992019399, + "grad_norm": 0.629256278740197, + "learning_rate": 1.9315225975348802e-05, + "loss": 1.0735, + "step": 2361 + }, + { + "epoch": 0.1450013812578655, + "grad_norm": 0.7800287347082454, + "learning_rate": 1.9314502661309303e-05, + "loss": 1.1336, + "step": 2362 + }, + { + "epoch": 0.14506277049633198, + "grad_norm": 0.6356694074874728, + "learning_rate": 1.93137789790177e-05, + "loss": 1.0627, + "step": 2363 + }, + { + "epoch": 0.1451241597347985, + "grad_norm": 0.6849058221794181, + "learning_rate": 1.9313054928502596e-05, + "loss": 1.0881, + "step": 2364 + }, + { + "epoch": 0.145185548973265, + "grad_norm": 0.6570944004280659, + "learning_rate": 1.9312330509792624e-05, + "loss": 1.0385, + "step": 2365 + }, + { + "epoch": 0.14524693821173149, + "grad_norm": 0.6452845802432047, + "learning_rate": 1.931160572291642e-05, + "loss": 0.9829, + "step": 2366 + }, + { + "epoch": 0.14530832745019798, + "grad_norm": 0.6982431743203388, + "learning_rate": 1.931088056790264e-05, + "loss": 1.0546, + "step": 2367 + }, + { + "epoch": 0.14536971668866447, + "grad_norm": 0.6713951083556193, + "learning_rate": 1.9310155044779952e-05, + "loss": 1.0362, + "step": 2368 + }, + { + "epoch": 0.14543110592713096, + "grad_norm": 0.6653154005403199, + "learning_rate": 1.9309429153577042e-05, + "loss": 1.0719, + "step": 2369 + }, + { + "epoch": 0.14549249516559748, + "grad_norm": 0.6338169062289775, + "learning_rate": 1.9308702894322606e-05, + "loss": 0.973, + "step": 2370 + }, + { + "epoch": 0.14555388440406397, + "grad_norm": 0.6053837461534213, + "learning_rate": 1.930797626704536e-05, + "loss": 1.0343, + "step": 2371 + }, + { + "epoch": 0.14561527364253046, + "grad_norm": 0.6433854172302838, + "learning_rate": 1.9307249271774032e-05, + "loss": 1.0033, + "step": 2372 + }, + { + "epoch": 0.14567666288099695, + "grad_norm": 0.6045276246447674, + "learning_rate": 1.9306521908537358e-05, + "loss": 0.993, + "step": 2373 + }, + { + "epoch": 0.14573805211946345, + "grad_norm": 0.6783018172868627, + "learning_rate": 1.93057941773641e-05, + "loss": 1.0135, + "step": 2374 + }, + { + "epoch": 0.14579944135792997, + "grad_norm": 0.6940095465676364, + "learning_rate": 1.9305066078283025e-05, + "loss": 1.08, + "step": 2375 + }, + { + "epoch": 0.14586083059639646, + "grad_norm": 0.6238155298808882, + "learning_rate": 1.9304337611322918e-05, + "loss": 1.0525, + "step": 2376 + }, + { + "epoch": 0.14592221983486295, + "grad_norm": 0.6410576015233653, + "learning_rate": 1.9303608776512587e-05, + "loss": 1.0189, + "step": 2377 + }, + { + "epoch": 0.14598360907332944, + "grad_norm": 0.7109379430428798, + "learning_rate": 1.930287957388084e-05, + "loss": 1.046, + "step": 2378 + }, + { + "epoch": 0.14604499831179593, + "grad_norm": 0.6066614296783172, + "learning_rate": 1.9302150003456514e-05, + "loss": 1.0096, + "step": 2379 + }, + { + "epoch": 0.14610638755026245, + "grad_norm": 0.5909292954019603, + "learning_rate": 1.9301420065268438e-05, + "loss": 0.9462, + "step": 2380 + }, + { + "epoch": 0.14616777678872894, + "grad_norm": 0.627638932260758, + "learning_rate": 1.9300689759345484e-05, + "loss": 1.0534, + "step": 2381 + }, + { + "epoch": 0.14622916602719543, + "grad_norm": 0.6441422028132846, + "learning_rate": 1.929995908571652e-05, + "loss": 1.0604, + "step": 2382 + }, + { + "epoch": 0.14629055526566193, + "grad_norm": 0.7156595771651351, + "learning_rate": 1.9299228044410435e-05, + "loss": 1.1011, + "step": 2383 + }, + { + "epoch": 0.14635194450412842, + "grad_norm": 0.6579397991522339, + "learning_rate": 1.929849663545613e-05, + "loss": 1.0477, + "step": 2384 + }, + { + "epoch": 0.14641333374259494, + "grad_norm": 0.6587045299578047, + "learning_rate": 1.9297764858882516e-05, + "loss": 1.0805, + "step": 2385 + }, + { + "epoch": 0.14647472298106143, + "grad_norm": 0.6595577225258167, + "learning_rate": 1.929703271471853e-05, + "loss": 1.0544, + "step": 2386 + }, + { + "epoch": 0.14653611221952792, + "grad_norm": 0.660747942359393, + "learning_rate": 1.929630020299312e-05, + "loss": 1.0563, + "step": 2387 + }, + { + "epoch": 0.1465975014579944, + "grad_norm": 0.6320154112368621, + "learning_rate": 1.9295567323735242e-05, + "loss": 1.0136, + "step": 2388 + }, + { + "epoch": 0.1466588906964609, + "grad_norm": 0.6253506358269086, + "learning_rate": 1.9294834076973872e-05, + "loss": 1.0513, + "step": 2389 + }, + { + "epoch": 0.1467202799349274, + "grad_norm": 0.6327102782599977, + "learning_rate": 1.9294100462737998e-05, + "loss": 1.0175, + "step": 2390 + }, + { + "epoch": 0.1467816691733939, + "grad_norm": 0.602075271008103, + "learning_rate": 1.9293366481056622e-05, + "loss": 1.017, + "step": 2391 + }, + { + "epoch": 0.1468430584118604, + "grad_norm": 0.6851148169117821, + "learning_rate": 1.9292632131958768e-05, + "loss": 1.0736, + "step": 2392 + }, + { + "epoch": 0.1469044476503269, + "grad_norm": 0.6565177902033571, + "learning_rate": 1.9291897415473465e-05, + "loss": 1.0738, + "step": 2393 + }, + { + "epoch": 0.1469658368887934, + "grad_norm": 0.6052802458321247, + "learning_rate": 1.9291162331629762e-05, + "loss": 0.9577, + "step": 2394 + }, + { + "epoch": 0.14702722612725988, + "grad_norm": 0.6278929239560069, + "learning_rate": 1.9290426880456717e-05, + "loss": 1.0062, + "step": 2395 + }, + { + "epoch": 0.1470886153657264, + "grad_norm": 0.6277293682541475, + "learning_rate": 1.928969106198341e-05, + "loss": 1.0206, + "step": 2396 + }, + { + "epoch": 0.1471500046041929, + "grad_norm": 0.655246727763989, + "learning_rate": 1.9288954876238926e-05, + "loss": 1.0695, + "step": 2397 + }, + { + "epoch": 0.14721139384265938, + "grad_norm": 0.6390645019158971, + "learning_rate": 1.9288218323252383e-05, + "loss": 1.0221, + "step": 2398 + }, + { + "epoch": 0.14727278308112587, + "grad_norm": 0.6302813540178421, + "learning_rate": 1.9287481403052885e-05, + "loss": 1.0025, + "step": 2399 + }, + { + "epoch": 0.14733417231959237, + "grad_norm": 0.6518334207179535, + "learning_rate": 1.928674411566958e-05, + "loss": 1.0263, + "step": 2400 + }, + { + "epoch": 0.14739556155805889, + "grad_norm": 0.6209104615455299, + "learning_rate": 1.928600646113161e-05, + "loss": 0.995, + "step": 2401 + }, + { + "epoch": 0.14745695079652538, + "grad_norm": 0.6668128204398558, + "learning_rate": 1.9285268439468136e-05, + "loss": 1.0127, + "step": 2402 + }, + { + "epoch": 0.14751834003499187, + "grad_norm": 0.6634109537633233, + "learning_rate": 1.9284530050708342e-05, + "loss": 1.0456, + "step": 2403 + }, + { + "epoch": 0.14757972927345836, + "grad_norm": 0.6640036349556786, + "learning_rate": 1.9283791294881417e-05, + "loss": 1.0218, + "step": 2404 + }, + { + "epoch": 0.14764111851192485, + "grad_norm": 0.6805937862926167, + "learning_rate": 1.9283052172016566e-05, + "loss": 1.0484, + "step": 2405 + }, + { + "epoch": 0.14770250775039134, + "grad_norm": 0.6186736798148632, + "learning_rate": 1.928231268214302e-05, + "loss": 1.0218, + "step": 2406 + }, + { + "epoch": 0.14776389698885786, + "grad_norm": 0.6807421076699329, + "learning_rate": 1.9281572825290003e-05, + "loss": 1.0627, + "step": 2407 + }, + { + "epoch": 0.14782528622732435, + "grad_norm": 0.6399102266088456, + "learning_rate": 1.9280832601486774e-05, + "loss": 1.0095, + "step": 2408 + }, + { + "epoch": 0.14788667546579085, + "grad_norm": 0.6498464381597284, + "learning_rate": 1.9280092010762597e-05, + "loss": 1.0042, + "step": 2409 + }, + { + "epoch": 0.14794806470425734, + "grad_norm": 0.6071735452217789, + "learning_rate": 1.9279351053146747e-05, + "loss": 0.7962, + "step": 2410 + }, + { + "epoch": 0.14800945394272383, + "grad_norm": 0.7047233875994636, + "learning_rate": 1.927860972866852e-05, + "loss": 1.0316, + "step": 2411 + }, + { + "epoch": 0.14807084318119035, + "grad_norm": 0.702765874880503, + "learning_rate": 1.9277868037357222e-05, + "loss": 1.0734, + "step": 2412 + }, + { + "epoch": 0.14813223241965684, + "grad_norm": 0.6468098960655514, + "learning_rate": 1.9277125979242184e-05, + "loss": 1.0186, + "step": 2413 + }, + { + "epoch": 0.14819362165812333, + "grad_norm": 0.6651082004558513, + "learning_rate": 1.9276383554352734e-05, + "loss": 1.0363, + "step": 2414 + }, + { + "epoch": 0.14825501089658982, + "grad_norm": 0.6579135946163679, + "learning_rate": 1.9275640762718232e-05, + "loss": 1.0669, + "step": 2415 + }, + { + "epoch": 0.14831640013505631, + "grad_norm": 0.6126934713698816, + "learning_rate": 1.927489760436804e-05, + "loss": 1.0093, + "step": 2416 + }, + { + "epoch": 0.14837778937352283, + "grad_norm": 0.6412259285551705, + "learning_rate": 1.927415407933154e-05, + "loss": 0.9936, + "step": 2417 + }, + { + "epoch": 0.14843917861198933, + "grad_norm": 0.6730368884938452, + "learning_rate": 1.9273410187638125e-05, + "loss": 1.0217, + "step": 2418 + }, + { + "epoch": 0.14850056785045582, + "grad_norm": 0.6693668370734419, + "learning_rate": 1.927266592931721e-05, + "loss": 1.0687, + "step": 2419 + }, + { + "epoch": 0.1485619570889223, + "grad_norm": 0.650047908052238, + "learning_rate": 1.927192130439822e-05, + "loss": 1.0753, + "step": 2420 + }, + { + "epoch": 0.1486233463273888, + "grad_norm": 0.6269173578773531, + "learning_rate": 1.9271176312910587e-05, + "loss": 0.9929, + "step": 2421 + }, + { + "epoch": 0.14868473556585532, + "grad_norm": 0.6356216507367236, + "learning_rate": 1.927043095488377e-05, + "loss": 1.0376, + "step": 2422 + }, + { + "epoch": 0.1487461248043218, + "grad_norm": 0.6401202461879223, + "learning_rate": 1.9269685230347234e-05, + "loss": 1.0056, + "step": 2423 + }, + { + "epoch": 0.1488075140427883, + "grad_norm": 0.6346389015477599, + "learning_rate": 1.9268939139330463e-05, + "loss": 1.0297, + "step": 2424 + }, + { + "epoch": 0.1488689032812548, + "grad_norm": 0.6377432624279178, + "learning_rate": 1.9268192681862957e-05, + "loss": 1.0695, + "step": 2425 + }, + { + "epoch": 0.14893029251972129, + "grad_norm": 0.6372496416904702, + "learning_rate": 1.9267445857974225e-05, + "loss": 1.0726, + "step": 2426 + }, + { + "epoch": 0.14899168175818778, + "grad_norm": 0.6189406978440664, + "learning_rate": 1.926669866769379e-05, + "loss": 0.9593, + "step": 2427 + }, + { + "epoch": 0.1490530709966543, + "grad_norm": 0.611720740433777, + "learning_rate": 1.9265951111051194e-05, + "loss": 1.0339, + "step": 2428 + }, + { + "epoch": 0.1491144602351208, + "grad_norm": 0.6310598775839716, + "learning_rate": 1.9265203188075997e-05, + "loss": 1.0141, + "step": 2429 + }, + { + "epoch": 0.14917584947358728, + "grad_norm": 0.6279817005719708, + "learning_rate": 1.926445489879776e-05, + "loss": 1.0343, + "step": 2430 + }, + { + "epoch": 0.14923723871205377, + "grad_norm": 0.696365619127072, + "learning_rate": 1.9263706243246073e-05, + "loss": 1.0848, + "step": 2431 + }, + { + "epoch": 0.14929862795052026, + "grad_norm": 0.6195660700914934, + "learning_rate": 1.926295722145053e-05, + "loss": 1.0277, + "step": 2432 + }, + { + "epoch": 0.14936001718898678, + "grad_norm": 0.5911753997530943, + "learning_rate": 1.9262207833440748e-05, + "loss": 0.9712, + "step": 2433 + }, + { + "epoch": 0.14942140642745327, + "grad_norm": 0.6779061873220399, + "learning_rate": 1.9261458079246353e-05, + "loss": 1.0901, + "step": 2434 + }, + { + "epoch": 0.14948279566591977, + "grad_norm": 0.6927854000759354, + "learning_rate": 1.9260707958896986e-05, + "loss": 1.0803, + "step": 2435 + }, + { + "epoch": 0.14954418490438626, + "grad_norm": 0.6333155131170419, + "learning_rate": 1.9259957472422304e-05, + "loss": 1.029, + "step": 2436 + }, + { + "epoch": 0.14960557414285275, + "grad_norm": 0.6974510809706622, + "learning_rate": 1.925920661985198e-05, + "loss": 1.0581, + "step": 2437 + }, + { + "epoch": 0.14966696338131927, + "grad_norm": 0.6701319884929049, + "learning_rate": 1.925845540121569e-05, + "loss": 1.0283, + "step": 2438 + }, + { + "epoch": 0.14972835261978576, + "grad_norm": 0.6743968706001552, + "learning_rate": 1.9257703816543144e-05, + "loss": 1.0703, + "step": 2439 + }, + { + "epoch": 0.14978974185825225, + "grad_norm": 0.6425737419616216, + "learning_rate": 1.9256951865864053e-05, + "loss": 1.0446, + "step": 2440 + }, + { + "epoch": 0.14985113109671874, + "grad_norm": 0.6484724514688185, + "learning_rate": 1.9256199549208144e-05, + "loss": 1.0528, + "step": 2441 + }, + { + "epoch": 0.14991252033518523, + "grad_norm": 0.6547239539464281, + "learning_rate": 1.9255446866605163e-05, + "loss": 1.0228, + "step": 2442 + }, + { + "epoch": 0.14997390957365173, + "grad_norm": 0.6637224570656284, + "learning_rate": 1.9254693818084866e-05, + "loss": 1.0169, + "step": 2443 + }, + { + "epoch": 0.15003529881211825, + "grad_norm": 0.6249180008774116, + "learning_rate": 1.9253940403677022e-05, + "loss": 1.0343, + "step": 2444 + }, + { + "epoch": 0.15009668805058474, + "grad_norm": 0.6562338172204573, + "learning_rate": 1.925318662341142e-05, + "loss": 1.04, + "step": 2445 + }, + { + "epoch": 0.15015807728905123, + "grad_norm": 0.6199174354095517, + "learning_rate": 1.9252432477317865e-05, + "loss": 1.0153, + "step": 2446 + }, + { + "epoch": 0.15021946652751772, + "grad_norm": 0.6360506857566449, + "learning_rate": 1.9251677965426165e-05, + "loss": 1.0266, + "step": 2447 + }, + { + "epoch": 0.1502808557659842, + "grad_norm": 0.6214418987374133, + "learning_rate": 1.9250923087766154e-05, + "loss": 1.0479, + "step": 2448 + }, + { + "epoch": 0.15034224500445073, + "grad_norm": 0.6115725352946305, + "learning_rate": 1.925016784436768e-05, + "loss": 0.9672, + "step": 2449 + }, + { + "epoch": 0.15040363424291722, + "grad_norm": 0.6731278917408156, + "learning_rate": 1.924941223526059e-05, + "loss": 1.073, + "step": 2450 + }, + { + "epoch": 0.15046502348138371, + "grad_norm": 0.6244920230771589, + "learning_rate": 1.924865626047477e-05, + "loss": 1.0052, + "step": 2451 + }, + { + "epoch": 0.1505264127198502, + "grad_norm": 0.6445673677105549, + "learning_rate": 1.9247899920040106e-05, + "loss": 1.0543, + "step": 2452 + }, + { + "epoch": 0.1505878019583167, + "grad_norm": 0.5764353963692432, + "learning_rate": 1.924714321398649e-05, + "loss": 0.9867, + "step": 2453 + }, + { + "epoch": 0.15064919119678322, + "grad_norm": 0.6474909568729634, + "learning_rate": 1.924638614234385e-05, + "loss": 1.0385, + "step": 2454 + }, + { + "epoch": 0.1507105804352497, + "grad_norm": 0.6189734309957735, + "learning_rate": 1.9245628705142115e-05, + "loss": 1.0215, + "step": 2455 + }, + { + "epoch": 0.1507719696737162, + "grad_norm": 0.62086384817658, + "learning_rate": 1.9244870902411223e-05, + "loss": 0.9961, + "step": 2456 + }, + { + "epoch": 0.1508333589121827, + "grad_norm": 0.6300865746605275, + "learning_rate": 1.9244112734181142e-05, + "loss": 1.0345, + "step": 2457 + }, + { + "epoch": 0.15089474815064918, + "grad_norm": 0.7140649758420746, + "learning_rate": 1.924335420048184e-05, + "loss": 1.0595, + "step": 2458 + }, + { + "epoch": 0.15095613738911567, + "grad_norm": 0.6206539497349078, + "learning_rate": 1.9242595301343315e-05, + "loss": 0.9936, + "step": 2459 + }, + { + "epoch": 0.1510175266275822, + "grad_norm": 0.6489424216029159, + "learning_rate": 1.924183603679556e-05, + "loss": 1.0525, + "step": 2460 + }, + { + "epoch": 0.15107891586604869, + "grad_norm": 0.6399027467719576, + "learning_rate": 1.92410764068686e-05, + "loss": 1.038, + "step": 2461 + }, + { + "epoch": 0.15114030510451518, + "grad_norm": 0.6889756589934453, + "learning_rate": 1.9240316411592465e-05, + "loss": 1.0556, + "step": 2462 + }, + { + "epoch": 0.15120169434298167, + "grad_norm": 0.6368540484494133, + "learning_rate": 1.9239556050997202e-05, + "loss": 1.0219, + "step": 2463 + }, + { + "epoch": 0.15126308358144816, + "grad_norm": 0.6447937798047026, + "learning_rate": 1.9238795325112867e-05, + "loss": 1.0635, + "step": 2464 + }, + { + "epoch": 0.15132447281991468, + "grad_norm": 0.6660321689784777, + "learning_rate": 1.9238034233969546e-05, + "loss": 1.0637, + "step": 2465 + }, + { + "epoch": 0.15138586205838117, + "grad_norm": 0.6222145929732695, + "learning_rate": 1.9237272777597323e-05, + "loss": 1.0212, + "step": 2466 + }, + { + "epoch": 0.15144725129684766, + "grad_norm": 0.6159183895422791, + "learning_rate": 1.92365109560263e-05, + "loss": 0.9929, + "step": 2467 + }, + { + "epoch": 0.15150864053531415, + "grad_norm": 0.6127214921332468, + "learning_rate": 1.92357487692866e-05, + "loss": 1.0726, + "step": 2468 + }, + { + "epoch": 0.15157002977378065, + "grad_norm": 0.5963466436248287, + "learning_rate": 1.9234986217408353e-05, + "loss": 0.9471, + "step": 2469 + }, + { + "epoch": 0.15163141901224717, + "grad_norm": 0.6546875693950513, + "learning_rate": 1.923422330042171e-05, + "loss": 1.0718, + "step": 2470 + }, + { + "epoch": 0.15169280825071366, + "grad_norm": 0.6193969567033092, + "learning_rate": 1.9233460018356832e-05, + "loss": 0.9844, + "step": 2471 + }, + { + "epoch": 0.15175419748918015, + "grad_norm": 0.6027826921015089, + "learning_rate": 1.9232696371243894e-05, + "loss": 1.0296, + "step": 2472 + }, + { + "epoch": 0.15181558672764664, + "grad_norm": 0.6559732893515976, + "learning_rate": 1.923193235911309e-05, + "loss": 1.0277, + "step": 2473 + }, + { + "epoch": 0.15187697596611313, + "grad_norm": 0.6244244633910031, + "learning_rate": 1.9231167981994626e-05, + "loss": 1.0233, + "step": 2474 + }, + { + "epoch": 0.15193836520457965, + "grad_norm": 0.6283498213465613, + "learning_rate": 1.9230403239918714e-05, + "loss": 1.0032, + "step": 2475 + }, + { + "epoch": 0.15199975444304614, + "grad_norm": 0.5762757687926916, + "learning_rate": 1.9229638132915604e-05, + "loss": 1.0073, + "step": 2476 + }, + { + "epoch": 0.15206114368151263, + "grad_norm": 0.6780632947049265, + "learning_rate": 1.9228872661015528e-05, + "loss": 1.0743, + "step": 2477 + }, + { + "epoch": 0.15212253291997913, + "grad_norm": 0.6696270739123714, + "learning_rate": 1.9228106824248757e-05, + "loss": 1.0312, + "step": 2478 + }, + { + "epoch": 0.15218392215844562, + "grad_norm": 0.58305788625824, + "learning_rate": 1.9227340622645565e-05, + "loss": 1.0281, + "step": 2479 + }, + { + "epoch": 0.1522453113969121, + "grad_norm": 0.624255556481392, + "learning_rate": 1.922657405623625e-05, + "loss": 0.9879, + "step": 2480 + }, + { + "epoch": 0.15230670063537863, + "grad_norm": 0.6281130763567945, + "learning_rate": 1.9225807125051117e-05, + "loss": 1.017, + "step": 2481 + }, + { + "epoch": 0.15236808987384512, + "grad_norm": 0.6907080777597226, + "learning_rate": 1.922503982912048e-05, + "loss": 1.0239, + "step": 2482 + }, + { + "epoch": 0.1524294791123116, + "grad_norm": 0.6373765629523243, + "learning_rate": 1.9224272168474685e-05, + "loss": 1.0071, + "step": 2483 + }, + { + "epoch": 0.1524908683507781, + "grad_norm": 0.7103134672994211, + "learning_rate": 1.9223504143144076e-05, + "loss": 1.1042, + "step": 2484 + }, + { + "epoch": 0.1525522575892446, + "grad_norm": 0.621732585583175, + "learning_rate": 1.9222735753159017e-05, + "loss": 1.0349, + "step": 2485 + }, + { + "epoch": 0.1526136468277111, + "grad_norm": 0.6084248642846694, + "learning_rate": 1.9221966998549886e-05, + "loss": 1.0108, + "step": 2486 + }, + { + "epoch": 0.1526750360661776, + "grad_norm": 0.6483614950031915, + "learning_rate": 1.9221197879347078e-05, + "loss": 1.0347, + "step": 2487 + }, + { + "epoch": 0.1527364253046441, + "grad_norm": 0.5810643062380396, + "learning_rate": 1.9220428395580998e-05, + "loss": 0.9835, + "step": 2488 + }, + { + "epoch": 0.1527978145431106, + "grad_norm": 0.631647701171471, + "learning_rate": 1.921965854728207e-05, + "loss": 1.0657, + "step": 2489 + }, + { + "epoch": 0.15285920378157708, + "grad_norm": 0.6474445794446856, + "learning_rate": 1.9218888334480728e-05, + "loss": 1.047, + "step": 2490 + }, + { + "epoch": 0.1529205930200436, + "grad_norm": 0.6436122482374141, + "learning_rate": 1.9218117757207425e-05, + "loss": 1.0411, + "step": 2491 + }, + { + "epoch": 0.1529819822585101, + "grad_norm": 0.619166672344626, + "learning_rate": 1.9217346815492624e-05, + "loss": 1.0719, + "step": 2492 + }, + { + "epoch": 0.15304337149697658, + "grad_norm": 0.7075599009696333, + "learning_rate": 1.9216575509366807e-05, + "loss": 1.0697, + "step": 2493 + }, + { + "epoch": 0.15310476073544307, + "grad_norm": 0.6446631130293198, + "learning_rate": 1.9215803838860467e-05, + "loss": 1.0392, + "step": 2494 + }, + { + "epoch": 0.15316614997390957, + "grad_norm": 0.6260718885155114, + "learning_rate": 1.921503180400411e-05, + "loss": 1.0084, + "step": 2495 + }, + { + "epoch": 0.15322753921237606, + "grad_norm": 0.6553232295425512, + "learning_rate": 1.921425940482826e-05, + "loss": 1.0567, + "step": 2496 + }, + { + "epoch": 0.15328892845084258, + "grad_norm": 0.7110263003530105, + "learning_rate": 1.9213486641363458e-05, + "loss": 1.065, + "step": 2497 + }, + { + "epoch": 0.15335031768930907, + "grad_norm": 0.6364807766488042, + "learning_rate": 1.921271351364025e-05, + "loss": 1.0064, + "step": 2498 + }, + { + "epoch": 0.15341170692777556, + "grad_norm": 0.6316025354924213, + "learning_rate": 1.92119400216892e-05, + "loss": 1.0203, + "step": 2499 + }, + { + "epoch": 0.15347309616624205, + "grad_norm": 0.6602294082849645, + "learning_rate": 1.9211166165540897e-05, + "loss": 1.057, + "step": 2500 + }, + { + "epoch": 0.15353448540470854, + "grad_norm": 0.6534693587288308, + "learning_rate": 1.9210391945225926e-05, + "loss": 1.0022, + "step": 2501 + }, + { + "epoch": 0.15359587464317506, + "grad_norm": 0.6570657329007846, + "learning_rate": 1.9209617360774907e-05, + "loss": 0.995, + "step": 2502 + }, + { + "epoch": 0.15365726388164155, + "grad_norm": 0.6163334799849097, + "learning_rate": 1.9208842412218453e-05, + "loss": 1.0305, + "step": 2503 + }, + { + "epoch": 0.15371865312010805, + "grad_norm": 0.6213258001467955, + "learning_rate": 1.9208067099587205e-05, + "loss": 1.0136, + "step": 2504 + }, + { + "epoch": 0.15378004235857454, + "grad_norm": 0.6463847489092447, + "learning_rate": 1.920729142291182e-05, + "loss": 1.0302, + "step": 2505 + }, + { + "epoch": 0.15384143159704103, + "grad_norm": 0.6731807717125613, + "learning_rate": 1.920651538222296e-05, + "loss": 1.078, + "step": 2506 + }, + { + "epoch": 0.15390282083550755, + "grad_norm": 0.6642765220029364, + "learning_rate": 1.9205738977551308e-05, + "loss": 1.0723, + "step": 2507 + }, + { + "epoch": 0.15396421007397404, + "grad_norm": 0.6393799926202192, + "learning_rate": 1.9204962208927557e-05, + "loss": 1.0507, + "step": 2508 + }, + { + "epoch": 0.15402559931244053, + "grad_norm": 0.8367627995336754, + "learning_rate": 1.9204185076382416e-05, + "loss": 1.0892, + "step": 2509 + }, + { + "epoch": 0.15408698855090702, + "grad_norm": 0.6295288930644514, + "learning_rate": 1.9203407579946612e-05, + "loss": 0.9659, + "step": 2510 + }, + { + "epoch": 0.15414837778937351, + "grad_norm": 0.615895791242721, + "learning_rate": 1.920262971965089e-05, + "loss": 1.0085, + "step": 2511 + }, + { + "epoch": 0.15420976702784003, + "grad_norm": 0.6386700861188382, + "learning_rate": 1.9201851495525986e-05, + "loss": 1.0399, + "step": 2512 + }, + { + "epoch": 0.15427115626630653, + "grad_norm": 0.6577068919823692, + "learning_rate": 1.9201072907602683e-05, + "loss": 1.0578, + "step": 2513 + }, + { + "epoch": 0.15433254550477302, + "grad_norm": 0.6112803966344444, + "learning_rate": 1.920029395591176e-05, + "loss": 0.9857, + "step": 2514 + }, + { + "epoch": 0.1543939347432395, + "grad_norm": 0.6660750154783138, + "learning_rate": 1.9199514640484003e-05, + "loss": 1.0115, + "step": 2515 + }, + { + "epoch": 0.154455323981706, + "grad_norm": 0.6273573204939784, + "learning_rate": 1.9198734961350234e-05, + "loss": 1.0114, + "step": 2516 + }, + { + "epoch": 0.1545167132201725, + "grad_norm": 0.6446281370806977, + "learning_rate": 1.9197954918541274e-05, + "loss": 1.0209, + "step": 2517 + }, + { + "epoch": 0.154578102458639, + "grad_norm": 0.6699496081150669, + "learning_rate": 1.9197174512087963e-05, + "loss": 1.0258, + "step": 2518 + }, + { + "epoch": 0.1546394916971055, + "grad_norm": 0.6800244142520903, + "learning_rate": 1.919639374202115e-05, + "loss": 1.0664, + "step": 2519 + }, + { + "epoch": 0.154700880935572, + "grad_norm": 0.6644577930518119, + "learning_rate": 1.9195612608371706e-05, + "loss": 1.0592, + "step": 2520 + }, + { + "epoch": 0.15476227017403849, + "grad_norm": 0.6379908590372313, + "learning_rate": 1.919483111117052e-05, + "loss": 1.0119, + "step": 2521 + }, + { + "epoch": 0.15482365941250498, + "grad_norm": 0.6000857472825883, + "learning_rate": 1.9194049250448476e-05, + "loss": 1.0241, + "step": 2522 + }, + { + "epoch": 0.1548850486509715, + "grad_norm": 0.6359924728161246, + "learning_rate": 1.9193267026236494e-05, + "loss": 1.0391, + "step": 2523 + }, + { + "epoch": 0.154946437889438, + "grad_norm": 0.6617950864261968, + "learning_rate": 1.91924844385655e-05, + "loss": 1.0347, + "step": 2524 + }, + { + "epoch": 0.15500782712790448, + "grad_norm": 0.6703366265295848, + "learning_rate": 1.919170148746643e-05, + "loss": 1.0368, + "step": 2525 + }, + { + "epoch": 0.15506921636637097, + "grad_norm": 0.6590705475596182, + "learning_rate": 1.919091817297024e-05, + "loss": 1.037, + "step": 2526 + }, + { + "epoch": 0.15513060560483746, + "grad_norm": 0.6341817616896445, + "learning_rate": 1.9190134495107896e-05, + "loss": 1.0345, + "step": 2527 + }, + { + "epoch": 0.15519199484330398, + "grad_norm": 0.6546096618641609, + "learning_rate": 1.9189350453910384e-05, + "loss": 1.0161, + "step": 2528 + }, + { + "epoch": 0.15525338408177047, + "grad_norm": 0.6941723291679252, + "learning_rate": 1.91885660494087e-05, + "loss": 1.0392, + "step": 2529 + }, + { + "epoch": 0.15531477332023697, + "grad_norm": 0.5907351675258543, + "learning_rate": 1.9187781281633858e-05, + "loss": 0.9611, + "step": 2530 + }, + { + "epoch": 0.15537616255870346, + "grad_norm": 0.6441608302808493, + "learning_rate": 1.918699615061688e-05, + "loss": 1.0162, + "step": 2531 + }, + { + "epoch": 0.15543755179716995, + "grad_norm": 0.6359108566480507, + "learning_rate": 1.918621065638881e-05, + "loss": 0.9916, + "step": 2532 + }, + { + "epoch": 0.15549894103563644, + "grad_norm": 0.5907911323695956, + "learning_rate": 1.9185424798980704e-05, + "loss": 1.0101, + "step": 2533 + }, + { + "epoch": 0.15556033027410296, + "grad_norm": 0.6957567391485657, + "learning_rate": 1.9184638578423624e-05, + "loss": 1.071, + "step": 2534 + }, + { + "epoch": 0.15562171951256945, + "grad_norm": 0.6326362898421383, + "learning_rate": 1.918385199474866e-05, + "loss": 0.9638, + "step": 2535 + }, + { + "epoch": 0.15568310875103594, + "grad_norm": 0.670801720434077, + "learning_rate": 1.9183065047986907e-05, + "loss": 1.0455, + "step": 2536 + }, + { + "epoch": 0.15574449798950243, + "grad_norm": 0.6733113516190349, + "learning_rate": 1.918227773816948e-05, + "loss": 1.059, + "step": 2537 + }, + { + "epoch": 0.15580588722796893, + "grad_norm": 0.6128712804764592, + "learning_rate": 1.9181490065327503e-05, + "loss": 1.0084, + "step": 2538 + }, + { + "epoch": 0.15586727646643544, + "grad_norm": 0.682865424102996, + "learning_rate": 1.9180702029492118e-05, + "loss": 1.0622, + "step": 2539 + }, + { + "epoch": 0.15592866570490194, + "grad_norm": 0.5747028664851611, + "learning_rate": 1.917991363069448e-05, + "loss": 0.9836, + "step": 2540 + }, + { + "epoch": 0.15599005494336843, + "grad_norm": 0.755414397662838, + "learning_rate": 1.9179124868965757e-05, + "loss": 1.02, + "step": 2541 + }, + { + "epoch": 0.15605144418183492, + "grad_norm": 0.6080501417879874, + "learning_rate": 1.9178335744337136e-05, + "loss": 1.0519, + "step": 2542 + }, + { + "epoch": 0.1561128334203014, + "grad_norm": 0.5969565766044141, + "learning_rate": 1.9177546256839814e-05, + "loss": 1.0135, + "step": 2543 + }, + { + "epoch": 0.15617422265876793, + "grad_norm": 0.598444880042539, + "learning_rate": 1.9176756406505e-05, + "loss": 1.037, + "step": 2544 + }, + { + "epoch": 0.15623561189723442, + "grad_norm": 0.6213073503632384, + "learning_rate": 1.917596619336393e-05, + "loss": 1.0155, + "step": 2545 + }, + { + "epoch": 0.1562970011357009, + "grad_norm": 0.6663129233902283, + "learning_rate": 1.9175175617447835e-05, + "loss": 1.0226, + "step": 2546 + }, + { + "epoch": 0.1563583903741674, + "grad_norm": 0.6606357777054739, + "learning_rate": 1.917438467878798e-05, + "loss": 1.0271, + "step": 2547 + }, + { + "epoch": 0.1564197796126339, + "grad_norm": 0.6088438987097228, + "learning_rate": 1.9173593377415628e-05, + "loss": 1.0163, + "step": 2548 + }, + { + "epoch": 0.1564811688511004, + "grad_norm": 0.5894715389721634, + "learning_rate": 1.9172801713362064e-05, + "loss": 0.9922, + "step": 2549 + }, + { + "epoch": 0.1565425580895669, + "grad_norm": 0.6001566041468879, + "learning_rate": 1.9172009686658592e-05, + "loss": 0.9733, + "step": 2550 + }, + { + "epoch": 0.1566039473280334, + "grad_norm": 0.6568133342091976, + "learning_rate": 1.917121729733652e-05, + "loss": 1.045, + "step": 2551 + }, + { + "epoch": 0.1566653365664999, + "grad_norm": 0.6650556057939729, + "learning_rate": 1.917042454542718e-05, + "loss": 1.0334, + "step": 2552 + }, + { + "epoch": 0.15672672580496638, + "grad_norm": 0.6338415615333536, + "learning_rate": 1.916963143096191e-05, + "loss": 1.0453, + "step": 2553 + }, + { + "epoch": 0.15678811504343287, + "grad_norm": 0.6619149688050149, + "learning_rate": 1.9168837953972063e-05, + "loss": 1.0938, + "step": 2554 + }, + { + "epoch": 0.1568495042818994, + "grad_norm": 0.6974505726002352, + "learning_rate": 1.9168044114489016e-05, + "loss": 1.0088, + "step": 2555 + }, + { + "epoch": 0.15691089352036589, + "grad_norm": 0.705299986459603, + "learning_rate": 1.916724991254415e-05, + "loss": 1.1002, + "step": 2556 + }, + { + "epoch": 0.15697228275883238, + "grad_norm": 0.670132466392121, + "learning_rate": 1.916645534816887e-05, + "loss": 1.0591, + "step": 2557 + }, + { + "epoch": 0.15703367199729887, + "grad_norm": 0.668817458723396, + "learning_rate": 1.9165660421394577e-05, + "loss": 1.0667, + "step": 2558 + }, + { + "epoch": 0.15709506123576536, + "grad_norm": 0.6593441038942227, + "learning_rate": 1.916486513225271e-05, + "loss": 0.993, + "step": 2559 + }, + { + "epoch": 0.15715645047423188, + "grad_norm": 0.6264871447521456, + "learning_rate": 1.916406948077471e-05, + "loss": 1.0015, + "step": 2560 + }, + { + "epoch": 0.15721783971269837, + "grad_norm": 0.637097069484657, + "learning_rate": 1.916327346699202e-05, + "loss": 0.9976, + "step": 2561 + }, + { + "epoch": 0.15727922895116486, + "grad_norm": 0.6523321799522896, + "learning_rate": 1.9162477090936134e-05, + "loss": 1.0619, + "step": 2562 + }, + { + "epoch": 0.15734061818963135, + "grad_norm": 0.6651026604889475, + "learning_rate": 1.916168035263852e-05, + "loss": 1.0231, + "step": 2563 + }, + { + "epoch": 0.15740200742809785, + "grad_norm": 0.6429583848162784, + "learning_rate": 1.9160883252130678e-05, + "loss": 1.07, + "step": 2564 + }, + { + "epoch": 0.15746339666656436, + "grad_norm": 0.6521050818115032, + "learning_rate": 1.9160085789444128e-05, + "loss": 1.0003, + "step": 2565 + }, + { + "epoch": 0.15752478590503086, + "grad_norm": 0.6314909949503192, + "learning_rate": 1.9159287964610393e-05, + "loss": 1.004, + "step": 2566 + }, + { + "epoch": 0.15758617514349735, + "grad_norm": 0.5983625969981717, + "learning_rate": 1.915848977766102e-05, + "loss": 0.9322, + "step": 2567 + }, + { + "epoch": 0.15764756438196384, + "grad_norm": 0.6025567192144956, + "learning_rate": 1.9157691228627562e-05, + "loss": 0.9786, + "step": 2568 + }, + { + "epoch": 0.15770895362043033, + "grad_norm": 0.632879206366799, + "learning_rate": 1.915689231754159e-05, + "loss": 1.0347, + "step": 2569 + }, + { + "epoch": 0.15777034285889682, + "grad_norm": 0.6501821272865458, + "learning_rate": 1.9156093044434693e-05, + "loss": 1.0499, + "step": 2570 + }, + { + "epoch": 0.15783173209736334, + "grad_norm": 0.635305543621918, + "learning_rate": 1.9155293409338464e-05, + "loss": 1.0515, + "step": 2571 + }, + { + "epoch": 0.15789312133582983, + "grad_norm": 0.647220373549265, + "learning_rate": 1.9154493412284524e-05, + "loss": 1.0599, + "step": 2572 + }, + { + "epoch": 0.15795451057429633, + "grad_norm": 0.6751889208264031, + "learning_rate": 1.9153693053304495e-05, + "loss": 1.0521, + "step": 2573 + }, + { + "epoch": 0.15801589981276282, + "grad_norm": 0.6430156188539489, + "learning_rate": 1.9152892332430026e-05, + "loss": 0.983, + "step": 2574 + }, + { + "epoch": 0.1580772890512293, + "grad_norm": 0.6433874635395674, + "learning_rate": 1.9152091249692764e-05, + "loss": 1.0694, + "step": 2575 + }, + { + "epoch": 0.15813867828969583, + "grad_norm": 0.7464205256144203, + "learning_rate": 1.915128980512439e-05, + "loss": 1.0275, + "step": 2576 + }, + { + "epoch": 0.15820006752816232, + "grad_norm": 0.6824171286551738, + "learning_rate": 1.9150487998756586e-05, + "loss": 1.0373, + "step": 2577 + }, + { + "epoch": 0.1582614567666288, + "grad_norm": 0.6401155542135448, + "learning_rate": 1.914968583062105e-05, + "loss": 1.0598, + "step": 2578 + }, + { + "epoch": 0.1583228460050953, + "grad_norm": 0.6639588267276691, + "learning_rate": 1.9148883300749496e-05, + "loss": 1.0315, + "step": 2579 + }, + { + "epoch": 0.1583842352435618, + "grad_norm": 0.6645909724116391, + "learning_rate": 1.9148080409173657e-05, + "loss": 1.0216, + "step": 2580 + }, + { + "epoch": 0.1584456244820283, + "grad_norm": 0.6682301326881921, + "learning_rate": 1.914727715592527e-05, + "loss": 1.0272, + "step": 2581 + }, + { + "epoch": 0.1585070137204948, + "grad_norm": 0.6545804509249772, + "learning_rate": 1.914647354103609e-05, + "loss": 1.0806, + "step": 2582 + }, + { + "epoch": 0.1585684029589613, + "grad_norm": 0.6075697549028327, + "learning_rate": 1.91456695645379e-05, + "loss": 1.0203, + "step": 2583 + }, + { + "epoch": 0.1586297921974278, + "grad_norm": 0.6213649050719771, + "learning_rate": 1.9144865226462473e-05, + "loss": 0.989, + "step": 2584 + }, + { + "epoch": 0.15869118143589428, + "grad_norm": 0.6116580709642113, + "learning_rate": 1.9144060526841614e-05, + "loss": 0.9649, + "step": 2585 + }, + { + "epoch": 0.15875257067436077, + "grad_norm": 0.6724068320889792, + "learning_rate": 1.9143255465707134e-05, + "loss": 1.104, + "step": 2586 + }, + { + "epoch": 0.1588139599128273, + "grad_norm": 0.6428622422296018, + "learning_rate": 1.9142450043090868e-05, + "loss": 1.0217, + "step": 2587 + }, + { + "epoch": 0.15887534915129378, + "grad_norm": 0.6873212045186732, + "learning_rate": 1.9141644259024654e-05, + "loss": 1.0292, + "step": 2588 + }, + { + "epoch": 0.15893673838976027, + "grad_norm": 0.6518719316436413, + "learning_rate": 1.9140838113540347e-05, + "loss": 1.0535, + "step": 2589 + }, + { + "epoch": 0.15899812762822677, + "grad_norm": 0.6575831056981831, + "learning_rate": 1.9140031606669823e-05, + "loss": 1.0518, + "step": 2590 + }, + { + "epoch": 0.15905951686669326, + "grad_norm": 0.6626655244862663, + "learning_rate": 1.9139224738444967e-05, + "loss": 1.0365, + "step": 2591 + }, + { + "epoch": 0.15912090610515978, + "grad_norm": 0.6258337248459328, + "learning_rate": 1.9138417508897672e-05, + "loss": 1.0193, + "step": 2592 + }, + { + "epoch": 0.15918229534362627, + "grad_norm": 0.6458415274517721, + "learning_rate": 1.9137609918059857e-05, + "loss": 0.997, + "step": 2593 + }, + { + "epoch": 0.15924368458209276, + "grad_norm": 0.6253870529495719, + "learning_rate": 1.9136801965963456e-05, + "loss": 0.994, + "step": 2594 + }, + { + "epoch": 0.15930507382055925, + "grad_norm": 0.6799250519104919, + "learning_rate": 1.9135993652640402e-05, + "loss": 1.0927, + "step": 2595 + }, + { + "epoch": 0.15936646305902574, + "grad_norm": 0.6246811152079061, + "learning_rate": 1.913518497812266e-05, + "loss": 0.9977, + "step": 2596 + }, + { + "epoch": 0.15942785229749226, + "grad_norm": 0.6483329862821977, + "learning_rate": 1.9134375942442192e-05, + "loss": 1.0209, + "step": 2597 + }, + { + "epoch": 0.15948924153595875, + "grad_norm": 0.6911496671146282, + "learning_rate": 1.9133566545630994e-05, + "loss": 1.1043, + "step": 2598 + }, + { + "epoch": 0.15955063077442524, + "grad_norm": 0.6932934754396348, + "learning_rate": 1.9132756787721058e-05, + "loss": 1.027, + "step": 2599 + }, + { + "epoch": 0.15961202001289174, + "grad_norm": 0.6411653254676326, + "learning_rate": 1.9131946668744402e-05, + "loss": 1.0326, + "step": 2600 + }, + { + "epoch": 0.15967340925135823, + "grad_norm": 0.677004619302338, + "learning_rate": 1.913113618873305e-05, + "loss": 1.083, + "step": 2601 + }, + { + "epoch": 0.15973479848982475, + "grad_norm": 0.664060106197235, + "learning_rate": 1.9130325347719053e-05, + "loss": 1.0253, + "step": 2602 + }, + { + "epoch": 0.15979618772829124, + "grad_norm": 0.6710524607074189, + "learning_rate": 1.912951414573446e-05, + "loss": 1.0616, + "step": 2603 + }, + { + "epoch": 0.15985757696675773, + "grad_norm": 0.6458877233474231, + "learning_rate": 1.9128702582811344e-05, + "loss": 1.0155, + "step": 2604 + }, + { + "epoch": 0.15991896620522422, + "grad_norm": 0.6316446363787053, + "learning_rate": 1.912789065898179e-05, + "loss": 0.9613, + "step": 2605 + }, + { + "epoch": 0.1599803554436907, + "grad_norm": 0.6607074613710066, + "learning_rate": 1.91270783742779e-05, + "loss": 1.0491, + "step": 2606 + }, + { + "epoch": 0.1600417446821572, + "grad_norm": 0.6228842923539727, + "learning_rate": 1.912626572873179e-05, + "loss": 0.9999, + "step": 2607 + }, + { + "epoch": 0.16010313392062372, + "grad_norm": 0.5696852508748973, + "learning_rate": 1.912545272237558e-05, + "loss": 0.9528, + "step": 2608 + }, + { + "epoch": 0.16016452315909022, + "grad_norm": 0.6164658382806788, + "learning_rate": 1.912463935524142e-05, + "loss": 0.9752, + "step": 2609 + }, + { + "epoch": 0.1602259123975567, + "grad_norm": 0.636880163855388, + "learning_rate": 1.9123825627361468e-05, + "loss": 1.0432, + "step": 2610 + }, + { + "epoch": 0.1602873016360232, + "grad_norm": 0.6480581353817911, + "learning_rate": 1.9123011538767886e-05, + "loss": 1.0229, + "step": 2611 + }, + { + "epoch": 0.1603486908744897, + "grad_norm": 0.6752186974649553, + "learning_rate": 1.9122197089492866e-05, + "loss": 0.9975, + "step": 2612 + }, + { + "epoch": 0.1604100801129562, + "grad_norm": 0.6836405734753412, + "learning_rate": 1.912138227956861e-05, + "loss": 1.0696, + "step": 2613 + }, + { + "epoch": 0.1604714693514227, + "grad_norm": 0.6207842146995335, + "learning_rate": 1.912056710902732e-05, + "loss": 1.0003, + "step": 2614 + }, + { + "epoch": 0.1605328585898892, + "grad_norm": 0.673842938545317, + "learning_rate": 1.9119751577901237e-05, + "loss": 1.0279, + "step": 2615 + }, + { + "epoch": 0.16059424782835569, + "grad_norm": 0.6707448551722393, + "learning_rate": 1.9118935686222597e-05, + "loss": 1.0497, + "step": 2616 + }, + { + "epoch": 0.16065563706682218, + "grad_norm": 0.6525359362542443, + "learning_rate": 1.9118119434023658e-05, + "loss": 1.0399, + "step": 2617 + }, + { + "epoch": 0.1607170263052887, + "grad_norm": 0.6543349081336465, + "learning_rate": 1.911730282133669e-05, + "loss": 1.0176, + "step": 2618 + }, + { + "epoch": 0.1607784155437552, + "grad_norm": 0.6930483842723919, + "learning_rate": 1.911648584819398e-05, + "loss": 1.0853, + "step": 2619 + }, + { + "epoch": 0.16083980478222168, + "grad_norm": 0.630975211975196, + "learning_rate": 1.9115668514627826e-05, + "loss": 1.0335, + "step": 2620 + }, + { + "epoch": 0.16090119402068817, + "grad_norm": 0.6686247436878457, + "learning_rate": 1.911485082067054e-05, + "loss": 1.0553, + "step": 2621 + }, + { + "epoch": 0.16096258325915466, + "grad_norm": 0.6841310163415428, + "learning_rate": 1.9114032766354453e-05, + "loss": 1.0714, + "step": 2622 + }, + { + "epoch": 0.16102397249762115, + "grad_norm": 0.6498528394322276, + "learning_rate": 1.9113214351711905e-05, + "loss": 1.0444, + "step": 2623 + }, + { + "epoch": 0.16108536173608767, + "grad_norm": 0.6948853601096813, + "learning_rate": 1.9112395576775254e-05, + "loss": 1.0072, + "step": 2624 + }, + { + "epoch": 0.16114675097455416, + "grad_norm": 0.6473665422957088, + "learning_rate": 1.9111576441576866e-05, + "loss": 1.0012, + "step": 2625 + }, + { + "epoch": 0.16120814021302066, + "grad_norm": 0.6456688611210007, + "learning_rate": 1.9110756946149134e-05, + "loss": 1.0675, + "step": 2626 + }, + { + "epoch": 0.16126952945148715, + "grad_norm": 0.6862238030248197, + "learning_rate": 1.910993709052445e-05, + "loss": 1.0686, + "step": 2627 + }, + { + "epoch": 0.16133091868995364, + "grad_norm": 0.638520730708681, + "learning_rate": 1.9109116874735228e-05, + "loss": 1.0322, + "step": 2628 + }, + { + "epoch": 0.16139230792842016, + "grad_norm": 0.6285527612365349, + "learning_rate": 1.9108296298813898e-05, + "loss": 1.0173, + "step": 2629 + }, + { + "epoch": 0.16145369716688665, + "grad_norm": 0.6105513651244476, + "learning_rate": 1.91074753627929e-05, + "loss": 1.046, + "step": 2630 + }, + { + "epoch": 0.16151508640535314, + "grad_norm": 0.6247741645698296, + "learning_rate": 1.9106654066704694e-05, + "loss": 1.0388, + "step": 2631 + }, + { + "epoch": 0.16157647564381963, + "grad_norm": 0.6164910071149512, + "learning_rate": 1.9105832410581742e-05, + "loss": 0.9912, + "step": 2632 + }, + { + "epoch": 0.16163786488228613, + "grad_norm": 0.5989514330212877, + "learning_rate": 1.9105010394456537e-05, + "loss": 0.9794, + "step": 2633 + }, + { + "epoch": 0.16169925412075264, + "grad_norm": 0.6073508303792224, + "learning_rate": 1.910418801836157e-05, + "loss": 1.0148, + "step": 2634 + }, + { + "epoch": 0.16176064335921914, + "grad_norm": 0.6026435193516634, + "learning_rate": 1.910336528232936e-05, + "loss": 1.0175, + "step": 2635 + }, + { + "epoch": 0.16182203259768563, + "grad_norm": 0.6021418157183861, + "learning_rate": 1.9102542186392433e-05, + "loss": 0.9969, + "step": 2636 + }, + { + "epoch": 0.16188342183615212, + "grad_norm": 0.6438907071284953, + "learning_rate": 1.910171873058333e-05, + "loss": 1.0685, + "step": 2637 + }, + { + "epoch": 0.1619448110746186, + "grad_norm": 0.6973175510249269, + "learning_rate": 1.9100894914934607e-05, + "loss": 1.0453, + "step": 2638 + }, + { + "epoch": 0.1620062003130851, + "grad_norm": 0.6008796270823658, + "learning_rate": 1.9100070739478833e-05, + "loss": 0.9928, + "step": 2639 + }, + { + "epoch": 0.16206758955155162, + "grad_norm": 0.638719327346818, + "learning_rate": 1.909924620424859e-05, + "loss": 1.035, + "step": 2640 + }, + { + "epoch": 0.1621289787900181, + "grad_norm": 0.6230888757721719, + "learning_rate": 1.9098421309276477e-05, + "loss": 1.0262, + "step": 2641 + }, + { + "epoch": 0.1621903680284846, + "grad_norm": 0.6517712384034873, + "learning_rate": 1.909759605459511e-05, + "loss": 1.0255, + "step": 2642 + }, + { + "epoch": 0.1622517572669511, + "grad_norm": 0.6892163490191484, + "learning_rate": 1.9096770440237112e-05, + "loss": 1.0674, + "step": 2643 + }, + { + "epoch": 0.1623131465054176, + "grad_norm": 0.6093141073207575, + "learning_rate": 1.909594446623513e-05, + "loss": 0.9831, + "step": 2644 + }, + { + "epoch": 0.1623745357438841, + "grad_norm": 0.6470980279871287, + "learning_rate": 1.909511813262181e-05, + "loss": 1.0534, + "step": 2645 + }, + { + "epoch": 0.1624359249823506, + "grad_norm": 0.6716672192100945, + "learning_rate": 1.9094291439429827e-05, + "loss": 1.0271, + "step": 2646 + }, + { + "epoch": 0.1624973142208171, + "grad_norm": 0.6511211968315581, + "learning_rate": 1.9093464386691866e-05, + "loss": 1.0672, + "step": 2647 + }, + { + "epoch": 0.16255870345928358, + "grad_norm": 0.6218827398230705, + "learning_rate": 1.9092636974440624e-05, + "loss": 0.9603, + "step": 2648 + }, + { + "epoch": 0.16262009269775007, + "grad_norm": 0.6868097999684738, + "learning_rate": 1.9091809202708805e-05, + "loss": 1.0294, + "step": 2649 + }, + { + "epoch": 0.1626814819362166, + "grad_norm": 0.6760373537157727, + "learning_rate": 1.909098107152915e-05, + "loss": 1.0074, + "step": 2650 + }, + { + "epoch": 0.16274287117468308, + "grad_norm": 0.641916359777576, + "learning_rate": 1.9090152580934383e-05, + "loss": 0.9676, + "step": 2651 + }, + { + "epoch": 0.16280426041314958, + "grad_norm": 0.5788424625610106, + "learning_rate": 1.9089323730957273e-05, + "loss": 0.9613, + "step": 2652 + }, + { + "epoch": 0.16286564965161607, + "grad_norm": 0.6793177067504148, + "learning_rate": 1.908849452163058e-05, + "loss": 1.07, + "step": 2653 + }, + { + "epoch": 0.16292703889008256, + "grad_norm": 0.6482660848903287, + "learning_rate": 1.9087664952987087e-05, + "loss": 1.0013, + "step": 2654 + }, + { + "epoch": 0.16298842812854908, + "grad_norm": 0.666191834693747, + "learning_rate": 1.90868350250596e-05, + "loss": 1.0074, + "step": 2655 + }, + { + "epoch": 0.16304981736701557, + "grad_norm": 0.6928866537915502, + "learning_rate": 1.9086004737880925e-05, + "loss": 1.0894, + "step": 2656 + }, + { + "epoch": 0.16311120660548206, + "grad_norm": 0.5964556990851881, + "learning_rate": 1.9085174091483882e-05, + "loss": 0.9646, + "step": 2657 + }, + { + "epoch": 0.16317259584394855, + "grad_norm": 0.6241057312316552, + "learning_rate": 1.9084343085901322e-05, + "loss": 0.9726, + "step": 2658 + }, + { + "epoch": 0.16323398508241505, + "grad_norm": 0.5942143694398221, + "learning_rate": 1.908351172116609e-05, + "loss": 0.98, + "step": 2659 + }, + { + "epoch": 0.16329537432088154, + "grad_norm": 0.6481225347189842, + "learning_rate": 1.9082679997311055e-05, + "loss": 0.9973, + "step": 2660 + }, + { + "epoch": 0.16335676355934806, + "grad_norm": 0.6602008341801867, + "learning_rate": 1.90818479143691e-05, + "loss": 1.0817, + "step": 2661 + }, + { + "epoch": 0.16341815279781455, + "grad_norm": 0.5936743896965656, + "learning_rate": 1.908101547237313e-05, + "loss": 0.9895, + "step": 2662 + }, + { + "epoch": 0.16347954203628104, + "grad_norm": 0.6892090464117184, + "learning_rate": 1.9080182671356052e-05, + "loss": 1.0836, + "step": 2663 + }, + { + "epoch": 0.16354093127474753, + "grad_norm": 0.6687305475927923, + "learning_rate": 1.9079349511350784e-05, + "loss": 1.0858, + "step": 2664 + }, + { + "epoch": 0.16360232051321402, + "grad_norm": 0.5996749387977044, + "learning_rate": 1.907851599239027e-05, + "loss": 1.055, + "step": 2665 + }, + { + "epoch": 0.16366370975168054, + "grad_norm": 0.6455731504461902, + "learning_rate": 1.9077682114507466e-05, + "loss": 1.0468, + "step": 2666 + }, + { + "epoch": 0.16372509899014703, + "grad_norm": 0.6082755154379443, + "learning_rate": 1.9076847877735336e-05, + "loss": 0.9871, + "step": 2667 + }, + { + "epoch": 0.16378648822861352, + "grad_norm": 0.6511165498960704, + "learning_rate": 1.907601328210686e-05, + "loss": 1.0087, + "step": 2668 + }, + { + "epoch": 0.16384787746708002, + "grad_norm": 0.6565147033428638, + "learning_rate": 1.907517832765504e-05, + "loss": 1.0262, + "step": 2669 + }, + { + "epoch": 0.1639092667055465, + "grad_norm": 0.592080905579595, + "learning_rate": 1.9074343014412885e-05, + "loss": 1.0519, + "step": 2670 + }, + { + "epoch": 0.16397065594401303, + "grad_norm": 0.6216404726227341, + "learning_rate": 1.9073507342413417e-05, + "loss": 1.0029, + "step": 2671 + }, + { + "epoch": 0.16403204518247952, + "grad_norm": 0.7130165224137147, + "learning_rate": 1.9072671311689675e-05, + "loss": 1.0789, + "step": 2672 + }, + { + "epoch": 0.164093434420946, + "grad_norm": 0.7087233414666838, + "learning_rate": 1.9071834922274707e-05, + "loss": 1.0724, + "step": 2673 + }, + { + "epoch": 0.1641548236594125, + "grad_norm": 0.5774311341634871, + "learning_rate": 1.907099817420159e-05, + "loss": 0.9844, + "step": 2674 + }, + { + "epoch": 0.164216212897879, + "grad_norm": 0.5916652763424907, + "learning_rate": 1.90701610675034e-05, + "loss": 0.9881, + "step": 2675 + }, + { + "epoch": 0.16427760213634549, + "grad_norm": 0.6515725439913017, + "learning_rate": 1.906932360221323e-05, + "loss": 1.0322, + "step": 2676 + }, + { + "epoch": 0.164338991374812, + "grad_norm": 0.650245141022926, + "learning_rate": 1.9068485778364194e-05, + "loss": 1.0291, + "step": 2677 + }, + { + "epoch": 0.1644003806132785, + "grad_norm": 0.6091424814766488, + "learning_rate": 1.9067647595989413e-05, + "loss": 1.02, + "step": 2678 + }, + { + "epoch": 0.164461769851745, + "grad_norm": 0.6512956102898417, + "learning_rate": 1.9066809055122024e-05, + "loss": 1.0169, + "step": 2679 + }, + { + "epoch": 0.16452315909021148, + "grad_norm": 0.6756437803228628, + "learning_rate": 1.906597015579518e-05, + "loss": 1.0594, + "step": 2680 + }, + { + "epoch": 0.16458454832867797, + "grad_norm": 0.6764504699851935, + "learning_rate": 1.906513089804205e-05, + "loss": 1.0146, + "step": 2681 + }, + { + "epoch": 0.1646459375671445, + "grad_norm": 0.6886529857272967, + "learning_rate": 1.906429128189581e-05, + "loss": 1.0485, + "step": 2682 + }, + { + "epoch": 0.16470732680561098, + "grad_norm": 0.6524561770939039, + "learning_rate": 1.906345130738966e-05, + "loss": 0.9662, + "step": 2683 + }, + { + "epoch": 0.16476871604407747, + "grad_norm": 0.6788360301587062, + "learning_rate": 1.90626109745568e-05, + "loss": 1.072, + "step": 2684 + }, + { + "epoch": 0.16483010528254396, + "grad_norm": 0.6398735571864369, + "learning_rate": 1.906177028343046e-05, + "loss": 0.9912, + "step": 2685 + }, + { + "epoch": 0.16489149452101046, + "grad_norm": 0.6305458633368571, + "learning_rate": 1.9060929234043875e-05, + "loss": 1.0208, + "step": 2686 + }, + { + "epoch": 0.16495288375947698, + "grad_norm": 0.7148890304456428, + "learning_rate": 1.90600878264303e-05, + "loss": 1.1249, + "step": 2687 + }, + { + "epoch": 0.16501427299794347, + "grad_norm": 0.7190069490275686, + "learning_rate": 1.905924606062299e-05, + "loss": 1.0679, + "step": 2688 + }, + { + "epoch": 0.16507566223640996, + "grad_norm": 0.6803270939312501, + "learning_rate": 1.9058403936655235e-05, + "loss": 1.0223, + "step": 2689 + }, + { + "epoch": 0.16513705147487645, + "grad_norm": 0.646321737673637, + "learning_rate": 1.905756145456032e-05, + "loss": 1.055, + "step": 2690 + }, + { + "epoch": 0.16519844071334294, + "grad_norm": 0.6779800592940897, + "learning_rate": 1.9056718614371563e-05, + "loss": 1.0213, + "step": 2691 + }, + { + "epoch": 0.16525982995180946, + "grad_norm": 0.6433953239432687, + "learning_rate": 1.905587541612228e-05, + "loss": 1.025, + "step": 2692 + }, + { + "epoch": 0.16532121919027595, + "grad_norm": 0.5915421999987988, + "learning_rate": 1.9055031859845802e-05, + "loss": 1.0191, + "step": 2693 + }, + { + "epoch": 0.16538260842874244, + "grad_norm": 0.6729225473942011, + "learning_rate": 1.9054187945575492e-05, + "loss": 1.0591, + "step": 2694 + }, + { + "epoch": 0.16544399766720894, + "grad_norm": 0.6138824688251583, + "learning_rate": 1.90533436733447e-05, + "loss": 0.9558, + "step": 2695 + }, + { + "epoch": 0.16550538690567543, + "grad_norm": 0.6719392182022292, + "learning_rate": 1.905249904318682e-05, + "loss": 1.023, + "step": 2696 + }, + { + "epoch": 0.16556677614414192, + "grad_norm": 0.6477402077657697, + "learning_rate": 1.905165405513523e-05, + "loss": 1.0203, + "step": 2697 + }, + { + "epoch": 0.16562816538260844, + "grad_norm": 0.5940984987696495, + "learning_rate": 1.905080870922335e-05, + "loss": 0.9956, + "step": 2698 + }, + { + "epoch": 0.16568955462107493, + "grad_norm": 0.6570943122995113, + "learning_rate": 1.904996300548459e-05, + "loss": 1.0405, + "step": 2699 + }, + { + "epoch": 0.16575094385954142, + "grad_norm": 0.6427192746220575, + "learning_rate": 1.9049116943952386e-05, + "loss": 1.0624, + "step": 2700 + }, + { + "epoch": 0.1658123330980079, + "grad_norm": 0.5964169243159367, + "learning_rate": 1.9048270524660197e-05, + "loss": 1.0077, + "step": 2701 + }, + { + "epoch": 0.1658737223364744, + "grad_norm": 0.6778296435972114, + "learning_rate": 1.904742374764148e-05, + "loss": 1.1101, + "step": 2702 + }, + { + "epoch": 0.16593511157494092, + "grad_norm": 0.5919462906665086, + "learning_rate": 1.904657661292971e-05, + "loss": 0.9677, + "step": 2703 + }, + { + "epoch": 0.16599650081340742, + "grad_norm": 0.7183146217533602, + "learning_rate": 1.9045729120558385e-05, + "loss": 1.061, + "step": 2704 + }, + { + "epoch": 0.1660578900518739, + "grad_norm": 0.6377887484118555, + "learning_rate": 1.9044881270561008e-05, + "loss": 1.0295, + "step": 2705 + }, + { + "epoch": 0.1661192792903404, + "grad_norm": 0.6234493329475599, + "learning_rate": 1.90440330629711e-05, + "loss": 1.0143, + "step": 2706 + }, + { + "epoch": 0.1661806685288069, + "grad_norm": 0.6355940792227911, + "learning_rate": 1.9043184497822192e-05, + "loss": 1.0309, + "step": 2707 + }, + { + "epoch": 0.1662420577672734, + "grad_norm": 0.589540777439389, + "learning_rate": 1.9042335575147834e-05, + "loss": 0.9845, + "step": 2708 + }, + { + "epoch": 0.1663034470057399, + "grad_norm": 0.663790874090039, + "learning_rate": 1.9041486294981588e-05, + "loss": 1.0211, + "step": 2709 + }, + { + "epoch": 0.1663648362442064, + "grad_norm": 0.6288168813938662, + "learning_rate": 1.9040636657357036e-05, + "loss": 1.0063, + "step": 2710 + }, + { + "epoch": 0.16642622548267288, + "grad_norm": 0.6835556485261773, + "learning_rate": 1.903978666230776e-05, + "loss": 1.009, + "step": 2711 + }, + { + "epoch": 0.16648761472113938, + "grad_norm": 0.6272234015023175, + "learning_rate": 1.903893630986737e-05, + "loss": 0.987, + "step": 2712 + }, + { + "epoch": 0.16654900395960587, + "grad_norm": 0.6602144402295818, + "learning_rate": 1.9038085600069486e-05, + "loss": 1.0341, + "step": 2713 + }, + { + "epoch": 0.1666103931980724, + "grad_norm": 0.6867726782239496, + "learning_rate": 1.9037234532947737e-05, + "loss": 1.0282, + "step": 2714 + }, + { + "epoch": 0.16667178243653888, + "grad_norm": 0.611507428276087, + "learning_rate": 1.9036383108535773e-05, + "loss": 0.998, + "step": 2715 + }, + { + "epoch": 0.16673317167500537, + "grad_norm": 0.5997598477605866, + "learning_rate": 1.9035531326867252e-05, + "loss": 0.9574, + "step": 2716 + }, + { + "epoch": 0.16679456091347186, + "grad_norm": 0.676345668403721, + "learning_rate": 1.9034679187975857e-05, + "loss": 1.0145, + "step": 2717 + }, + { + "epoch": 0.16685595015193835, + "grad_norm": 0.6277028593319885, + "learning_rate": 1.9033826691895273e-05, + "loss": 0.9654, + "step": 2718 + }, + { + "epoch": 0.16691733939040487, + "grad_norm": 0.656205647585148, + "learning_rate": 1.9032973838659198e-05, + "loss": 1.0208, + "step": 2719 + }, + { + "epoch": 0.16697872862887136, + "grad_norm": 0.6241766653883738, + "learning_rate": 1.903212062830136e-05, + "loss": 1.0145, + "step": 2720 + }, + { + "epoch": 0.16704011786733786, + "grad_norm": 0.6273049654904839, + "learning_rate": 1.9031267060855487e-05, + "loss": 0.9843, + "step": 2721 + }, + { + "epoch": 0.16710150710580435, + "grad_norm": 0.6170304864982159, + "learning_rate": 1.9030413136355322e-05, + "loss": 1.0134, + "step": 2722 + }, + { + "epoch": 0.16716289634427084, + "grad_norm": 0.6519113445862144, + "learning_rate": 1.9029558854834626e-05, + "loss": 1.0623, + "step": 2723 + }, + { + "epoch": 0.16722428558273736, + "grad_norm": 0.6506536953756434, + "learning_rate": 1.9028704216327177e-05, + "loss": 1.0132, + "step": 2724 + }, + { + "epoch": 0.16728567482120385, + "grad_norm": 0.6949709383134189, + "learning_rate": 1.9027849220866767e-05, + "loss": 1.092, + "step": 2725 + }, + { + "epoch": 0.16734706405967034, + "grad_norm": 0.6367357076519243, + "learning_rate": 1.9026993868487184e-05, + "loss": 1.0295, + "step": 2726 + }, + { + "epoch": 0.16740845329813683, + "grad_norm": 0.6663047416674142, + "learning_rate": 1.902613815922226e-05, + "loss": 1.1341, + "step": 2727 + }, + { + "epoch": 0.16746984253660332, + "grad_norm": 0.660030539469941, + "learning_rate": 1.9025282093105814e-05, + "loss": 1.0332, + "step": 2728 + }, + { + "epoch": 0.16753123177506982, + "grad_norm": 0.6402745120313829, + "learning_rate": 1.90244256701717e-05, + "loss": 1.0345, + "step": 2729 + }, + { + "epoch": 0.16759262101353634, + "grad_norm": 0.6122176326242627, + "learning_rate": 1.902356889045377e-05, + "loss": 0.9662, + "step": 2730 + }, + { + "epoch": 0.16765401025200283, + "grad_norm": 0.6492403735401746, + "learning_rate": 1.9022711753985904e-05, + "loss": 1.0367, + "step": 2731 + }, + { + "epoch": 0.16771539949046932, + "grad_norm": 0.6042194497193925, + "learning_rate": 1.9021854260801986e-05, + "loss": 1.0204, + "step": 2732 + }, + { + "epoch": 0.1677767887289358, + "grad_norm": 0.6058823115536844, + "learning_rate": 1.9020996410935915e-05, + "loss": 0.9991, + "step": 2733 + }, + { + "epoch": 0.1678381779674023, + "grad_norm": 0.6281307447369712, + "learning_rate": 1.902013820442161e-05, + "loss": 1.0202, + "step": 2734 + }, + { + "epoch": 0.16789956720586882, + "grad_norm": 0.5893575928861977, + "learning_rate": 1.9019279641292993e-05, + "loss": 1.0095, + "step": 2735 + }, + { + "epoch": 0.1679609564443353, + "grad_norm": 0.6523605448452005, + "learning_rate": 1.901842072158402e-05, + "loss": 1.0548, + "step": 2736 + }, + { + "epoch": 0.1680223456828018, + "grad_norm": 0.6498424343608917, + "learning_rate": 1.9017561445328638e-05, + "loss": 0.9997, + "step": 2737 + }, + { + "epoch": 0.1680837349212683, + "grad_norm": 0.6557356120026736, + "learning_rate": 1.9016701812560824e-05, + "loss": 1.029, + "step": 2738 + }, + { + "epoch": 0.1681451241597348, + "grad_norm": 0.6799091755758022, + "learning_rate": 1.901584182331456e-05, + "loss": 1.0663, + "step": 2739 + }, + { + "epoch": 0.1682065133982013, + "grad_norm": 0.6228759361511104, + "learning_rate": 1.9014981477623852e-05, + "loss": 0.9693, + "step": 2740 + }, + { + "epoch": 0.1682679026366678, + "grad_norm": 0.6018972559728284, + "learning_rate": 1.9014120775522712e-05, + "loss": 0.9875, + "step": 2741 + }, + { + "epoch": 0.1683292918751343, + "grad_norm": 0.6220006025375242, + "learning_rate": 1.901325971704516e-05, + "loss": 0.9933, + "step": 2742 + }, + { + "epoch": 0.16839068111360078, + "grad_norm": 0.5922527163664331, + "learning_rate": 1.901239830222525e-05, + "loss": 0.9666, + "step": 2743 + }, + { + "epoch": 0.16845207035206727, + "grad_norm": 0.6267904241332026, + "learning_rate": 1.9011536531097035e-05, + "loss": 0.995, + "step": 2744 + }, + { + "epoch": 0.1685134595905338, + "grad_norm": 0.6401495132849244, + "learning_rate": 1.901067440369458e-05, + "loss": 0.9853, + "step": 2745 + }, + { + "epoch": 0.16857484882900028, + "grad_norm": 0.7034652987173236, + "learning_rate": 1.9009811920051977e-05, + "loss": 1.0718, + "step": 2746 + }, + { + "epoch": 0.16863623806746678, + "grad_norm": 0.6047223248037474, + "learning_rate": 1.900894908020332e-05, + "loss": 0.9655, + "step": 2747 + }, + { + "epoch": 0.16869762730593327, + "grad_norm": 0.6669487046333815, + "learning_rate": 1.9008085884182722e-05, + "loss": 1.0444, + "step": 2748 + }, + { + "epoch": 0.16875901654439976, + "grad_norm": 0.627422586115118, + "learning_rate": 1.9007222332024308e-05, + "loss": 1.0021, + "step": 2749 + }, + { + "epoch": 0.16882040578286625, + "grad_norm": 0.6813256382777165, + "learning_rate": 1.9006358423762225e-05, + "loss": 1.0382, + "step": 2750 + }, + { + "epoch": 0.16888179502133277, + "grad_norm": 0.6011821269748924, + "learning_rate": 1.900549415943062e-05, + "loss": 1.03, + "step": 2751 + }, + { + "epoch": 0.16894318425979926, + "grad_norm": 0.6156563233213174, + "learning_rate": 1.900462953906367e-05, + "loss": 0.9879, + "step": 2752 + }, + { + "epoch": 0.16900457349826575, + "grad_norm": 0.722727609686364, + "learning_rate": 1.900376456269555e-05, + "loss": 1.1263, + "step": 2753 + }, + { + "epoch": 0.16906596273673224, + "grad_norm": 0.6518025360282289, + "learning_rate": 1.9002899230360467e-05, + "loss": 1.0441, + "step": 2754 + }, + { + "epoch": 0.16912735197519874, + "grad_norm": 0.6430283747402227, + "learning_rate": 1.9002033542092625e-05, + "loss": 1.0486, + "step": 2755 + }, + { + "epoch": 0.16918874121366526, + "grad_norm": 0.6991707037016683, + "learning_rate": 1.9001167497926248e-05, + "loss": 1.0828, + "step": 2756 + }, + { + "epoch": 0.16925013045213175, + "grad_norm": 0.6147391886396523, + "learning_rate": 1.900030109789558e-05, + "loss": 0.9957, + "step": 2757 + }, + { + "epoch": 0.16931151969059824, + "grad_norm": 0.6086067849766207, + "learning_rate": 1.899943434203487e-05, + "loss": 1.0091, + "step": 2758 + }, + { + "epoch": 0.16937290892906473, + "grad_norm": 0.6209787029425794, + "learning_rate": 1.8998567230378394e-05, + "loss": 0.9671, + "step": 2759 + }, + { + "epoch": 0.16943429816753122, + "grad_norm": 0.6376668163090708, + "learning_rate": 1.8997699762960424e-05, + "loss": 1.0304, + "step": 2760 + }, + { + "epoch": 0.16949568740599774, + "grad_norm": 0.640319341838031, + "learning_rate": 1.8996831939815258e-05, + "loss": 1.0065, + "step": 2761 + }, + { + "epoch": 0.16955707664446423, + "grad_norm": 0.612179779640302, + "learning_rate": 1.899596376097721e-05, + "loss": 1.0042, + "step": 2762 + }, + { + "epoch": 0.16961846588293072, + "grad_norm": 0.6837198857936965, + "learning_rate": 1.8995095226480598e-05, + "loss": 1.057, + "step": 2763 + }, + { + "epoch": 0.16967985512139722, + "grad_norm": 0.642034268391028, + "learning_rate": 1.899422633635976e-05, + "loss": 1.0492, + "step": 2764 + }, + { + "epoch": 0.1697412443598637, + "grad_norm": 0.6577718006020382, + "learning_rate": 1.899335709064906e-05, + "loss": 1.0618, + "step": 2765 + }, + { + "epoch": 0.1698026335983302, + "grad_norm": 0.6363740700146967, + "learning_rate": 1.8992487489382846e-05, + "loss": 1.0262, + "step": 2766 + }, + { + "epoch": 0.16986402283679672, + "grad_norm": 0.7150342591819387, + "learning_rate": 1.899161753259551e-05, + "loss": 1.1063, + "step": 2767 + }, + { + "epoch": 0.1699254120752632, + "grad_norm": 0.6302400394196856, + "learning_rate": 1.8990747220321438e-05, + "loss": 0.9971, + "step": 2768 + }, + { + "epoch": 0.1699868013137297, + "grad_norm": 0.6333516825688452, + "learning_rate": 1.8989876552595045e-05, + "loss": 1.0406, + "step": 2769 + }, + { + "epoch": 0.1700481905521962, + "grad_norm": 0.6217624014598755, + "learning_rate": 1.8989005529450752e-05, + "loss": 1.0154, + "step": 2770 + }, + { + "epoch": 0.17010957979066268, + "grad_norm": 0.680202953970514, + "learning_rate": 1.8988134150922994e-05, + "loss": 1.022, + "step": 2771 + }, + { + "epoch": 0.1701709690291292, + "grad_norm": 0.7322670190250878, + "learning_rate": 1.898726241704622e-05, + "loss": 0.7656, + "step": 2772 + }, + { + "epoch": 0.1702323582675957, + "grad_norm": 0.7469897187081539, + "learning_rate": 1.8986390327854894e-05, + "loss": 1.0376, + "step": 2773 + }, + { + "epoch": 0.1702937475060622, + "grad_norm": 0.6053833461389735, + "learning_rate": 1.8985517883383498e-05, + "loss": 0.758, + "step": 2774 + }, + { + "epoch": 0.17035513674452868, + "grad_norm": 0.6869320872577005, + "learning_rate": 1.898464508366652e-05, + "loss": 1.0172, + "step": 2775 + }, + { + "epoch": 0.17041652598299517, + "grad_norm": 0.665502352570566, + "learning_rate": 1.8983771928738474e-05, + "loss": 1.0587, + "step": 2776 + }, + { + "epoch": 0.1704779152214617, + "grad_norm": 0.6366705486686193, + "learning_rate": 1.898289841863387e-05, + "loss": 0.9724, + "step": 2777 + }, + { + "epoch": 0.17053930445992818, + "grad_norm": 0.6626507046369352, + "learning_rate": 1.8982024553387246e-05, + "loss": 0.8137, + "step": 2778 + }, + { + "epoch": 0.17060069369839467, + "grad_norm": 0.6426039793217395, + "learning_rate": 1.8981150333033155e-05, + "loss": 1.0476, + "step": 2779 + }, + { + "epoch": 0.17066208293686116, + "grad_norm": 0.6413995684403894, + "learning_rate": 1.8980275757606157e-05, + "loss": 1.0196, + "step": 2780 + }, + { + "epoch": 0.17072347217532766, + "grad_norm": 0.6574805034140515, + "learning_rate": 1.897940082714083e-05, + "loss": 1.0223, + "step": 2781 + }, + { + "epoch": 0.17078486141379418, + "grad_norm": 0.6445898571021179, + "learning_rate": 1.897852554167176e-05, + "loss": 1.0001, + "step": 2782 + }, + { + "epoch": 0.17084625065226067, + "grad_norm": 0.6342377071112159, + "learning_rate": 1.8977649901233556e-05, + "loss": 1.0219, + "step": 2783 + }, + { + "epoch": 0.17090763989072716, + "grad_norm": 0.6373851110332668, + "learning_rate": 1.8976773905860836e-05, + "loss": 0.9789, + "step": 2784 + }, + { + "epoch": 0.17096902912919365, + "grad_norm": 0.7036683567397019, + "learning_rate": 1.8975897555588233e-05, + "loss": 1.098, + "step": 2785 + }, + { + "epoch": 0.17103041836766014, + "grad_norm": 0.6434978361551237, + "learning_rate": 1.8975020850450388e-05, + "loss": 1.0487, + "step": 2786 + }, + { + "epoch": 0.17109180760612663, + "grad_norm": 0.6243256114221225, + "learning_rate": 1.8974143790481974e-05, + "loss": 0.9941, + "step": 2787 + }, + { + "epoch": 0.17115319684459315, + "grad_norm": 0.650438978474015, + "learning_rate": 1.8973266375717653e-05, + "loss": 0.9962, + "step": 2788 + }, + { + "epoch": 0.17121458608305964, + "grad_norm": 0.7158607972847874, + "learning_rate": 1.8972388606192124e-05, + "loss": 1.0608, + "step": 2789 + }, + { + "epoch": 0.17127597532152614, + "grad_norm": 0.6912777721320019, + "learning_rate": 1.8971510481940087e-05, + "loss": 1.0203, + "step": 2790 + }, + { + "epoch": 0.17133736455999263, + "grad_norm": 0.6671466291161968, + "learning_rate": 1.8970632002996252e-05, + "loss": 1.0479, + "step": 2791 + }, + { + "epoch": 0.17139875379845912, + "grad_norm": 0.6678859552504947, + "learning_rate": 1.896975316939536e-05, + "loss": 1.0342, + "step": 2792 + }, + { + "epoch": 0.17146014303692564, + "grad_norm": 0.659309549300069, + "learning_rate": 1.8968873981172148e-05, + "loss": 0.9754, + "step": 2793 + }, + { + "epoch": 0.17152153227539213, + "grad_norm": 0.6199552442132106, + "learning_rate": 1.8967994438361382e-05, + "loss": 0.9877, + "step": 2794 + }, + { + "epoch": 0.17158292151385862, + "grad_norm": 0.6522524431378485, + "learning_rate": 1.896711454099783e-05, + "loss": 0.9945, + "step": 2795 + }, + { + "epoch": 0.1716443107523251, + "grad_norm": 0.627779657396489, + "learning_rate": 1.896623428911628e-05, + "loss": 0.9171, + "step": 2796 + }, + { + "epoch": 0.1717056999907916, + "grad_norm": 0.6505102954262387, + "learning_rate": 1.8965353682751535e-05, + "loss": 1.0119, + "step": 2797 + }, + { + "epoch": 0.17176708922925812, + "grad_norm": 0.6201537110147124, + "learning_rate": 1.896447272193841e-05, + "loss": 0.9832, + "step": 2798 + }, + { + "epoch": 0.17182847846772462, + "grad_norm": 0.6525190950427432, + "learning_rate": 1.896359140671173e-05, + "loss": 1.0362, + "step": 2799 + }, + { + "epoch": 0.1718898677061911, + "grad_norm": 0.6126486901916891, + "learning_rate": 1.8962709737106345e-05, + "loss": 0.9376, + "step": 2800 + }, + { + "epoch": 0.1719512569446576, + "grad_norm": 0.6360377470973033, + "learning_rate": 1.8961827713157105e-05, + "loss": 1.003, + "step": 2801 + }, + { + "epoch": 0.1720126461831241, + "grad_norm": 0.6747356840184294, + "learning_rate": 1.8960945334898887e-05, + "loss": 1.0349, + "step": 2802 + }, + { + "epoch": 0.17207403542159058, + "grad_norm": 0.6131373096683411, + "learning_rate": 1.896006260236657e-05, + "loss": 0.987, + "step": 2803 + }, + { + "epoch": 0.1721354246600571, + "grad_norm": 0.6646428752613819, + "learning_rate": 1.8959179515595056e-05, + "loss": 1.0553, + "step": 2804 + }, + { + "epoch": 0.1721968138985236, + "grad_norm": 0.6876035917729574, + "learning_rate": 1.8958296074619263e-05, + "loss": 1.0116, + "step": 2805 + }, + { + "epoch": 0.17225820313699008, + "grad_norm": 0.6224375092447737, + "learning_rate": 1.895741227947411e-05, + "loss": 1.0524, + "step": 2806 + }, + { + "epoch": 0.17231959237545658, + "grad_norm": 0.6288973722519637, + "learning_rate": 1.895652813019454e-05, + "loss": 1.027, + "step": 2807 + }, + { + "epoch": 0.17238098161392307, + "grad_norm": 0.6096378902534938, + "learning_rate": 1.8955643626815517e-05, + "loss": 0.9429, + "step": 2808 + }, + { + "epoch": 0.1724423708523896, + "grad_norm": 0.6412551545657416, + "learning_rate": 1.8954758769372e-05, + "loss": 1.0252, + "step": 2809 + }, + { + "epoch": 0.17250376009085608, + "grad_norm": 0.5978173894548418, + "learning_rate": 1.8953873557898977e-05, + "loss": 1.0468, + "step": 2810 + }, + { + "epoch": 0.17256514932932257, + "grad_norm": 0.6451012125150922, + "learning_rate": 1.895298799243144e-05, + "loss": 1.0336, + "step": 2811 + }, + { + "epoch": 0.17262653856778906, + "grad_norm": 0.6711813187482549, + "learning_rate": 1.8952102073004408e-05, + "loss": 1.0221, + "step": 2812 + }, + { + "epoch": 0.17268792780625555, + "grad_norm": 0.6516712677686776, + "learning_rate": 1.89512157996529e-05, + "loss": 0.9739, + "step": 2813 + }, + { + "epoch": 0.17274931704472207, + "grad_norm": 0.6530406170353373, + "learning_rate": 1.8950329172411954e-05, + "loss": 1.0113, + "step": 2814 + }, + { + "epoch": 0.17281070628318856, + "grad_norm": 0.6364376446888598, + "learning_rate": 1.8949442191316628e-05, + "loss": 0.9958, + "step": 2815 + }, + { + "epoch": 0.17287209552165506, + "grad_norm": 0.6395286014244277, + "learning_rate": 1.894855485640199e-05, + "loss": 0.9883, + "step": 2816 + }, + { + "epoch": 0.17293348476012155, + "grad_norm": 0.6337876330463292, + "learning_rate": 1.8947667167703116e-05, + "loss": 1.065, + "step": 2817 + }, + { + "epoch": 0.17299487399858804, + "grad_norm": 0.6484993107746936, + "learning_rate": 1.89467791252551e-05, + "loss": 0.9876, + "step": 2818 + }, + { + "epoch": 0.17305626323705453, + "grad_norm": 0.706446505601606, + "learning_rate": 1.894589072909306e-05, + "loss": 1.0566, + "step": 2819 + }, + { + "epoch": 0.17311765247552105, + "grad_norm": 0.6099426431013543, + "learning_rate": 1.894500197925211e-05, + "loss": 0.7898, + "step": 2820 + }, + { + "epoch": 0.17317904171398754, + "grad_norm": 0.649009946800884, + "learning_rate": 1.8944112875767395e-05, + "loss": 1.0147, + "step": 2821 + }, + { + "epoch": 0.17324043095245403, + "grad_norm": 0.6467028450456799, + "learning_rate": 1.8943223418674055e-05, + "loss": 0.9767, + "step": 2822 + }, + { + "epoch": 0.17330182019092052, + "grad_norm": 0.6510052783912277, + "learning_rate": 1.8942333608007267e-05, + "loss": 0.9919, + "step": 2823 + }, + { + "epoch": 0.17336320942938702, + "grad_norm": 0.6802873356656346, + "learning_rate": 1.89414434438022e-05, + "loss": 1.0691, + "step": 2824 + }, + { + "epoch": 0.17342459866785354, + "grad_norm": 0.7363877444120154, + "learning_rate": 1.8940552926094055e-05, + "loss": 1.0275, + "step": 2825 + }, + { + "epoch": 0.17348598790632003, + "grad_norm": 0.6102888589058315, + "learning_rate": 1.8939662054918035e-05, + "loss": 0.9965, + "step": 2826 + }, + { + "epoch": 0.17354737714478652, + "grad_norm": 0.6276079006774243, + "learning_rate": 1.893877083030936e-05, + "loss": 0.9913, + "step": 2827 + }, + { + "epoch": 0.173608766383253, + "grad_norm": 0.6284183105057786, + "learning_rate": 1.8937879252303268e-05, + "loss": 1.0076, + "step": 2828 + }, + { + "epoch": 0.1736701556217195, + "grad_norm": 0.7268213121152889, + "learning_rate": 1.8936987320935003e-05, + "loss": 1.0574, + "step": 2829 + }, + { + "epoch": 0.17373154486018602, + "grad_norm": 0.6167429339963033, + "learning_rate": 1.8936095036239833e-05, + "loss": 1.0241, + "step": 2830 + }, + { + "epoch": 0.1737929340986525, + "grad_norm": 0.6214126749066894, + "learning_rate": 1.893520239825303e-05, + "loss": 1.0413, + "step": 2831 + }, + { + "epoch": 0.173854323337119, + "grad_norm": 0.6126709482178174, + "learning_rate": 1.8934309407009893e-05, + "loss": 1.0187, + "step": 2832 + }, + { + "epoch": 0.1739157125755855, + "grad_norm": 0.6849007660268519, + "learning_rate": 1.8933416062545717e-05, + "loss": 1.0506, + "step": 2833 + }, + { + "epoch": 0.173977101814052, + "grad_norm": 0.6615933666998487, + "learning_rate": 1.8932522364895826e-05, + "loss": 0.9933, + "step": 2834 + }, + { + "epoch": 0.1740384910525185, + "grad_norm": 0.6525997046458963, + "learning_rate": 1.8931628314095548e-05, + "loss": 1.0132, + "step": 2835 + }, + { + "epoch": 0.174099880290985, + "grad_norm": 0.6248833766158324, + "learning_rate": 1.8930733910180238e-05, + "loss": 1.0149, + "step": 2836 + }, + { + "epoch": 0.1741612695294515, + "grad_norm": 0.684934693482054, + "learning_rate": 1.892983915318525e-05, + "loss": 1.0411, + "step": 2837 + }, + { + "epoch": 0.17422265876791798, + "grad_norm": 0.5985630468045305, + "learning_rate": 1.892894404314596e-05, + "loss": 1.0337, + "step": 2838 + }, + { + "epoch": 0.17428404800638447, + "grad_norm": 0.640209924068235, + "learning_rate": 1.8928048580097758e-05, + "loss": 1.0322, + "step": 2839 + }, + { + "epoch": 0.17434543724485096, + "grad_norm": 0.6595297334211015, + "learning_rate": 1.892715276407604e-05, + "loss": 0.9894, + "step": 2840 + }, + { + "epoch": 0.17440682648331748, + "grad_norm": 0.6506736136490635, + "learning_rate": 1.8926256595116233e-05, + "loss": 1.0124, + "step": 2841 + }, + { + "epoch": 0.17446821572178398, + "grad_norm": 0.6122118245439402, + "learning_rate": 1.8925360073253758e-05, + "loss": 0.9938, + "step": 2842 + }, + { + "epoch": 0.17452960496025047, + "grad_norm": 0.6619152076729038, + "learning_rate": 1.8924463198524066e-05, + "loss": 1.0865, + "step": 2843 + }, + { + "epoch": 0.17459099419871696, + "grad_norm": 0.7107366047351192, + "learning_rate": 1.892356597096261e-05, + "loss": 1.0535, + "step": 2844 + }, + { + "epoch": 0.17465238343718345, + "grad_norm": 0.6300653883821389, + "learning_rate": 1.892266839060487e-05, + "loss": 1.0212, + "step": 2845 + }, + { + "epoch": 0.17471377267564997, + "grad_norm": 0.6949743231480875, + "learning_rate": 1.892177045748632e-05, + "loss": 1.0241, + "step": 2846 + }, + { + "epoch": 0.17477516191411646, + "grad_norm": 0.6741008600606477, + "learning_rate": 1.892087217164247e-05, + "loss": 1.0115, + "step": 2847 + }, + { + "epoch": 0.17483655115258295, + "grad_norm": 0.6105180091898569, + "learning_rate": 1.891997353310883e-05, + "loss": 1.0064, + "step": 2848 + }, + { + "epoch": 0.17489794039104944, + "grad_norm": 0.5867709920347677, + "learning_rate": 1.8919074541920928e-05, + "loss": 0.93, + "step": 2849 + }, + { + "epoch": 0.17495932962951594, + "grad_norm": 0.6296030592688623, + "learning_rate": 1.8918175198114304e-05, + "loss": 1.0595, + "step": 2850 + }, + { + "epoch": 0.17502071886798246, + "grad_norm": 0.6172812227184541, + "learning_rate": 1.8917275501724524e-05, + "loss": 1.0201, + "step": 2851 + }, + { + "epoch": 0.17508210810644895, + "grad_norm": 0.6288554719742862, + "learning_rate": 1.8916375452787146e-05, + "loss": 1.0008, + "step": 2852 + }, + { + "epoch": 0.17514349734491544, + "grad_norm": 0.6213396392708963, + "learning_rate": 1.891547505133776e-05, + "loss": 0.9945, + "step": 2853 + }, + { + "epoch": 0.17520488658338193, + "grad_norm": 0.69326571003425, + "learning_rate": 1.891457429741196e-05, + "loss": 0.7965, + "step": 2854 + }, + { + "epoch": 0.17526627582184842, + "grad_norm": 0.623936762155564, + "learning_rate": 1.8913673191045362e-05, + "loss": 0.9901, + "step": 2855 + }, + { + "epoch": 0.1753276650603149, + "grad_norm": 0.6888810069692611, + "learning_rate": 1.891277173227359e-05, + "loss": 1.0534, + "step": 2856 + }, + { + "epoch": 0.17538905429878143, + "grad_norm": 0.6473450734678878, + "learning_rate": 1.891186992113228e-05, + "loss": 0.9809, + "step": 2857 + }, + { + "epoch": 0.17545044353724792, + "grad_norm": 0.6360810650327369, + "learning_rate": 1.891096775765709e-05, + "loss": 1.0156, + "step": 2858 + }, + { + "epoch": 0.17551183277571442, + "grad_norm": 0.6487367392192949, + "learning_rate": 1.891006524188368e-05, + "loss": 1.0113, + "step": 2859 + }, + { + "epoch": 0.1755732220141809, + "grad_norm": 0.6089767336229578, + "learning_rate": 1.890916237384774e-05, + "loss": 1.0033, + "step": 2860 + }, + { + "epoch": 0.1756346112526474, + "grad_norm": 0.6585681008030607, + "learning_rate": 1.8908259153584964e-05, + "loss": 1.0259, + "step": 2861 + }, + { + "epoch": 0.17569600049111392, + "grad_norm": 0.6599702061158911, + "learning_rate": 1.8907355581131055e-05, + "loss": 1.0471, + "step": 2862 + }, + { + "epoch": 0.1757573897295804, + "grad_norm": 0.6394765636599388, + "learning_rate": 1.890645165652174e-05, + "loss": 1.0527, + "step": 2863 + }, + { + "epoch": 0.1758187789680469, + "grad_norm": 0.63532580955942, + "learning_rate": 1.890554737979276e-05, + "loss": 1.0077, + "step": 2864 + }, + { + "epoch": 0.1758801682065134, + "grad_norm": 0.6561865338622677, + "learning_rate": 1.8904642750979862e-05, + "loss": 1.0163, + "step": 2865 + }, + { + "epoch": 0.17594155744497988, + "grad_norm": 0.6609041507573928, + "learning_rate": 1.8903737770118806e-05, + "loss": 1.0288, + "step": 2866 + }, + { + "epoch": 0.1760029466834464, + "grad_norm": 0.6036567989300884, + "learning_rate": 1.890283243724538e-05, + "loss": 0.9925, + "step": 2867 + }, + { + "epoch": 0.1760643359219129, + "grad_norm": 0.6232636671407659, + "learning_rate": 1.8901926752395366e-05, + "loss": 1.0304, + "step": 2868 + }, + { + "epoch": 0.1761257251603794, + "grad_norm": 0.642402572216999, + "learning_rate": 1.8901020715604583e-05, + "loss": 1.0438, + "step": 2869 + }, + { + "epoch": 0.17618711439884588, + "grad_norm": 0.6335851463696127, + "learning_rate": 1.8900114326908846e-05, + "loss": 1.0213, + "step": 2870 + }, + { + "epoch": 0.17624850363731237, + "grad_norm": 0.6840738387633699, + "learning_rate": 1.889920758634398e-05, + "loss": 1.0504, + "step": 2871 + }, + { + "epoch": 0.1763098928757789, + "grad_norm": 0.7020357547077206, + "learning_rate": 1.889830049394585e-05, + "loss": 0.7367, + "step": 2872 + }, + { + "epoch": 0.17637128211424538, + "grad_norm": 0.648681406636883, + "learning_rate": 1.8897393049750308e-05, + "loss": 1.0815, + "step": 2873 + }, + { + "epoch": 0.17643267135271187, + "grad_norm": 0.6346232084502201, + "learning_rate": 1.889648525379323e-05, + "loss": 0.9992, + "step": 2874 + }, + { + "epoch": 0.17649406059117836, + "grad_norm": 0.6951842700905448, + "learning_rate": 1.889557710611051e-05, + "loss": 1.0527, + "step": 2875 + }, + { + "epoch": 0.17655544982964486, + "grad_norm": 0.6238438702876002, + "learning_rate": 1.8894668606738048e-05, + "loss": 0.994, + "step": 2876 + }, + { + "epoch": 0.17661683906811135, + "grad_norm": 0.6325613130202625, + "learning_rate": 1.8893759755711767e-05, + "loss": 1.0348, + "step": 2877 + }, + { + "epoch": 0.17667822830657787, + "grad_norm": 0.6799022328176781, + "learning_rate": 1.8892850553067595e-05, + "loss": 1.0964, + "step": 2878 + }, + { + "epoch": 0.17673961754504436, + "grad_norm": 0.5953289299505896, + "learning_rate": 1.8891940998841476e-05, + "loss": 0.7616, + "step": 2879 + }, + { + "epoch": 0.17680100678351085, + "grad_norm": 0.6291331662288389, + "learning_rate": 1.8891031093069375e-05, + "loss": 0.9632, + "step": 2880 + }, + { + "epoch": 0.17686239602197734, + "grad_norm": 0.675452538742634, + "learning_rate": 1.889012083578726e-05, + "loss": 1.0567, + "step": 2881 + }, + { + "epoch": 0.17692378526044383, + "grad_norm": 0.6645389327957436, + "learning_rate": 1.8889210227031118e-05, + "loss": 1.0101, + "step": 2882 + }, + { + "epoch": 0.17698517449891035, + "grad_norm": 0.6306511609531364, + "learning_rate": 1.8888299266836955e-05, + "loss": 0.9843, + "step": 2883 + }, + { + "epoch": 0.17704656373737684, + "grad_norm": 0.578915968211286, + "learning_rate": 1.888738795524079e-05, + "loss": 0.7705, + "step": 2884 + }, + { + "epoch": 0.17710795297584334, + "grad_norm": 0.6137958402186432, + "learning_rate": 1.888647629227864e-05, + "loss": 0.9759, + "step": 2885 + }, + { + "epoch": 0.17716934221430983, + "grad_norm": 0.668209441700054, + "learning_rate": 1.8885564277986553e-05, + "loss": 1.061, + "step": 2886 + }, + { + "epoch": 0.17723073145277632, + "grad_norm": 0.6569635916920714, + "learning_rate": 1.8884651912400592e-05, + "loss": 1.0678, + "step": 2887 + }, + { + "epoch": 0.17729212069124284, + "grad_norm": 0.6217993165403395, + "learning_rate": 1.8883739195556818e-05, + "loss": 1.0178, + "step": 2888 + }, + { + "epoch": 0.17735350992970933, + "grad_norm": 0.6446595798184271, + "learning_rate": 1.888282612749132e-05, + "loss": 1.0242, + "step": 2889 + }, + { + "epoch": 0.17741489916817582, + "grad_norm": 0.6777145241860777, + "learning_rate": 1.8881912708240198e-05, + "loss": 1.0375, + "step": 2890 + }, + { + "epoch": 0.1774762884066423, + "grad_norm": 0.6481246359840809, + "learning_rate": 1.8880998937839564e-05, + "loss": 1.0274, + "step": 2891 + }, + { + "epoch": 0.1775376776451088, + "grad_norm": 0.6273220993994886, + "learning_rate": 1.8880084816325542e-05, + "loss": 0.9992, + "step": 2892 + }, + { + "epoch": 0.1775990668835753, + "grad_norm": 0.6398316969707498, + "learning_rate": 1.8879170343734273e-05, + "loss": 1.0406, + "step": 2893 + }, + { + "epoch": 0.17766045612204182, + "grad_norm": 0.651097891065258, + "learning_rate": 1.8878255520101908e-05, + "loss": 1.0558, + "step": 2894 + }, + { + "epoch": 0.1777218453605083, + "grad_norm": 0.6665365943549091, + "learning_rate": 1.8877340345464623e-05, + "loss": 1.0371, + "step": 2895 + }, + { + "epoch": 0.1777832345989748, + "grad_norm": 0.6347470987312134, + "learning_rate": 1.8876424819858596e-05, + "loss": 1.0002, + "step": 2896 + }, + { + "epoch": 0.1778446238374413, + "grad_norm": 0.6623526846503753, + "learning_rate": 1.8875508943320015e-05, + "loss": 1.0238, + "step": 2897 + }, + { + "epoch": 0.17790601307590778, + "grad_norm": 0.6797707313793812, + "learning_rate": 1.88745927158851e-05, + "loss": 1.0322, + "step": 2898 + }, + { + "epoch": 0.1779674023143743, + "grad_norm": 0.6336995877341024, + "learning_rate": 1.887367613759007e-05, + "loss": 1.0089, + "step": 2899 + }, + { + "epoch": 0.1780287915528408, + "grad_norm": 0.6425514441702245, + "learning_rate": 1.887275920847116e-05, + "loss": 1.0176, + "step": 2900 + }, + { + "epoch": 0.17809018079130728, + "grad_norm": 0.5900846563162565, + "learning_rate": 1.887184192856463e-05, + "loss": 0.9712, + "step": 2901 + }, + { + "epoch": 0.17815157002977378, + "grad_norm": 0.6401363115732711, + "learning_rate": 1.887092429790673e-05, + "loss": 1.0173, + "step": 2902 + }, + { + "epoch": 0.17821295926824027, + "grad_norm": 0.6664424841666082, + "learning_rate": 1.8870006316533753e-05, + "loss": 1.0809, + "step": 2903 + }, + { + "epoch": 0.1782743485067068, + "grad_norm": 0.610308523128169, + "learning_rate": 1.8869087984481983e-05, + "loss": 0.981, + "step": 2904 + }, + { + "epoch": 0.17833573774517328, + "grad_norm": 0.5855693620992573, + "learning_rate": 1.8868169301787734e-05, + "loss": 0.9683, + "step": 2905 + }, + { + "epoch": 0.17839712698363977, + "grad_norm": 0.67058921194564, + "learning_rate": 1.886725026848732e-05, + "loss": 1.0459, + "step": 2906 + }, + { + "epoch": 0.17845851622210626, + "grad_norm": 0.629215601647153, + "learning_rate": 1.8866330884617078e-05, + "loss": 0.9971, + "step": 2907 + }, + { + "epoch": 0.17851990546057275, + "grad_norm": 0.64554992521713, + "learning_rate": 1.8865411150213356e-05, + "loss": 1.0115, + "step": 2908 + }, + { + "epoch": 0.17858129469903924, + "grad_norm": 0.7212868298284487, + "learning_rate": 1.8864491065312512e-05, + "loss": 1.0616, + "step": 2909 + }, + { + "epoch": 0.17864268393750576, + "grad_norm": 0.6025489925435489, + "learning_rate": 1.886357062995093e-05, + "loss": 0.9653, + "step": 2910 + }, + { + "epoch": 0.17870407317597226, + "grad_norm": 0.6609975081387738, + "learning_rate": 1.8862649844164994e-05, + "loss": 1.0282, + "step": 2911 + }, + { + "epoch": 0.17876546241443875, + "grad_norm": 0.5804956358663129, + "learning_rate": 1.8861728707991106e-05, + "loss": 0.9429, + "step": 2912 + }, + { + "epoch": 0.17882685165290524, + "grad_norm": 0.6569867778570684, + "learning_rate": 1.886080722146569e-05, + "loss": 1.0578, + "step": 2913 + }, + { + "epoch": 0.17888824089137173, + "grad_norm": 0.6677529001637048, + "learning_rate": 1.885988538462517e-05, + "loss": 1.0721, + "step": 2914 + }, + { + "epoch": 0.17894963012983825, + "grad_norm": 0.6181220391986906, + "learning_rate": 1.8858963197506e-05, + "loss": 1.0124, + "step": 2915 + }, + { + "epoch": 0.17901101936830474, + "grad_norm": 0.6694863294040287, + "learning_rate": 1.885804066014463e-05, + "loss": 1.0581, + "step": 2916 + }, + { + "epoch": 0.17907240860677123, + "grad_norm": 0.5941576819860148, + "learning_rate": 1.8857117772577537e-05, + "loss": 0.9763, + "step": 2917 + }, + { + "epoch": 0.17913379784523772, + "grad_norm": 0.6400802873790971, + "learning_rate": 1.885619453484121e-05, + "loss": 1.0262, + "step": 2918 + }, + { + "epoch": 0.17919518708370422, + "grad_norm": 0.6043036397540938, + "learning_rate": 1.8855270946972146e-05, + "loss": 0.988, + "step": 2919 + }, + { + "epoch": 0.17925657632217074, + "grad_norm": 0.63825862768753, + "learning_rate": 1.8854347009006856e-05, + "loss": 0.9932, + "step": 2920 + }, + { + "epoch": 0.17931796556063723, + "grad_norm": 0.6374969160956632, + "learning_rate": 1.8853422720981873e-05, + "loss": 1.0098, + "step": 2921 + }, + { + "epoch": 0.17937935479910372, + "grad_norm": 0.6403721436974766, + "learning_rate": 1.8852498082933742e-05, + "loss": 0.98, + "step": 2922 + }, + { + "epoch": 0.1794407440375702, + "grad_norm": 0.6756869748449125, + "learning_rate": 1.8851573094899014e-05, + "loss": 0.9858, + "step": 2923 + }, + { + "epoch": 0.1795021332760367, + "grad_norm": 0.7020046056909733, + "learning_rate": 1.885064775691426e-05, + "loss": 1.0929, + "step": 2924 + }, + { + "epoch": 0.17956352251450322, + "grad_norm": 0.6478973306161031, + "learning_rate": 1.8849722069016062e-05, + "loss": 1.0004, + "step": 2925 + }, + { + "epoch": 0.1796249117529697, + "grad_norm": 0.6130498397788985, + "learning_rate": 1.8848796031241022e-05, + "loss": 1.0255, + "step": 2926 + }, + { + "epoch": 0.1796863009914362, + "grad_norm": 0.6051421772472124, + "learning_rate": 1.8847869643625745e-05, + "loss": 1.0012, + "step": 2927 + }, + { + "epoch": 0.1797476902299027, + "grad_norm": 0.6288622843145136, + "learning_rate": 1.884694290620686e-05, + "loss": 0.9856, + "step": 2928 + }, + { + "epoch": 0.1798090794683692, + "grad_norm": 0.6515986404700134, + "learning_rate": 1.884601581902101e-05, + "loss": 1.0165, + "step": 2929 + }, + { + "epoch": 0.17987046870683568, + "grad_norm": 0.6527054961097352, + "learning_rate": 1.8845088382104837e-05, + "loss": 1.0091, + "step": 2930 + }, + { + "epoch": 0.1799318579453022, + "grad_norm": 0.6795319496669606, + "learning_rate": 1.8844160595495013e-05, + "loss": 1.0729, + "step": 2931 + }, + { + "epoch": 0.1799932471837687, + "grad_norm": 0.6802808959813577, + "learning_rate": 1.884323245922822e-05, + "loss": 1.0486, + "step": 2932 + }, + { + "epoch": 0.18005463642223518, + "grad_norm": 0.6765728072843629, + "learning_rate": 1.8842303973341154e-05, + "loss": 1.0502, + "step": 2933 + }, + { + "epoch": 0.18011602566070167, + "grad_norm": 0.6528885123301668, + "learning_rate": 1.8841375137870517e-05, + "loss": 1.0056, + "step": 2934 + }, + { + "epoch": 0.18017741489916816, + "grad_norm": 0.6159407589449344, + "learning_rate": 1.8840445952853034e-05, + "loss": 0.9917, + "step": 2935 + }, + { + "epoch": 0.18023880413763468, + "grad_norm": 0.6407462171204653, + "learning_rate": 1.8839516418325444e-05, + "loss": 1.0047, + "step": 2936 + }, + { + "epoch": 0.18030019337610118, + "grad_norm": 0.6961098554425319, + "learning_rate": 1.8838586534324488e-05, + "loss": 1.0479, + "step": 2937 + }, + { + "epoch": 0.18036158261456767, + "grad_norm": 0.6835535966810946, + "learning_rate": 1.8837656300886937e-05, + "loss": 1.034, + "step": 2938 + }, + { + "epoch": 0.18042297185303416, + "grad_norm": 0.6926570136475062, + "learning_rate": 1.8836725718049562e-05, + "loss": 1.028, + "step": 2939 + }, + { + "epoch": 0.18048436109150065, + "grad_norm": 0.6501775632512374, + "learning_rate": 1.8835794785849163e-05, + "loss": 1.0203, + "step": 2940 + }, + { + "epoch": 0.18054575032996717, + "grad_norm": 0.694059427399925, + "learning_rate": 1.8834863504322533e-05, + "loss": 1.0327, + "step": 2941 + }, + { + "epoch": 0.18060713956843366, + "grad_norm": 0.6115544005030329, + "learning_rate": 1.8833931873506502e-05, + "loss": 1.0201, + "step": 2942 + }, + { + "epoch": 0.18066852880690015, + "grad_norm": 0.6178993286848433, + "learning_rate": 1.8832999893437893e-05, + "loss": 1.0046, + "step": 2943 + }, + { + "epoch": 0.18072991804536664, + "grad_norm": 0.6341172489267239, + "learning_rate": 1.8832067564153557e-05, + "loss": 0.9866, + "step": 2944 + }, + { + "epoch": 0.18079130728383314, + "grad_norm": 0.6876171213089904, + "learning_rate": 1.883113488569035e-05, + "loss": 1.0033, + "step": 2945 + }, + { + "epoch": 0.18085269652229963, + "grad_norm": 0.5906275605396738, + "learning_rate": 1.8830201858085156e-05, + "loss": 0.9649, + "step": 2946 + }, + { + "epoch": 0.18091408576076615, + "grad_norm": 0.6681924018420219, + "learning_rate": 1.882926848137485e-05, + "loss": 0.9729, + "step": 2947 + }, + { + "epoch": 0.18097547499923264, + "grad_norm": 0.610578635575952, + "learning_rate": 1.8828334755596337e-05, + "loss": 0.9469, + "step": 2948 + }, + { + "epoch": 0.18103686423769913, + "grad_norm": 0.6741332982875893, + "learning_rate": 1.8827400680786538e-05, + "loss": 1.0115, + "step": 2949 + }, + { + "epoch": 0.18109825347616562, + "grad_norm": 0.6466550826558922, + "learning_rate": 1.8826466256982377e-05, + "loss": 0.9735, + "step": 2950 + }, + { + "epoch": 0.1811596427146321, + "grad_norm": 0.7049771123403109, + "learning_rate": 1.8825531484220797e-05, + "loss": 1.0422, + "step": 2951 + }, + { + "epoch": 0.18122103195309863, + "grad_norm": 0.6587944962965203, + "learning_rate": 1.8824596362538753e-05, + "loss": 1.0122, + "step": 2952 + }, + { + "epoch": 0.18128242119156512, + "grad_norm": 0.7008920647342877, + "learning_rate": 1.8823660891973223e-05, + "loss": 1.0585, + "step": 2953 + }, + { + "epoch": 0.18134381043003162, + "grad_norm": 0.6369443484126487, + "learning_rate": 1.882272507256118e-05, + "loss": 0.9881, + "step": 2954 + }, + { + "epoch": 0.1814051996684981, + "grad_norm": 0.6653822258889992, + "learning_rate": 1.8821788904339633e-05, + "loss": 1.0259, + "step": 2955 + }, + { + "epoch": 0.1814665889069646, + "grad_norm": 0.5892598352069875, + "learning_rate": 1.8820852387345585e-05, + "loss": 0.9906, + "step": 2956 + }, + { + "epoch": 0.18152797814543112, + "grad_norm": 0.6207896597636771, + "learning_rate": 1.8819915521616066e-05, + "loss": 1.0027, + "step": 2957 + }, + { + "epoch": 0.1815893673838976, + "grad_norm": 0.6862106690135322, + "learning_rate": 1.8818978307188113e-05, + "loss": 1.0146, + "step": 2958 + }, + { + "epoch": 0.1816507566223641, + "grad_norm": 0.6566735656618771, + "learning_rate": 1.881804074409878e-05, + "loss": 1.033, + "step": 2959 + }, + { + "epoch": 0.1817121458608306, + "grad_norm": 0.6597847606614057, + "learning_rate": 1.8817102832385134e-05, + "loss": 1.0127, + "step": 2960 + }, + { + "epoch": 0.18177353509929708, + "grad_norm": 0.6596955255153351, + "learning_rate": 1.8816164572084256e-05, + "loss": 0.9985, + "step": 2961 + }, + { + "epoch": 0.1818349243377636, + "grad_norm": 0.6530529851865079, + "learning_rate": 1.881522596323324e-05, + "loss": 1.0861, + "step": 2962 + }, + { + "epoch": 0.1818963135762301, + "grad_norm": 0.6938026066954229, + "learning_rate": 1.8814287005869198e-05, + "loss": 1.0658, + "step": 2963 + }, + { + "epoch": 0.1819577028146966, + "grad_norm": 0.6974966671978401, + "learning_rate": 1.8813347700029244e-05, + "loss": 1.0315, + "step": 2964 + }, + { + "epoch": 0.18201909205316308, + "grad_norm": 0.6919173730311103, + "learning_rate": 1.8812408045750524e-05, + "loss": 1.0359, + "step": 2965 + }, + { + "epoch": 0.18208048129162957, + "grad_norm": 0.6560817626270385, + "learning_rate": 1.881146804307018e-05, + "loss": 1.0364, + "step": 2966 + }, + { + "epoch": 0.18214187053009606, + "grad_norm": 0.6406368938638352, + "learning_rate": 1.8810527692025372e-05, + "loss": 0.9918, + "step": 2967 + }, + { + "epoch": 0.18220325976856258, + "grad_norm": 0.6414392592675638, + "learning_rate": 1.8809586992653285e-05, + "loss": 1.0282, + "step": 2968 + }, + { + "epoch": 0.18226464900702907, + "grad_norm": 0.619888371890077, + "learning_rate": 1.880864594499111e-05, + "loss": 1.0063, + "step": 2969 + }, + { + "epoch": 0.18232603824549556, + "grad_norm": 0.6522970149886717, + "learning_rate": 1.8807704549076047e-05, + "loss": 1.0481, + "step": 2970 + }, + { + "epoch": 0.18238742748396206, + "grad_norm": 0.652687788948403, + "learning_rate": 1.8806762804945317e-05, + "loss": 1.0121, + "step": 2971 + }, + { + "epoch": 0.18244881672242855, + "grad_norm": 0.6756343067636703, + "learning_rate": 1.880582071263615e-05, + "loss": 1.1069, + "step": 2972 + }, + { + "epoch": 0.18251020596089507, + "grad_norm": 0.6222608317389693, + "learning_rate": 1.8804878272185794e-05, + "loss": 1.0684, + "step": 2973 + }, + { + "epoch": 0.18257159519936156, + "grad_norm": 0.6615170405462117, + "learning_rate": 1.8803935483631507e-05, + "loss": 1.0432, + "step": 2974 + }, + { + "epoch": 0.18263298443782805, + "grad_norm": 0.6723449797018803, + "learning_rate": 1.8802992347010568e-05, + "loss": 1.0425, + "step": 2975 + }, + { + "epoch": 0.18269437367629454, + "grad_norm": 0.6223854228560325, + "learning_rate": 1.8802048862360254e-05, + "loss": 0.9827, + "step": 2976 + }, + { + "epoch": 0.18275576291476103, + "grad_norm": 0.5758439987250785, + "learning_rate": 1.8801105029717875e-05, + "loss": 0.9549, + "step": 2977 + }, + { + "epoch": 0.18281715215322755, + "grad_norm": 0.6068786690003296, + "learning_rate": 1.8800160849120742e-05, + "loss": 0.9977, + "step": 2978 + }, + { + "epoch": 0.18287854139169404, + "grad_norm": 0.6135775231246164, + "learning_rate": 1.8799216320606187e-05, + "loss": 1.0019, + "step": 2979 + }, + { + "epoch": 0.18293993063016054, + "grad_norm": 0.6270163921272924, + "learning_rate": 1.8798271444211545e-05, + "loss": 0.9847, + "step": 2980 + }, + { + "epoch": 0.18300131986862703, + "grad_norm": 0.6639253388999623, + "learning_rate": 1.8797326219974177e-05, + "loss": 1.0438, + "step": 2981 + }, + { + "epoch": 0.18306270910709352, + "grad_norm": 0.7027080135233669, + "learning_rate": 1.879638064793145e-05, + "loss": 1.0244, + "step": 2982 + }, + { + "epoch": 0.18312409834556, + "grad_norm": 0.6653160525044325, + "learning_rate": 1.8795434728120756e-05, + "loss": 1.0155, + "step": 2983 + }, + { + "epoch": 0.18318548758402653, + "grad_norm": 0.6871487646905192, + "learning_rate": 1.8794488460579483e-05, + "loss": 1.0194, + "step": 2984 + }, + { + "epoch": 0.18324687682249302, + "grad_norm": 0.6377846159440055, + "learning_rate": 1.8793541845345045e-05, + "loss": 1.0488, + "step": 2985 + }, + { + "epoch": 0.1833082660609595, + "grad_norm": 0.6567483435409736, + "learning_rate": 1.8792594882454863e-05, + "loss": 1.0503, + "step": 2986 + }, + { + "epoch": 0.183369655299426, + "grad_norm": 0.6530083787156734, + "learning_rate": 1.8791647571946384e-05, + "loss": 1.0294, + "step": 2987 + }, + { + "epoch": 0.1834310445378925, + "grad_norm": 0.6546314066959757, + "learning_rate": 1.8790699913857054e-05, + "loss": 1.0487, + "step": 2988 + }, + { + "epoch": 0.18349243377635902, + "grad_norm": 0.6585845399251619, + "learning_rate": 1.878975190822434e-05, + "loss": 0.9977, + "step": 2989 + }, + { + "epoch": 0.1835538230148255, + "grad_norm": 0.6342790449026267, + "learning_rate": 1.8788803555085722e-05, + "loss": 0.9595, + "step": 2990 + }, + { + "epoch": 0.183615212253292, + "grad_norm": 0.6079334111450714, + "learning_rate": 1.8787854854478693e-05, + "loss": 0.9735, + "step": 2991 + }, + { + "epoch": 0.1836766014917585, + "grad_norm": 0.6319821987862201, + "learning_rate": 1.8786905806440762e-05, + "loss": 0.9996, + "step": 2992 + }, + { + "epoch": 0.18373799073022498, + "grad_norm": 0.6778832282257241, + "learning_rate": 1.878595641100945e-05, + "loss": 1.0672, + "step": 2993 + }, + { + "epoch": 0.1837993799686915, + "grad_norm": 0.6824214632850691, + "learning_rate": 1.8785006668222287e-05, + "loss": 1.0441, + "step": 2994 + }, + { + "epoch": 0.183860769207158, + "grad_norm": 0.6325275677210477, + "learning_rate": 1.8784056578116827e-05, + "loss": 1.0188, + "step": 2995 + }, + { + "epoch": 0.18392215844562448, + "grad_norm": 0.6325800446676586, + "learning_rate": 1.878310614073063e-05, + "loss": 1.0276, + "step": 2996 + }, + { + "epoch": 0.18398354768409098, + "grad_norm": 0.6812228635690333, + "learning_rate": 1.8782155356101272e-05, + "loss": 1.079, + "step": 2997 + }, + { + "epoch": 0.18404493692255747, + "grad_norm": 0.6278450449941393, + "learning_rate": 1.8781204224266342e-05, + "loss": 0.9941, + "step": 2998 + }, + { + "epoch": 0.18410632616102396, + "grad_norm": 0.6365720547806734, + "learning_rate": 1.8780252745263445e-05, + "loss": 1.0033, + "step": 2999 + }, + { + "epoch": 0.18416771539949048, + "grad_norm": 0.6040148431470179, + "learning_rate": 1.8779300919130198e-05, + "loss": 0.9682, + "step": 3000 + }, + { + "epoch": 0.18422910463795697, + "grad_norm": 0.6474941006664838, + "learning_rate": 1.8778348745904228e-05, + "loss": 1.0098, + "step": 3001 + }, + { + "epoch": 0.18429049387642346, + "grad_norm": 0.6421879446449578, + "learning_rate": 1.877739622562318e-05, + "loss": 1.0049, + "step": 3002 + }, + { + "epoch": 0.18435188311488995, + "grad_norm": 0.6938516874605374, + "learning_rate": 1.8776443358324718e-05, + "loss": 1.08, + "step": 3003 + }, + { + "epoch": 0.18441327235335644, + "grad_norm": 0.6708090564976759, + "learning_rate": 1.877549014404651e-05, + "loss": 1.0089, + "step": 3004 + }, + { + "epoch": 0.18447466159182296, + "grad_norm": 0.6245461512893096, + "learning_rate": 1.877453658282624e-05, + "loss": 1.0069, + "step": 3005 + }, + { + "epoch": 0.18453605083028946, + "grad_norm": 0.681914817624046, + "learning_rate": 1.8773582674701614e-05, + "loss": 1.0388, + "step": 3006 + }, + { + "epoch": 0.18459744006875595, + "grad_norm": 0.6664896339257783, + "learning_rate": 1.8772628419710335e-05, + "loss": 1.0272, + "step": 3007 + }, + { + "epoch": 0.18465882930722244, + "grad_norm": 0.6093090332641934, + "learning_rate": 1.877167381789014e-05, + "loss": 0.9813, + "step": 3008 + }, + { + "epoch": 0.18472021854568893, + "grad_norm": 0.6958316756373225, + "learning_rate": 1.8770718869278762e-05, + "loss": 1.0047, + "step": 3009 + }, + { + "epoch": 0.18478160778415545, + "grad_norm": 0.6259077649948722, + "learning_rate": 1.8769763573913956e-05, + "loss": 0.9792, + "step": 3010 + }, + { + "epoch": 0.18484299702262194, + "grad_norm": 0.6799052753676257, + "learning_rate": 1.8768807931833496e-05, + "loss": 1.0436, + "step": 3011 + }, + { + "epoch": 0.18490438626108843, + "grad_norm": 0.6388033617278622, + "learning_rate": 1.8767851943075157e-05, + "loss": 1.0329, + "step": 3012 + }, + { + "epoch": 0.18496577549955492, + "grad_norm": 0.6057986390494285, + "learning_rate": 1.876689560767674e-05, + "loss": 0.9412, + "step": 3013 + }, + { + "epoch": 0.18502716473802142, + "grad_norm": 0.6235320342049627, + "learning_rate": 1.8765938925676046e-05, + "loss": 0.9911, + "step": 3014 + }, + { + "epoch": 0.18508855397648794, + "grad_norm": 0.6386580445186353, + "learning_rate": 1.8764981897110906e-05, + "loss": 1.0265, + "step": 3015 + }, + { + "epoch": 0.18514994321495443, + "grad_norm": 0.6622051851917055, + "learning_rate": 1.8764024522019152e-05, + "loss": 1.067, + "step": 3016 + }, + { + "epoch": 0.18521133245342092, + "grad_norm": 0.5933721812816456, + "learning_rate": 1.8763066800438638e-05, + "loss": 0.9325, + "step": 3017 + }, + { + "epoch": 0.1852727216918874, + "grad_norm": 0.6449214970149374, + "learning_rate": 1.8762108732407224e-05, + "loss": 1.0596, + "step": 3018 + }, + { + "epoch": 0.1853341109303539, + "grad_norm": 0.6827935640365898, + "learning_rate": 1.8761150317962788e-05, + "loss": 1.0815, + "step": 3019 + }, + { + "epoch": 0.1853955001688204, + "grad_norm": 0.6959810263077477, + "learning_rate": 1.876019155714322e-05, + "loss": 1.0468, + "step": 3020 + }, + { + "epoch": 0.1854568894072869, + "grad_norm": 0.6756787441449694, + "learning_rate": 1.8759232449986432e-05, + "loss": 1.0259, + "step": 3021 + }, + { + "epoch": 0.1855182786457534, + "grad_norm": 0.6465283204263316, + "learning_rate": 1.8758272996530332e-05, + "loss": 0.9887, + "step": 3022 + }, + { + "epoch": 0.1855796678842199, + "grad_norm": 0.6162466566593263, + "learning_rate": 1.8757313196812862e-05, + "loss": 0.985, + "step": 3023 + }, + { + "epoch": 0.1856410571226864, + "grad_norm": 0.6642897442659681, + "learning_rate": 1.875635305087196e-05, + "loss": 0.9541, + "step": 3024 + }, + { + "epoch": 0.18570244636115288, + "grad_norm": 0.6510884659034227, + "learning_rate": 1.8755392558745593e-05, + "loss": 0.9749, + "step": 3025 + }, + { + "epoch": 0.1857638355996194, + "grad_norm": 0.6404685387015387, + "learning_rate": 1.875443172047173e-05, + "loss": 1.0342, + "step": 3026 + }, + { + "epoch": 0.1858252248380859, + "grad_norm": 0.6723157189953273, + "learning_rate": 1.875347053608836e-05, + "loss": 1.074, + "step": 3027 + }, + { + "epoch": 0.18588661407655238, + "grad_norm": 0.6086582364731545, + "learning_rate": 1.8752509005633482e-05, + "loss": 1.0057, + "step": 3028 + }, + { + "epoch": 0.18594800331501887, + "grad_norm": 0.6690696685147193, + "learning_rate": 1.875154712914511e-05, + "loss": 0.9948, + "step": 3029 + }, + { + "epoch": 0.18600939255348536, + "grad_norm": 0.6215752002147285, + "learning_rate": 1.8750584906661274e-05, + "loss": 0.9779, + "step": 3030 + }, + { + "epoch": 0.18607078179195188, + "grad_norm": 0.5554144945571319, + "learning_rate": 1.8749622338220016e-05, + "loss": 0.9297, + "step": 3031 + }, + { + "epoch": 0.18613217103041838, + "grad_norm": 0.6221820627596821, + "learning_rate": 1.8748659423859393e-05, + "loss": 0.9785, + "step": 3032 + }, + { + "epoch": 0.18619356026888487, + "grad_norm": 0.7171186125685817, + "learning_rate": 1.8747696163617467e-05, + "loss": 1.0585, + "step": 3033 + }, + { + "epoch": 0.18625494950735136, + "grad_norm": 0.6789809011170463, + "learning_rate": 1.874673255753233e-05, + "loss": 1.0262, + "step": 3034 + }, + { + "epoch": 0.18631633874581785, + "grad_norm": 0.6733265233580129, + "learning_rate": 1.8745768605642074e-05, + "loss": 1.0568, + "step": 3035 + }, + { + "epoch": 0.18637772798428434, + "grad_norm": 0.6208266154432261, + "learning_rate": 1.8744804307984806e-05, + "loss": 0.996, + "step": 3036 + }, + { + "epoch": 0.18643911722275086, + "grad_norm": 0.6519810183775715, + "learning_rate": 1.8743839664598654e-05, + "loss": 1.0515, + "step": 3037 + }, + { + "epoch": 0.18650050646121735, + "grad_norm": 0.6311443469307586, + "learning_rate": 1.8742874675521757e-05, + "loss": 0.9668, + "step": 3038 + }, + { + "epoch": 0.18656189569968384, + "grad_norm": 0.6283495478074906, + "learning_rate": 1.874190934079226e-05, + "loss": 0.9928, + "step": 3039 + }, + { + "epoch": 0.18662328493815034, + "grad_norm": 0.6197043154757318, + "learning_rate": 1.8740943660448336e-05, + "loss": 0.9878, + "step": 3040 + }, + { + "epoch": 0.18668467417661683, + "grad_norm": 0.7106731757126827, + "learning_rate": 1.873997763452816e-05, + "loss": 0.9694, + "step": 3041 + }, + { + "epoch": 0.18674606341508335, + "grad_norm": 0.6291535051468445, + "learning_rate": 1.873901126306992e-05, + "loss": 1.0508, + "step": 3042 + }, + { + "epoch": 0.18680745265354984, + "grad_norm": 0.6361192484381066, + "learning_rate": 1.8738044546111824e-05, + "loss": 1.0133, + "step": 3043 + }, + { + "epoch": 0.18686884189201633, + "grad_norm": 0.6553236484727044, + "learning_rate": 1.8737077483692097e-05, + "loss": 1.0277, + "step": 3044 + }, + { + "epoch": 0.18693023113048282, + "grad_norm": 0.6536413727627303, + "learning_rate": 1.8736110075848967e-05, + "loss": 1.0604, + "step": 3045 + }, + { + "epoch": 0.1869916203689493, + "grad_norm": 0.6057097233209997, + "learning_rate": 1.8735142322620678e-05, + "loss": 0.9953, + "step": 3046 + }, + { + "epoch": 0.18705300960741583, + "grad_norm": 0.6497807003644235, + "learning_rate": 1.8734174224045496e-05, + "loss": 1.0638, + "step": 3047 + }, + { + "epoch": 0.18711439884588232, + "grad_norm": 0.6333516865385892, + "learning_rate": 1.8733205780161694e-05, + "loss": 1.015, + "step": 3048 + }, + { + "epoch": 0.18717578808434882, + "grad_norm": 0.6114600023113391, + "learning_rate": 1.873223699100756e-05, + "loss": 0.9865, + "step": 3049 + }, + { + "epoch": 0.1872371773228153, + "grad_norm": 0.6417190119888322, + "learning_rate": 1.8731267856621392e-05, + "loss": 1.036, + "step": 3050 + }, + { + "epoch": 0.1872985665612818, + "grad_norm": 0.606825121010391, + "learning_rate": 1.873029837704151e-05, + "loss": 0.9896, + "step": 3051 + }, + { + "epoch": 0.18735995579974832, + "grad_norm": 0.6571470971906597, + "learning_rate": 1.872932855230624e-05, + "loss": 1.0587, + "step": 3052 + }, + { + "epoch": 0.1874213450382148, + "grad_norm": 0.630452749447464, + "learning_rate": 1.8728358382453923e-05, + "loss": 1.0101, + "step": 3053 + }, + { + "epoch": 0.1874827342766813, + "grad_norm": 0.6865550940418699, + "learning_rate": 1.872738786752292e-05, + "loss": 1.0414, + "step": 3054 + }, + { + "epoch": 0.1875441235151478, + "grad_norm": 0.654049031057672, + "learning_rate": 1.872641700755159e-05, + "loss": 1.0341, + "step": 3055 + }, + { + "epoch": 0.18760551275361428, + "grad_norm": 0.6141299677751586, + "learning_rate": 1.872544580257833e-05, + "loss": 0.9823, + "step": 3056 + }, + { + "epoch": 0.18766690199208078, + "grad_norm": 0.6970729552645406, + "learning_rate": 1.872447425264153e-05, + "loss": 1.1176, + "step": 3057 + }, + { + "epoch": 0.1877282912305473, + "grad_norm": 0.6414625650075974, + "learning_rate": 1.87235023577796e-05, + "loss": 1.0064, + "step": 3058 + }, + { + "epoch": 0.1877896804690138, + "grad_norm": 0.5937312381153752, + "learning_rate": 1.8722530118030966e-05, + "loss": 1.0111, + "step": 3059 + }, + { + "epoch": 0.18785106970748028, + "grad_norm": 0.6621449334898074, + "learning_rate": 1.872155753343406e-05, + "loss": 0.9702, + "step": 3060 + }, + { + "epoch": 0.18791245894594677, + "grad_norm": 0.6833772184161298, + "learning_rate": 1.8720584604027344e-05, + "loss": 1.0543, + "step": 3061 + }, + { + "epoch": 0.18797384818441326, + "grad_norm": 0.6256791781867702, + "learning_rate": 1.871961132984928e-05, + "loss": 0.9631, + "step": 3062 + }, + { + "epoch": 0.18803523742287978, + "grad_norm": 0.6413530118652686, + "learning_rate": 1.8718637710938336e-05, + "loss": 1.0431, + "step": 3063 + }, + { + "epoch": 0.18809662666134627, + "grad_norm": 0.6800986392542634, + "learning_rate": 1.871766374733302e-05, + "loss": 1.04, + "step": 3064 + }, + { + "epoch": 0.18815801589981276, + "grad_norm": 0.6475182550590897, + "learning_rate": 1.8716689439071827e-05, + "loss": 1.0149, + "step": 3065 + }, + { + "epoch": 0.18821940513827926, + "grad_norm": 0.6661550749524124, + "learning_rate": 1.871571478619328e-05, + "loss": 1.0384, + "step": 3066 + }, + { + "epoch": 0.18828079437674575, + "grad_norm": 0.619410444554572, + "learning_rate": 1.8714739788735917e-05, + "loss": 1.0197, + "step": 3067 + }, + { + "epoch": 0.18834218361521227, + "grad_norm": 0.593243052030775, + "learning_rate": 1.8713764446738277e-05, + "loss": 0.9374, + "step": 3068 + }, + { + "epoch": 0.18840357285367876, + "grad_norm": 0.6122547387227083, + "learning_rate": 1.8712788760238923e-05, + "loss": 0.9984, + "step": 3069 + }, + { + "epoch": 0.18846496209214525, + "grad_norm": 0.6741233161363057, + "learning_rate": 1.8711812729276433e-05, + "loss": 1.0176, + "step": 3070 + }, + { + "epoch": 0.18852635133061174, + "grad_norm": 0.6268314096762931, + "learning_rate": 1.871083635388939e-05, + "loss": 1.0384, + "step": 3071 + }, + { + "epoch": 0.18858774056907823, + "grad_norm": 0.6222625149612587, + "learning_rate": 1.8709859634116396e-05, + "loss": 0.9648, + "step": 3072 + }, + { + "epoch": 0.18864912980754472, + "grad_norm": 0.6246893321396811, + "learning_rate": 1.870888256999607e-05, + "loss": 0.9913, + "step": 3073 + }, + { + "epoch": 0.18871051904601124, + "grad_norm": 0.6687572911985188, + "learning_rate": 1.8707905161567033e-05, + "loss": 1.0488, + "step": 3074 + }, + { + "epoch": 0.18877190828447774, + "grad_norm": 0.6419077192196042, + "learning_rate": 1.8706927408867936e-05, + "loss": 0.9549, + "step": 3075 + }, + { + "epoch": 0.18883329752294423, + "grad_norm": 0.6674339804655629, + "learning_rate": 1.8705949311937427e-05, + "loss": 1.0334, + "step": 3076 + }, + { + "epoch": 0.18889468676141072, + "grad_norm": 0.7277407729486617, + "learning_rate": 1.8704970870814186e-05, + "loss": 1.0419, + "step": 3077 + }, + { + "epoch": 0.1889560759998772, + "grad_norm": 0.6084216339338225, + "learning_rate": 1.870399208553688e-05, + "loss": 0.9869, + "step": 3078 + }, + { + "epoch": 0.18901746523834373, + "grad_norm": 0.6238983256899753, + "learning_rate": 1.870301295614422e-05, + "loss": 0.9571, + "step": 3079 + }, + { + "epoch": 0.18907885447681022, + "grad_norm": 0.6329615383871664, + "learning_rate": 1.870203348267491e-05, + "loss": 1.0211, + "step": 3080 + }, + { + "epoch": 0.1891402437152767, + "grad_norm": 0.7031155327907265, + "learning_rate": 1.8701053665167673e-05, + "loss": 1.0332, + "step": 3081 + }, + { + "epoch": 0.1892016329537432, + "grad_norm": 0.7300780729664603, + "learning_rate": 1.8700073503661254e-05, + "loss": 1.0454, + "step": 3082 + }, + { + "epoch": 0.1892630221922097, + "grad_norm": 0.687700531547152, + "learning_rate": 1.869909299819439e-05, + "loss": 1.0289, + "step": 3083 + }, + { + "epoch": 0.18932441143067621, + "grad_norm": 0.6789887110500639, + "learning_rate": 1.869811214880586e-05, + "loss": 1.0206, + "step": 3084 + }, + { + "epoch": 0.1893858006691427, + "grad_norm": 0.5969044785999513, + "learning_rate": 1.8697130955534432e-05, + "loss": 0.9626, + "step": 3085 + }, + { + "epoch": 0.1894471899076092, + "grad_norm": 0.6201823272029678, + "learning_rate": 1.8696149418418903e-05, + "loss": 0.9856, + "step": 3086 + }, + { + "epoch": 0.1895085791460757, + "grad_norm": 0.6447192118023075, + "learning_rate": 1.869516753749808e-05, + "loss": 1.0494, + "step": 3087 + }, + { + "epoch": 0.18956996838454218, + "grad_norm": 0.6646775498000151, + "learning_rate": 1.8694185312810775e-05, + "loss": 0.969, + "step": 3088 + }, + { + "epoch": 0.18963135762300867, + "grad_norm": 0.6615100172356877, + "learning_rate": 1.869320274439583e-05, + "loss": 1.0461, + "step": 3089 + }, + { + "epoch": 0.1896927468614752, + "grad_norm": 0.6048474540005346, + "learning_rate": 1.869221983229208e-05, + "loss": 0.9431, + "step": 3090 + }, + { + "epoch": 0.18975413609994168, + "grad_norm": 0.6558181303165862, + "learning_rate": 1.8691236576538393e-05, + "loss": 1.0463, + "step": 3091 + }, + { + "epoch": 0.18981552533840818, + "grad_norm": 0.6049576668334844, + "learning_rate": 1.869025297717364e-05, + "loss": 1.006, + "step": 3092 + }, + { + "epoch": 0.18987691457687467, + "grad_norm": 0.6926102254026799, + "learning_rate": 1.868926903423671e-05, + "loss": 1.0327, + "step": 3093 + }, + { + "epoch": 0.18993830381534116, + "grad_norm": 0.612106571953873, + "learning_rate": 1.8688284747766498e-05, + "loss": 0.9913, + "step": 3094 + }, + { + "epoch": 0.18999969305380768, + "grad_norm": 0.6654420118304509, + "learning_rate": 1.8687300117801927e-05, + "loss": 1.0402, + "step": 3095 + }, + { + "epoch": 0.19006108229227417, + "grad_norm": 0.6132427594167803, + "learning_rate": 1.8686315144381914e-05, + "loss": 0.9935, + "step": 3096 + }, + { + "epoch": 0.19012247153074066, + "grad_norm": 0.6453835166547633, + "learning_rate": 1.8685329827545407e-05, + "loss": 1.0018, + "step": 3097 + }, + { + "epoch": 0.19018386076920715, + "grad_norm": 0.7015138416419868, + "learning_rate": 1.8684344167331362e-05, + "loss": 1.0144, + "step": 3098 + }, + { + "epoch": 0.19024525000767364, + "grad_norm": 0.651428494272002, + "learning_rate": 1.8683358163778743e-05, + "loss": 1.0186, + "step": 3099 + }, + { + "epoch": 0.19030663924614016, + "grad_norm": 0.655059883537817, + "learning_rate": 1.8682371816926533e-05, + "loss": 0.9859, + "step": 3100 + }, + { + "epoch": 0.19036802848460666, + "grad_norm": 0.6178240351322267, + "learning_rate": 1.868138512681373e-05, + "loss": 0.9913, + "step": 3101 + }, + { + "epoch": 0.19042941772307315, + "grad_norm": 0.6593820072542653, + "learning_rate": 1.868039809347934e-05, + "loss": 0.9974, + "step": 3102 + }, + { + "epoch": 0.19049080696153964, + "grad_norm": 0.5710781152330009, + "learning_rate": 1.867941071696239e-05, + "loss": 0.9721, + "step": 3103 + }, + { + "epoch": 0.19055219620000613, + "grad_norm": 0.669488077334532, + "learning_rate": 1.8678422997301912e-05, + "loss": 0.9677, + "step": 3104 + }, + { + "epoch": 0.19061358543847265, + "grad_norm": 0.646965521240002, + "learning_rate": 1.8677434934536958e-05, + "loss": 1.0448, + "step": 3105 + }, + { + "epoch": 0.19067497467693914, + "grad_norm": 0.6588092491190397, + "learning_rate": 1.867644652870659e-05, + "loss": 0.9719, + "step": 3106 + }, + { + "epoch": 0.19073636391540563, + "grad_norm": 0.6804058159541243, + "learning_rate": 1.867545777984989e-05, + "loss": 1.014, + "step": 3107 + }, + { + "epoch": 0.19079775315387212, + "grad_norm": 0.7117561383299372, + "learning_rate": 1.867446868800594e-05, + "loss": 1.0111, + "step": 3108 + }, + { + "epoch": 0.19085914239233862, + "grad_norm": 0.6464282948679572, + "learning_rate": 1.8673479253213848e-05, + "loss": 1.026, + "step": 3109 + }, + { + "epoch": 0.1909205316308051, + "grad_norm": 0.6395363420056533, + "learning_rate": 1.867248947551273e-05, + "loss": 0.9792, + "step": 3110 + }, + { + "epoch": 0.19098192086927163, + "grad_norm": 0.6815199219844715, + "learning_rate": 1.8671499354941726e-05, + "loss": 1.0375, + "step": 3111 + }, + { + "epoch": 0.19104331010773812, + "grad_norm": 0.6154888034740321, + "learning_rate": 1.867050889153997e-05, + "loss": 0.9619, + "step": 3112 + }, + { + "epoch": 0.1911046993462046, + "grad_norm": 0.5835322254970914, + "learning_rate": 1.8669518085346624e-05, + "loss": 0.9513, + "step": 3113 + }, + { + "epoch": 0.1911660885846711, + "grad_norm": 0.6419225458639946, + "learning_rate": 1.8668526936400863e-05, + "loss": 0.9842, + "step": 3114 + }, + { + "epoch": 0.1912274778231376, + "grad_norm": 0.7233112715440776, + "learning_rate": 1.866753544474187e-05, + "loss": 1.0465, + "step": 3115 + }, + { + "epoch": 0.1912888670616041, + "grad_norm": 0.6425419867414739, + "learning_rate": 1.866654361040884e-05, + "loss": 1.0226, + "step": 3116 + }, + { + "epoch": 0.1913502563000706, + "grad_norm": 0.5625353265280313, + "learning_rate": 1.8665551433440988e-05, + "loss": 0.9716, + "step": 3117 + }, + { + "epoch": 0.1914116455385371, + "grad_norm": 0.6326920225957907, + "learning_rate": 1.8664558913877548e-05, + "loss": 1.0249, + "step": 3118 + }, + { + "epoch": 0.1914730347770036, + "grad_norm": 0.6308477295963428, + "learning_rate": 1.8663566051757747e-05, + "loss": 0.9688, + "step": 3119 + }, + { + "epoch": 0.19153442401547008, + "grad_norm": 0.6423989760374899, + "learning_rate": 1.8662572847120845e-05, + "loss": 1.0585, + "step": 3120 + }, + { + "epoch": 0.1915958132539366, + "grad_norm": 0.6445818890283675, + "learning_rate": 1.866157930000611e-05, + "loss": 1.0287, + "step": 3121 + }, + { + "epoch": 0.1916572024924031, + "grad_norm": 0.6315085749772894, + "learning_rate": 1.8660585410452818e-05, + "loss": 1.0537, + "step": 3122 + }, + { + "epoch": 0.19171859173086958, + "grad_norm": 0.6518866317315721, + "learning_rate": 1.8659591178500266e-05, + "loss": 1.0106, + "step": 3123 + }, + { + "epoch": 0.19177998096933607, + "grad_norm": 0.6319537938612954, + "learning_rate": 1.8658596604187758e-05, + "loss": 0.998, + "step": 3124 + }, + { + "epoch": 0.19184137020780256, + "grad_norm": 0.6161482151057556, + "learning_rate": 1.8657601687554616e-05, + "loss": 0.976, + "step": 3125 + }, + { + "epoch": 0.19190275944626906, + "grad_norm": 0.6814997392802631, + "learning_rate": 1.865660642864018e-05, + "loss": 0.9955, + "step": 3126 + }, + { + "epoch": 0.19196414868473557, + "grad_norm": 0.6199517142982826, + "learning_rate": 1.8655610827483788e-05, + "loss": 0.9773, + "step": 3127 + }, + { + "epoch": 0.19202553792320207, + "grad_norm": 0.6090447946717451, + "learning_rate": 1.865461488412481e-05, + "loss": 0.9632, + "step": 3128 + }, + { + "epoch": 0.19208692716166856, + "grad_norm": 0.7150061174188559, + "learning_rate": 1.8653618598602615e-05, + "loss": 1.0475, + "step": 3129 + }, + { + "epoch": 0.19214831640013505, + "grad_norm": 0.71962893994292, + "learning_rate": 1.8652621970956594e-05, + "loss": 1.0679, + "step": 3130 + }, + { + "epoch": 0.19220970563860154, + "grad_norm": 0.6791934072425934, + "learning_rate": 1.8651625001226153e-05, + "loss": 1.0099, + "step": 3131 + }, + { + "epoch": 0.19227109487706806, + "grad_norm": 0.680128869979321, + "learning_rate": 1.86506276894507e-05, + "loss": 1.0548, + "step": 3132 + }, + { + "epoch": 0.19233248411553455, + "grad_norm": 0.6716334400555453, + "learning_rate": 1.864963003566967e-05, + "loss": 1.0358, + "step": 3133 + }, + { + "epoch": 0.19239387335400104, + "grad_norm": 0.6079927469211417, + "learning_rate": 1.86486320399225e-05, + "loss": 0.9711, + "step": 3134 + }, + { + "epoch": 0.19245526259246754, + "grad_norm": 0.5695695416437281, + "learning_rate": 1.8647633702248648e-05, + "loss": 0.9591, + "step": 3135 + }, + { + "epoch": 0.19251665183093403, + "grad_norm": 0.7063507392497257, + "learning_rate": 1.864663502268759e-05, + "loss": 1.0427, + "step": 3136 + }, + { + "epoch": 0.19257804106940055, + "grad_norm": 0.639516461482057, + "learning_rate": 1.86456360012788e-05, + "loss": 0.9884, + "step": 3137 + }, + { + "epoch": 0.19263943030786704, + "grad_norm": 0.6602532932900967, + "learning_rate": 1.864463663806178e-05, + "loss": 1.0429, + "step": 3138 + }, + { + "epoch": 0.19270081954633353, + "grad_norm": 0.639038147072029, + "learning_rate": 1.864363693307604e-05, + "loss": 1.0168, + "step": 3139 + }, + { + "epoch": 0.19276220878480002, + "grad_norm": 0.6514670020431078, + "learning_rate": 1.8642636886361102e-05, + "loss": 1.0104, + "step": 3140 + }, + { + "epoch": 0.1928235980232665, + "grad_norm": 0.6810236958263925, + "learning_rate": 1.8641636497956504e-05, + "loss": 1.0325, + "step": 3141 + }, + { + "epoch": 0.19288498726173303, + "grad_norm": 0.707492544006931, + "learning_rate": 1.8640635767901796e-05, + "loss": 1.0869, + "step": 3142 + }, + { + "epoch": 0.19294637650019952, + "grad_norm": 0.647563063204901, + "learning_rate": 1.8639634696236542e-05, + "loss": 1.0089, + "step": 3143 + }, + { + "epoch": 0.19300776573866602, + "grad_norm": 0.6122468872721932, + "learning_rate": 1.8638633283000323e-05, + "loss": 0.9497, + "step": 3144 + }, + { + "epoch": 0.1930691549771325, + "grad_norm": 0.6476856504406165, + "learning_rate": 1.863763152823273e-05, + "loss": 0.9602, + "step": 3145 + }, + { + "epoch": 0.193130544215599, + "grad_norm": 0.6700725930037611, + "learning_rate": 1.863662943197336e-05, + "loss": 1.0433, + "step": 3146 + }, + { + "epoch": 0.1931919334540655, + "grad_norm": 0.6262755468382964, + "learning_rate": 1.863562699426184e-05, + "loss": 0.9693, + "step": 3147 + }, + { + "epoch": 0.193253322692532, + "grad_norm": 0.6204591122345593, + "learning_rate": 1.863462421513779e-05, + "loss": 0.9613, + "step": 3148 + }, + { + "epoch": 0.1933147119309985, + "grad_norm": 0.6646173824236274, + "learning_rate": 1.8633621094640873e-05, + "loss": 1.0028, + "step": 3149 + }, + { + "epoch": 0.193376101169465, + "grad_norm": 0.6478419109145029, + "learning_rate": 1.8632617632810737e-05, + "loss": 1.0813, + "step": 3150 + }, + { + "epoch": 0.19343749040793148, + "grad_norm": 0.6353170280043491, + "learning_rate": 1.8631613829687053e-05, + "loss": 0.9757, + "step": 3151 + }, + { + "epoch": 0.19349887964639798, + "grad_norm": 0.6034072008391402, + "learning_rate": 1.863060968530951e-05, + "loss": 0.9831, + "step": 3152 + }, + { + "epoch": 0.1935602688848645, + "grad_norm": 0.6646420950469002, + "learning_rate": 1.8629605199717805e-05, + "loss": 1.0, + "step": 3153 + }, + { + "epoch": 0.193621658123331, + "grad_norm": 0.6361849398821743, + "learning_rate": 1.8628600372951656e-05, + "loss": 1.0189, + "step": 3154 + }, + { + "epoch": 0.19368304736179748, + "grad_norm": 0.6412678684001264, + "learning_rate": 1.862759520505078e-05, + "loss": 0.9678, + "step": 3155 + }, + { + "epoch": 0.19374443660026397, + "grad_norm": 0.6485565269939465, + "learning_rate": 1.8626589696054927e-05, + "loss": 1.0058, + "step": 3156 + }, + { + "epoch": 0.19380582583873046, + "grad_norm": 0.6922280329238204, + "learning_rate": 1.8625583846003843e-05, + "loss": 1.0134, + "step": 3157 + }, + { + "epoch": 0.19386721507719698, + "grad_norm": 0.63148630913106, + "learning_rate": 1.8624577654937294e-05, + "loss": 0.9834, + "step": 3158 + }, + { + "epoch": 0.19392860431566347, + "grad_norm": 0.6830655229763892, + "learning_rate": 1.8623571122895065e-05, + "loss": 1.0712, + "step": 3159 + }, + { + "epoch": 0.19398999355412996, + "grad_norm": 0.5622873519965311, + "learning_rate": 1.862256424991695e-05, + "loss": 0.9361, + "step": 3160 + }, + { + "epoch": 0.19405138279259646, + "grad_norm": 0.6344569693935865, + "learning_rate": 1.862155703604275e-05, + "loss": 0.9568, + "step": 3161 + }, + { + "epoch": 0.19411277203106295, + "grad_norm": 0.6324276446383209, + "learning_rate": 1.8620549481312293e-05, + "loss": 0.9884, + "step": 3162 + }, + { + "epoch": 0.19417416126952944, + "grad_norm": 0.6520626447737684, + "learning_rate": 1.8619541585765403e-05, + "loss": 1.0073, + "step": 3163 + }, + { + "epoch": 0.19423555050799596, + "grad_norm": 0.6936773482326278, + "learning_rate": 1.861853334944194e-05, + "loss": 1.0525, + "step": 3164 + }, + { + "epoch": 0.19429693974646245, + "grad_norm": 0.6203035778221846, + "learning_rate": 1.8617524772381753e-05, + "loss": 1.0501, + "step": 3165 + }, + { + "epoch": 0.19435832898492894, + "grad_norm": 0.6225904964639141, + "learning_rate": 1.8616515854624725e-05, + "loss": 1.0241, + "step": 3166 + }, + { + "epoch": 0.19441971822339543, + "grad_norm": 0.6742809208537486, + "learning_rate": 1.861550659621074e-05, + "loss": 1.0214, + "step": 3167 + }, + { + "epoch": 0.19448110746186192, + "grad_norm": 0.6597867364735786, + "learning_rate": 1.8614496997179703e-05, + "loss": 1.017, + "step": 3168 + }, + { + "epoch": 0.19454249670032844, + "grad_norm": 0.6056167856075032, + "learning_rate": 1.8613487057571523e-05, + "loss": 0.9836, + "step": 3169 + }, + { + "epoch": 0.19460388593879493, + "grad_norm": 0.6303576106491626, + "learning_rate": 1.861247677742613e-05, + "loss": 1.0448, + "step": 3170 + }, + { + "epoch": 0.19466527517726143, + "grad_norm": 0.6126221598175892, + "learning_rate": 1.861146615678347e-05, + "loss": 0.9594, + "step": 3171 + }, + { + "epoch": 0.19472666441572792, + "grad_norm": 0.7008660591530786, + "learning_rate": 1.8610455195683497e-05, + "loss": 1.0739, + "step": 3172 + }, + { + "epoch": 0.1947880536541944, + "grad_norm": 0.6447126517276113, + "learning_rate": 1.8609443894166176e-05, + "loss": 1.0175, + "step": 3173 + }, + { + "epoch": 0.19484944289266093, + "grad_norm": 0.6990236545471706, + "learning_rate": 1.860843225227149e-05, + "loss": 1.0485, + "step": 3174 + }, + { + "epoch": 0.19491083213112742, + "grad_norm": 0.6617888243813342, + "learning_rate": 1.860742027003944e-05, + "loss": 1.0238, + "step": 3175 + }, + { + "epoch": 0.1949722213695939, + "grad_norm": 0.6169869158194724, + "learning_rate": 1.8606407947510026e-05, + "loss": 0.9934, + "step": 3176 + }, + { + "epoch": 0.1950336106080604, + "grad_norm": 0.676090767194794, + "learning_rate": 1.8605395284723277e-05, + "loss": 0.9981, + "step": 3177 + }, + { + "epoch": 0.1950949998465269, + "grad_norm": 0.6422975299361298, + "learning_rate": 1.860438228171923e-05, + "loss": 1.0113, + "step": 3178 + }, + { + "epoch": 0.1951563890849934, + "grad_norm": 0.5983133789423084, + "learning_rate": 1.860336893853793e-05, + "loss": 1.0043, + "step": 3179 + }, + { + "epoch": 0.1952177783234599, + "grad_norm": 0.655420024830359, + "learning_rate": 1.8602355255219443e-05, + "loss": 1.0226, + "step": 3180 + }, + { + "epoch": 0.1952791675619264, + "grad_norm": 0.6333440808023447, + "learning_rate": 1.8601341231803844e-05, + "loss": 0.9789, + "step": 3181 + }, + { + "epoch": 0.1953405568003929, + "grad_norm": 0.6252021234353584, + "learning_rate": 1.860032686833122e-05, + "loss": 1.0298, + "step": 3182 + }, + { + "epoch": 0.19540194603885938, + "grad_norm": 0.6096855983728333, + "learning_rate": 1.859931216484168e-05, + "loss": 0.9913, + "step": 3183 + }, + { + "epoch": 0.19546333527732587, + "grad_norm": 0.5963210245316967, + "learning_rate": 1.859829712137534e-05, + "loss": 1.0036, + "step": 3184 + }, + { + "epoch": 0.1955247245157924, + "grad_norm": 0.6246284284114102, + "learning_rate": 1.8597281737972323e-05, + "loss": 1.0209, + "step": 3185 + }, + { + "epoch": 0.19558611375425888, + "grad_norm": 0.6707478482837544, + "learning_rate": 1.859626601467278e-05, + "loss": 1.0234, + "step": 3186 + }, + { + "epoch": 0.19564750299272538, + "grad_norm": 0.6349339566284733, + "learning_rate": 1.8595249951516862e-05, + "loss": 1.0387, + "step": 3187 + }, + { + "epoch": 0.19570889223119187, + "grad_norm": 0.6806587322662533, + "learning_rate": 1.8594233548544746e-05, + "loss": 1.0521, + "step": 3188 + }, + { + "epoch": 0.19577028146965836, + "grad_norm": 0.5989867226155985, + "learning_rate": 1.8593216805796612e-05, + "loss": 0.9759, + "step": 3189 + }, + { + "epoch": 0.19583167070812488, + "grad_norm": 0.6411553817603887, + "learning_rate": 1.8592199723312657e-05, + "loss": 0.9766, + "step": 3190 + }, + { + "epoch": 0.19589305994659137, + "grad_norm": 0.6056971087405739, + "learning_rate": 1.8591182301133094e-05, + "loss": 1.0023, + "step": 3191 + }, + { + "epoch": 0.19595444918505786, + "grad_norm": 0.6210960817830516, + "learning_rate": 1.8590164539298144e-05, + "loss": 0.9938, + "step": 3192 + }, + { + "epoch": 0.19601583842352435, + "grad_norm": 0.7154605546796289, + "learning_rate": 1.858914643784805e-05, + "loss": 1.0616, + "step": 3193 + }, + { + "epoch": 0.19607722766199084, + "grad_norm": 0.6424522906239314, + "learning_rate": 1.8588127996823056e-05, + "loss": 1.0047, + "step": 3194 + }, + { + "epoch": 0.19613861690045736, + "grad_norm": 0.6566053338529569, + "learning_rate": 1.8587109216263434e-05, + "loss": 1.0373, + "step": 3195 + }, + { + "epoch": 0.19620000613892385, + "grad_norm": 0.6515635937279404, + "learning_rate": 1.858609009620945e-05, + "loss": 0.9587, + "step": 3196 + }, + { + "epoch": 0.19626139537739035, + "grad_norm": 0.7044759782451849, + "learning_rate": 1.858507063670141e-05, + "loss": 1.0117, + "step": 3197 + }, + { + "epoch": 0.19632278461585684, + "grad_norm": 0.6714332014859097, + "learning_rate": 1.8584050837779607e-05, + "loss": 1.0611, + "step": 3198 + }, + { + "epoch": 0.19638417385432333, + "grad_norm": 0.641700037035409, + "learning_rate": 1.858303069948437e-05, + "loss": 1.0296, + "step": 3199 + }, + { + "epoch": 0.19644556309278982, + "grad_norm": 0.6426019626699702, + "learning_rate": 1.8582010221856018e-05, + "loss": 0.9652, + "step": 3200 + }, + { + "epoch": 0.19650695233125634, + "grad_norm": 0.6773959732959942, + "learning_rate": 1.8580989404934902e-05, + "loss": 1.0664, + "step": 3201 + }, + { + "epoch": 0.19656834156972283, + "grad_norm": 0.6657167475415919, + "learning_rate": 1.8579968248761384e-05, + "loss": 1.0835, + "step": 3202 + }, + { + "epoch": 0.19662973080818932, + "grad_norm": 0.622310556729123, + "learning_rate": 1.8578946753375828e-05, + "loss": 0.9976, + "step": 3203 + }, + { + "epoch": 0.19669112004665582, + "grad_norm": 0.6189773159878157, + "learning_rate": 1.8577924918818626e-05, + "loss": 1.0256, + "step": 3204 + }, + { + "epoch": 0.1967525092851223, + "grad_norm": 0.6614466209084903, + "learning_rate": 1.8576902745130175e-05, + "loss": 0.9931, + "step": 3205 + }, + { + "epoch": 0.19681389852358883, + "grad_norm": 0.6594379653723036, + "learning_rate": 1.8575880232350883e-05, + "loss": 0.9853, + "step": 3206 + }, + { + "epoch": 0.19687528776205532, + "grad_norm": 0.6465184042940201, + "learning_rate": 1.857485738052118e-05, + "loss": 1.04, + "step": 3207 + }, + { + "epoch": 0.1969366770005218, + "grad_norm": 0.6528043831543627, + "learning_rate": 1.8573834189681507e-05, + "loss": 1.0175, + "step": 3208 + }, + { + "epoch": 0.1969980662389883, + "grad_norm": 0.6091373170450529, + "learning_rate": 1.8572810659872307e-05, + "loss": 0.9787, + "step": 3209 + }, + { + "epoch": 0.1970594554774548, + "grad_norm": 0.6187618728971938, + "learning_rate": 1.8571786791134054e-05, + "loss": 1.0063, + "step": 3210 + }, + { + "epoch": 0.1971208447159213, + "grad_norm": 0.6090388789176625, + "learning_rate": 1.857076258350722e-05, + "loss": 0.9814, + "step": 3211 + }, + { + "epoch": 0.1971822339543878, + "grad_norm": 0.6798677869860312, + "learning_rate": 1.8569738037032304e-05, + "loss": 1.0489, + "step": 3212 + }, + { + "epoch": 0.1972436231928543, + "grad_norm": 0.7191576640114942, + "learning_rate": 1.856871315174981e-05, + "loss": 0.7841, + "step": 3213 + }, + { + "epoch": 0.1973050124313208, + "grad_norm": 0.6506985418980531, + "learning_rate": 1.8567687927700255e-05, + "loss": 1.0214, + "step": 3214 + }, + { + "epoch": 0.19736640166978728, + "grad_norm": 0.6268738010993495, + "learning_rate": 1.8566662364924175e-05, + "loss": 0.9912, + "step": 3215 + }, + { + "epoch": 0.19742779090825377, + "grad_norm": 0.6500765142361002, + "learning_rate": 1.8565636463462113e-05, + "loss": 0.99, + "step": 3216 + }, + { + "epoch": 0.1974891801467203, + "grad_norm": 0.6545693458255619, + "learning_rate": 1.856461022335463e-05, + "loss": 1.0184, + "step": 3217 + }, + { + "epoch": 0.19755056938518678, + "grad_norm": 0.6633854310351786, + "learning_rate": 1.8563583644642298e-05, + "loss": 0.989, + "step": 3218 + }, + { + "epoch": 0.19761195862365327, + "grad_norm": 0.6528216961002615, + "learning_rate": 1.85625567273657e-05, + "loss": 1.0107, + "step": 3219 + }, + { + "epoch": 0.19767334786211976, + "grad_norm": 0.6892474029375352, + "learning_rate": 1.8561529471565442e-05, + "loss": 1.0052, + "step": 3220 + }, + { + "epoch": 0.19773473710058626, + "grad_norm": 0.6139053222403148, + "learning_rate": 1.8560501877282133e-05, + "loss": 0.9645, + "step": 3221 + }, + { + "epoch": 0.19779612633905277, + "grad_norm": 0.6103792336966752, + "learning_rate": 1.85594739445564e-05, + "loss": 1.0228, + "step": 3222 + }, + { + "epoch": 0.19785751557751927, + "grad_norm": 0.6729646668334217, + "learning_rate": 1.855844567342888e-05, + "loss": 1.0024, + "step": 3223 + }, + { + "epoch": 0.19791890481598576, + "grad_norm": 0.6830956962246183, + "learning_rate": 1.8557417063940236e-05, + "loss": 1.005, + "step": 3224 + }, + { + "epoch": 0.19798029405445225, + "grad_norm": 0.6658241322273777, + "learning_rate": 1.8556388116131122e-05, + "loss": 1.0072, + "step": 3225 + }, + { + "epoch": 0.19804168329291874, + "grad_norm": 0.5475426069270264, + "learning_rate": 1.8555358830042226e-05, + "loss": 0.9971, + "step": 3226 + }, + { + "epoch": 0.19810307253138526, + "grad_norm": 0.6088375117330228, + "learning_rate": 1.8554329205714232e-05, + "loss": 0.9463, + "step": 3227 + }, + { + "epoch": 0.19816446176985175, + "grad_norm": 0.6475704472027333, + "learning_rate": 1.855329924318786e-05, + "loss": 1.0011, + "step": 3228 + }, + { + "epoch": 0.19822585100831824, + "grad_norm": 0.611786685180343, + "learning_rate": 1.8552268942503817e-05, + "loss": 0.9962, + "step": 3229 + }, + { + "epoch": 0.19828724024678474, + "grad_norm": 0.6816355503276842, + "learning_rate": 1.8551238303702847e-05, + "loss": 1.016, + "step": 3230 + }, + { + "epoch": 0.19834862948525123, + "grad_norm": 0.689880838868186, + "learning_rate": 1.8550207326825687e-05, + "loss": 1.0194, + "step": 3231 + }, + { + "epoch": 0.19841001872371775, + "grad_norm": 0.6397270243182058, + "learning_rate": 1.85491760119131e-05, + "loss": 1.0566, + "step": 3232 + }, + { + "epoch": 0.19847140796218424, + "grad_norm": 0.702651700940396, + "learning_rate": 1.8548144359005865e-05, + "loss": 1.0529, + "step": 3233 + }, + { + "epoch": 0.19853279720065073, + "grad_norm": 0.6325858758772143, + "learning_rate": 1.8547112368144768e-05, + "loss": 1.0009, + "step": 3234 + }, + { + "epoch": 0.19859418643911722, + "grad_norm": 0.6033981255996995, + "learning_rate": 1.85460800393706e-05, + "loss": 1.0285, + "step": 3235 + }, + { + "epoch": 0.1986555756775837, + "grad_norm": 0.6237945792718214, + "learning_rate": 1.854504737272418e-05, + "loss": 0.9496, + "step": 3236 + }, + { + "epoch": 0.1987169649160502, + "grad_norm": 0.6803932578172429, + "learning_rate": 1.8544014368246343e-05, + "loss": 1.019, + "step": 3237 + }, + { + "epoch": 0.19877835415451672, + "grad_norm": 0.6133637463971917, + "learning_rate": 1.8542981025977914e-05, + "loss": 0.986, + "step": 3238 + }, + { + "epoch": 0.19883974339298321, + "grad_norm": 0.6428071939474398, + "learning_rate": 1.8541947345959753e-05, + "loss": 1.0145, + "step": 3239 + }, + { + "epoch": 0.1989011326314497, + "grad_norm": 0.6758447389729616, + "learning_rate": 1.8540913328232734e-05, + "loss": 0.9445, + "step": 3240 + }, + { + "epoch": 0.1989625218699162, + "grad_norm": 0.6579952168520811, + "learning_rate": 1.8539878972837728e-05, + "loss": 0.9779, + "step": 3241 + }, + { + "epoch": 0.1990239111083827, + "grad_norm": 0.6664995376932831, + "learning_rate": 1.853884427981563e-05, + "loss": 1.0042, + "step": 3242 + }, + { + "epoch": 0.1990853003468492, + "grad_norm": 0.7092394997847157, + "learning_rate": 1.853780924920735e-05, + "loss": 1.0659, + "step": 3243 + }, + { + "epoch": 0.1991466895853157, + "grad_norm": 0.6241615042129661, + "learning_rate": 1.853677388105381e-05, + "loss": 1.0229, + "step": 3244 + }, + { + "epoch": 0.1992080788237822, + "grad_norm": 0.6556027837829108, + "learning_rate": 1.853573817539594e-05, + "loss": 1.0144, + "step": 3245 + }, + { + "epoch": 0.19926946806224868, + "grad_norm": 0.6388706633125902, + "learning_rate": 1.8534702132274684e-05, + "loss": 1.0195, + "step": 3246 + }, + { + "epoch": 0.19933085730071518, + "grad_norm": 0.6044307041143736, + "learning_rate": 1.8533665751731006e-05, + "loss": 0.9742, + "step": 3247 + }, + { + "epoch": 0.1993922465391817, + "grad_norm": 0.6828966642483404, + "learning_rate": 1.8532629033805883e-05, + "loss": 1.0108, + "step": 3248 + }, + { + "epoch": 0.19945363577764819, + "grad_norm": 0.6002585869966062, + "learning_rate": 1.8531591978540297e-05, + "loss": 0.9597, + "step": 3249 + }, + { + "epoch": 0.19951502501611468, + "grad_norm": 0.6104014261057423, + "learning_rate": 1.8530554585975247e-05, + "loss": 0.9612, + "step": 3250 + }, + { + "epoch": 0.19957641425458117, + "grad_norm": 0.6083836982247491, + "learning_rate": 1.8529516856151755e-05, + "loss": 0.9795, + "step": 3251 + }, + { + "epoch": 0.19963780349304766, + "grad_norm": 0.6961734890339318, + "learning_rate": 1.8528478789110842e-05, + "loss": 1.0065, + "step": 3252 + }, + { + "epoch": 0.19969919273151415, + "grad_norm": 0.6673933597294361, + "learning_rate": 1.8527440384893544e-05, + "loss": 1.0052, + "step": 3253 + }, + { + "epoch": 0.19976058196998067, + "grad_norm": 0.5855725089144794, + "learning_rate": 1.8526401643540924e-05, + "loss": 0.9564, + "step": 3254 + }, + { + "epoch": 0.19982197120844716, + "grad_norm": 0.6096154568955886, + "learning_rate": 1.8525362565094043e-05, + "loss": 1.0036, + "step": 3255 + }, + { + "epoch": 0.19988336044691365, + "grad_norm": 0.6244262840684751, + "learning_rate": 1.8524323149593985e-05, + "loss": 0.9941, + "step": 3256 + }, + { + "epoch": 0.19994474968538015, + "grad_norm": 0.699367503818553, + "learning_rate": 1.852328339708184e-05, + "loss": 1.0691, + "step": 3257 + }, + { + "epoch": 0.20000613892384664, + "grad_norm": 0.6417623190618583, + "learning_rate": 1.852224330759871e-05, + "loss": 0.9858, + "step": 3258 + }, + { + "epoch": 0.20006752816231316, + "grad_norm": 0.5645271221322723, + "learning_rate": 1.8521202881185733e-05, + "loss": 0.9437, + "step": 3259 + }, + { + "epoch": 0.20012891740077965, + "grad_norm": 0.6709384765159382, + "learning_rate": 1.8520162117884027e-05, + "loss": 0.9846, + "step": 3260 + }, + { + "epoch": 0.20019030663924614, + "grad_norm": 0.6591868209209379, + "learning_rate": 1.8519121017734743e-05, + "loss": 1.0562, + "step": 3261 + }, + { + "epoch": 0.20025169587771263, + "grad_norm": 0.609616290978602, + "learning_rate": 1.8518079580779044e-05, + "loss": 0.9434, + "step": 3262 + }, + { + "epoch": 0.20031308511617912, + "grad_norm": 0.5863653943730235, + "learning_rate": 1.8517037807058095e-05, + "loss": 0.9559, + "step": 3263 + }, + { + "epoch": 0.20037447435464564, + "grad_norm": 0.6743377496259582, + "learning_rate": 1.8515995696613096e-05, + "loss": 0.9943, + "step": 3264 + }, + { + "epoch": 0.20043586359311213, + "grad_norm": 0.634744662553511, + "learning_rate": 1.8514953249485236e-05, + "loss": 1.013, + "step": 3265 + }, + { + "epoch": 0.20049725283157863, + "grad_norm": 0.619960644057128, + "learning_rate": 1.8513910465715733e-05, + "loss": 1.0187, + "step": 3266 + }, + { + "epoch": 0.20055864207004512, + "grad_norm": 0.6734898179367547, + "learning_rate": 1.851286734534582e-05, + "loss": 1.0079, + "step": 3267 + }, + { + "epoch": 0.2006200313085116, + "grad_norm": 0.601139025068393, + "learning_rate": 1.8511823888416725e-05, + "loss": 0.9437, + "step": 3268 + }, + { + "epoch": 0.2006814205469781, + "grad_norm": 0.6662098167668927, + "learning_rate": 1.8510780094969708e-05, + "loss": 1.0995, + "step": 3269 + }, + { + "epoch": 0.20074280978544462, + "grad_norm": 0.599604690685775, + "learning_rate": 1.8509735965046035e-05, + "loss": 0.92, + "step": 3270 + }, + { + "epoch": 0.2008041990239111, + "grad_norm": 0.6855234507812251, + "learning_rate": 1.8508691498686985e-05, + "loss": 1.0559, + "step": 3271 + }, + { + "epoch": 0.2008655882623776, + "grad_norm": 0.6651020469983724, + "learning_rate": 1.8507646695933855e-05, + "loss": 1.0204, + "step": 3272 + }, + { + "epoch": 0.2009269775008441, + "grad_norm": 0.6516216732246632, + "learning_rate": 1.850660155682795e-05, + "loss": 1.0015, + "step": 3273 + }, + { + "epoch": 0.2009883667393106, + "grad_norm": 0.6504519054746787, + "learning_rate": 1.8505556081410584e-05, + "loss": 0.9897, + "step": 3274 + }, + { + "epoch": 0.2010497559777771, + "grad_norm": 0.6852724359785412, + "learning_rate": 1.85045102697231e-05, + "loss": 1.0706, + "step": 3275 + }, + { + "epoch": 0.2011111452162436, + "grad_norm": 0.6547930085426258, + "learning_rate": 1.8503464121806836e-05, + "loss": 0.9877, + "step": 3276 + }, + { + "epoch": 0.2011725344547101, + "grad_norm": 0.6400773591818436, + "learning_rate": 1.8502417637703155e-05, + "loss": 0.9885, + "step": 3277 + }, + { + "epoch": 0.20123392369317658, + "grad_norm": 0.617221810262962, + "learning_rate": 1.8501370817453435e-05, + "loss": 1.0024, + "step": 3278 + }, + { + "epoch": 0.20129531293164307, + "grad_norm": 0.6105845151865251, + "learning_rate": 1.8500323661099057e-05, + "loss": 0.9252, + "step": 3279 + }, + { + "epoch": 0.2013567021701096, + "grad_norm": 0.6245040929353729, + "learning_rate": 1.849927616868142e-05, + "loss": 1.0158, + "step": 3280 + }, + { + "epoch": 0.20141809140857608, + "grad_norm": 0.6162219252736383, + "learning_rate": 1.849822834024194e-05, + "loss": 0.9478, + "step": 3281 + }, + { + "epoch": 0.20147948064704257, + "grad_norm": 0.6620955281768743, + "learning_rate": 1.849718017582204e-05, + "loss": 1.0766, + "step": 3282 + }, + { + "epoch": 0.20154086988550907, + "grad_norm": 0.596938835280662, + "learning_rate": 1.8496131675463163e-05, + "loss": 0.9822, + "step": 3283 + }, + { + "epoch": 0.20160225912397556, + "grad_norm": 0.6476802640606465, + "learning_rate": 1.8495082839206762e-05, + "loss": 1.0653, + "step": 3284 + }, + { + "epoch": 0.20166364836244208, + "grad_norm": 0.696816253601024, + "learning_rate": 1.84940336670943e-05, + "loss": 1.0551, + "step": 3285 + }, + { + "epoch": 0.20172503760090857, + "grad_norm": 0.6321773752156119, + "learning_rate": 1.8492984159167256e-05, + "loss": 0.9836, + "step": 3286 + }, + { + "epoch": 0.20178642683937506, + "grad_norm": 0.6570806281189028, + "learning_rate": 1.8491934315467126e-05, + "loss": 1.0643, + "step": 3287 + }, + { + "epoch": 0.20184781607784155, + "grad_norm": 0.6766943480090292, + "learning_rate": 1.8490884136035415e-05, + "loss": 1.0355, + "step": 3288 + }, + { + "epoch": 0.20190920531630804, + "grad_norm": 0.6714536702060022, + "learning_rate": 1.8489833620913644e-05, + "loss": 0.9805, + "step": 3289 + }, + { + "epoch": 0.20197059455477454, + "grad_norm": 0.6528101437385557, + "learning_rate": 1.8488782770143337e-05, + "loss": 1.016, + "step": 3290 + }, + { + "epoch": 0.20203198379324105, + "grad_norm": 0.6751432514551815, + "learning_rate": 1.8487731583766048e-05, + "loss": 1.0508, + "step": 3291 + }, + { + "epoch": 0.20209337303170755, + "grad_norm": 0.649304810913547, + "learning_rate": 1.8486680061823338e-05, + "loss": 1.0435, + "step": 3292 + }, + { + "epoch": 0.20215476227017404, + "grad_norm": 0.6745378735022906, + "learning_rate": 1.8485628204356773e-05, + "loss": 1.0193, + "step": 3293 + }, + { + "epoch": 0.20221615150864053, + "grad_norm": 0.6580258826369061, + "learning_rate": 1.8484576011407938e-05, + "loss": 1.0196, + "step": 3294 + }, + { + "epoch": 0.20227754074710702, + "grad_norm": 0.6329790598451829, + "learning_rate": 1.8483523483018437e-05, + "loss": 0.9719, + "step": 3295 + }, + { + "epoch": 0.20233892998557354, + "grad_norm": 0.6250517840834018, + "learning_rate": 1.848247061922988e-05, + "loss": 0.9921, + "step": 3296 + }, + { + "epoch": 0.20240031922404003, + "grad_norm": 0.6152056978344931, + "learning_rate": 1.8481417420083892e-05, + "loss": 0.9484, + "step": 3297 + }, + { + "epoch": 0.20246170846250652, + "grad_norm": 0.6112261851982583, + "learning_rate": 1.848036388562211e-05, + "loss": 0.9913, + "step": 3298 + }, + { + "epoch": 0.20252309770097301, + "grad_norm": 0.6672592022813236, + "learning_rate": 1.8479310015886186e-05, + "loss": 0.9953, + "step": 3299 + }, + { + "epoch": 0.2025844869394395, + "grad_norm": 0.6377431435705572, + "learning_rate": 1.8478255810917793e-05, + "loss": 1.0021, + "step": 3300 + }, + { + "epoch": 0.20264587617790603, + "grad_norm": 0.6269485211175966, + "learning_rate": 1.8477201270758597e-05, + "loss": 0.9745, + "step": 3301 + }, + { + "epoch": 0.20270726541637252, + "grad_norm": 0.6066223228976374, + "learning_rate": 1.8476146395450298e-05, + "loss": 0.9825, + "step": 3302 + }, + { + "epoch": 0.202768654654839, + "grad_norm": 0.6561655638486809, + "learning_rate": 1.8475091185034595e-05, + "loss": 1.0161, + "step": 3303 + }, + { + "epoch": 0.2028300438933055, + "grad_norm": 0.6547004854135585, + "learning_rate": 1.847403563955321e-05, + "loss": 1.0107, + "step": 3304 + }, + { + "epoch": 0.202891433131772, + "grad_norm": 0.7303172841534257, + "learning_rate": 1.847297975904788e-05, + "loss": 1.0536, + "step": 3305 + }, + { + "epoch": 0.20295282237023848, + "grad_norm": 0.6721255324228452, + "learning_rate": 1.847192354356034e-05, + "loss": 0.9994, + "step": 3306 + }, + { + "epoch": 0.203014211608705, + "grad_norm": 0.6744805103624967, + "learning_rate": 1.847086699313235e-05, + "loss": 0.9977, + "step": 3307 + }, + { + "epoch": 0.2030756008471715, + "grad_norm": 0.6609879990702453, + "learning_rate": 1.8469810107805683e-05, + "loss": 1.0429, + "step": 3308 + }, + { + "epoch": 0.203136990085638, + "grad_norm": 0.6441899567958513, + "learning_rate": 1.8468752887622123e-05, + "loss": 0.9614, + "step": 3309 + }, + { + "epoch": 0.20319837932410448, + "grad_norm": 0.6559132373046554, + "learning_rate": 1.8467695332623464e-05, + "loss": 0.9838, + "step": 3310 + }, + { + "epoch": 0.20325976856257097, + "grad_norm": 0.6331242468136415, + "learning_rate": 1.8466637442851524e-05, + "loss": 1.0164, + "step": 3311 + }, + { + "epoch": 0.2033211578010375, + "grad_norm": 0.6263568354513142, + "learning_rate": 1.8465579218348123e-05, + "loss": 0.9529, + "step": 3312 + }, + { + "epoch": 0.20338254703950398, + "grad_norm": 0.663114523637127, + "learning_rate": 1.8464520659155097e-05, + "loss": 1.0166, + "step": 3313 + }, + { + "epoch": 0.20344393627797047, + "grad_norm": 0.5954167423916876, + "learning_rate": 1.8463461765314302e-05, + "loss": 0.982, + "step": 3314 + }, + { + "epoch": 0.20350532551643696, + "grad_norm": 0.7249052920947908, + "learning_rate": 1.846240253686759e-05, + "loss": 1.0262, + "step": 3315 + }, + { + "epoch": 0.20356671475490346, + "grad_norm": 0.6346106931630157, + "learning_rate": 1.8461342973856853e-05, + "loss": 1.061, + "step": 3316 + }, + { + "epoch": 0.20362810399336997, + "grad_norm": 0.6766401681585258, + "learning_rate": 1.846028307632397e-05, + "loss": 1.0203, + "step": 3317 + }, + { + "epoch": 0.20368949323183647, + "grad_norm": 0.646998571731235, + "learning_rate": 1.845922284431085e-05, + "loss": 0.9716, + "step": 3318 + }, + { + "epoch": 0.20375088247030296, + "grad_norm": 0.6511243717617915, + "learning_rate": 1.8458162277859406e-05, + "loss": 0.9345, + "step": 3319 + }, + { + "epoch": 0.20381227170876945, + "grad_norm": 0.6617297269267, + "learning_rate": 1.845710137701157e-05, + "loss": 1.0445, + "step": 3320 + }, + { + "epoch": 0.20387366094723594, + "grad_norm": 0.7034247266579793, + "learning_rate": 1.8456040141809284e-05, + "loss": 1.0065, + "step": 3321 + }, + { + "epoch": 0.20393505018570246, + "grad_norm": 0.6345462877069535, + "learning_rate": 1.8454978572294506e-05, + "loss": 0.989, + "step": 3322 + }, + { + "epoch": 0.20399643942416895, + "grad_norm": 0.6310785357860638, + "learning_rate": 1.8453916668509207e-05, + "loss": 0.9626, + "step": 3323 + }, + { + "epoch": 0.20405782866263544, + "grad_norm": 0.6565631118694322, + "learning_rate": 1.8452854430495363e-05, + "loss": 0.9725, + "step": 3324 + }, + { + "epoch": 0.20411921790110193, + "grad_norm": 0.677212877437587, + "learning_rate": 1.845179185829498e-05, + "loss": 1.0447, + "step": 3325 + }, + { + "epoch": 0.20418060713956843, + "grad_norm": 0.6006887700187672, + "learning_rate": 1.8450728951950056e-05, + "loss": 0.9555, + "step": 3326 + }, + { + "epoch": 0.20424199637803492, + "grad_norm": 0.5915601565517935, + "learning_rate": 1.8449665711502622e-05, + "loss": 0.9713, + "step": 3327 + }, + { + "epoch": 0.20430338561650144, + "grad_norm": 0.6480139790943266, + "learning_rate": 1.8448602136994708e-05, + "loss": 1.0144, + "step": 3328 + }, + { + "epoch": 0.20436477485496793, + "grad_norm": 0.6575579259941225, + "learning_rate": 1.844753822846837e-05, + "loss": 1.0074, + "step": 3329 + }, + { + "epoch": 0.20442616409343442, + "grad_norm": 0.6115590952678912, + "learning_rate": 1.844647398596566e-05, + "loss": 1.0075, + "step": 3330 + }, + { + "epoch": 0.2044875533319009, + "grad_norm": 0.6753187907569492, + "learning_rate": 1.844540940952866e-05, + "loss": 1.0147, + "step": 3331 + }, + { + "epoch": 0.2045489425703674, + "grad_norm": 0.6581266730289635, + "learning_rate": 1.8444344499199456e-05, + "loss": 1.0366, + "step": 3332 + }, + { + "epoch": 0.20461033180883392, + "grad_norm": 0.6397509798167398, + "learning_rate": 1.8443279255020153e-05, + "loss": 1.0097, + "step": 3333 + }, + { + "epoch": 0.20467172104730041, + "grad_norm": 0.620244773390073, + "learning_rate": 1.8442213677032862e-05, + "loss": 0.9533, + "step": 3334 + }, + { + "epoch": 0.2047331102857669, + "grad_norm": 0.634952904430711, + "learning_rate": 1.8441147765279713e-05, + "loss": 1.0233, + "step": 3335 + }, + { + "epoch": 0.2047944995242334, + "grad_norm": 0.6235676741013518, + "learning_rate": 1.8440081519802843e-05, + "loss": 1.0227, + "step": 3336 + }, + { + "epoch": 0.2048558887626999, + "grad_norm": 0.6058062869897479, + "learning_rate": 1.8439014940644412e-05, + "loss": 0.9874, + "step": 3337 + }, + { + "epoch": 0.2049172780011664, + "grad_norm": 0.672957929094694, + "learning_rate": 1.8437948027846587e-05, + "loss": 1.0007, + "step": 3338 + }, + { + "epoch": 0.2049786672396329, + "grad_norm": 0.61683382015137, + "learning_rate": 1.8436880781451545e-05, + "loss": 0.9511, + "step": 3339 + }, + { + "epoch": 0.2050400564780994, + "grad_norm": 0.6855660968227487, + "learning_rate": 1.8435813201501484e-05, + "loss": 1.0096, + "step": 3340 + }, + { + "epoch": 0.20510144571656588, + "grad_norm": 0.6722366530472741, + "learning_rate": 1.8434745288038603e-05, + "loss": 1.0188, + "step": 3341 + }, + { + "epoch": 0.20516283495503237, + "grad_norm": 0.6102115072504183, + "learning_rate": 1.8433677041105137e-05, + "loss": 0.962, + "step": 3342 + }, + { + "epoch": 0.20522422419349887, + "grad_norm": 0.6571768589478941, + "learning_rate": 1.8432608460743306e-05, + "loss": 1.013, + "step": 3343 + }, + { + "epoch": 0.20528561343196539, + "grad_norm": 0.6496647838925235, + "learning_rate": 1.8431539546995366e-05, + "loss": 1.0244, + "step": 3344 + }, + { + "epoch": 0.20534700267043188, + "grad_norm": 0.6331017333569179, + "learning_rate": 1.843047029990357e-05, + "loss": 0.9915, + "step": 3345 + }, + { + "epoch": 0.20540839190889837, + "grad_norm": 0.6223804190102892, + "learning_rate": 1.8429400719510192e-05, + "loss": 0.9634, + "step": 3346 + }, + { + "epoch": 0.20546978114736486, + "grad_norm": 0.6547673842668146, + "learning_rate": 1.8428330805857524e-05, + "loss": 0.9979, + "step": 3347 + }, + { + "epoch": 0.20553117038583135, + "grad_norm": 0.631181026767796, + "learning_rate": 1.842726055898786e-05, + "loss": 1.0093, + "step": 3348 + }, + { + "epoch": 0.20559255962429787, + "grad_norm": 0.6874245561954366, + "learning_rate": 1.8426189978943512e-05, + "loss": 1.0354, + "step": 3349 + }, + { + "epoch": 0.20565394886276436, + "grad_norm": 0.6064207931305045, + "learning_rate": 1.842511906576681e-05, + "loss": 0.9712, + "step": 3350 + }, + { + "epoch": 0.20571533810123085, + "grad_norm": 0.6287073843342155, + "learning_rate": 1.8424047819500087e-05, + "loss": 1.0128, + "step": 3351 + }, + { + "epoch": 0.20577672733969735, + "grad_norm": 0.6299387054908843, + "learning_rate": 1.84229762401857e-05, + "loss": 1.0107, + "step": 3352 + }, + { + "epoch": 0.20583811657816384, + "grad_norm": 0.7526818741905121, + "learning_rate": 1.8421904327866015e-05, + "loss": 0.7684, + "step": 3353 + }, + { + "epoch": 0.20589950581663036, + "grad_norm": 0.7101165820731672, + "learning_rate": 1.8420832082583407e-05, + "loss": 1.108, + "step": 3354 + }, + { + "epoch": 0.20596089505509685, + "grad_norm": 0.6150468595494392, + "learning_rate": 1.8419759504380274e-05, + "loss": 0.9738, + "step": 3355 + }, + { + "epoch": 0.20602228429356334, + "grad_norm": 0.6554463738645704, + "learning_rate": 1.841868659329901e-05, + "loss": 0.9942, + "step": 3356 + }, + { + "epoch": 0.20608367353202983, + "grad_norm": 0.5916405366396842, + "learning_rate": 1.841761334938204e-05, + "loss": 0.9404, + "step": 3357 + }, + { + "epoch": 0.20614506277049632, + "grad_norm": 0.6661276584387043, + "learning_rate": 1.841653977267179e-05, + "loss": 1.0202, + "step": 3358 + }, + { + "epoch": 0.20620645200896282, + "grad_norm": 0.6496237195183492, + "learning_rate": 1.8415465863210715e-05, + "loss": 0.9958, + "step": 3359 + }, + { + "epoch": 0.20626784124742933, + "grad_norm": 0.6934590864350787, + "learning_rate": 1.841439162104126e-05, + "loss": 1.0267, + "step": 3360 + }, + { + "epoch": 0.20632923048589583, + "grad_norm": 0.6596377526958974, + "learning_rate": 1.8413317046205903e-05, + "loss": 0.9899, + "step": 3361 + }, + { + "epoch": 0.20639061972436232, + "grad_norm": 0.6654121850677699, + "learning_rate": 1.841224213874713e-05, + "loss": 1.0098, + "step": 3362 + }, + { + "epoch": 0.2064520089628288, + "grad_norm": 0.6329052333089884, + "learning_rate": 1.8411166898707423e-05, + "loss": 0.9468, + "step": 3363 + }, + { + "epoch": 0.2065133982012953, + "grad_norm": 0.6883266856164296, + "learning_rate": 1.841009132612931e-05, + "loss": 1.0215, + "step": 3364 + }, + { + "epoch": 0.20657478743976182, + "grad_norm": 0.6554406844449926, + "learning_rate": 1.8409015421055305e-05, + "loss": 0.9906, + "step": 3365 + }, + { + "epoch": 0.2066361766782283, + "grad_norm": 0.6329079725450695, + "learning_rate": 1.8407939183527944e-05, + "loss": 0.9871, + "step": 3366 + }, + { + "epoch": 0.2066975659166948, + "grad_norm": 0.6706865251528417, + "learning_rate": 1.8406862613589784e-05, + "loss": 0.9838, + "step": 3367 + }, + { + "epoch": 0.2067589551551613, + "grad_norm": 0.6371265285460456, + "learning_rate": 1.8405785711283376e-05, + "loss": 0.9628, + "step": 3368 + }, + { + "epoch": 0.2068203443936278, + "grad_norm": 0.7426101754727361, + "learning_rate": 1.8404708476651303e-05, + "loss": 1.0696, + "step": 3369 + }, + { + "epoch": 0.2068817336320943, + "grad_norm": 0.6730000283400207, + "learning_rate": 1.8403630909736153e-05, + "loss": 1.022, + "step": 3370 + }, + { + "epoch": 0.2069431228705608, + "grad_norm": 1.1389246971802138, + "learning_rate": 1.840255301058053e-05, + "loss": 0.7674, + "step": 3371 + }, + { + "epoch": 0.2070045121090273, + "grad_norm": 0.6585008687284883, + "learning_rate": 1.840147477922704e-05, + "loss": 1.0067, + "step": 3372 + }, + { + "epoch": 0.20706590134749378, + "grad_norm": 0.7128333448632339, + "learning_rate": 1.8400396215718322e-05, + "loss": 1.039, + "step": 3373 + }, + { + "epoch": 0.20712729058596027, + "grad_norm": 0.6719336302693112, + "learning_rate": 1.8399317320097012e-05, + "loss": 0.9711, + "step": 3374 + }, + { + "epoch": 0.2071886798244268, + "grad_norm": 0.650767538447402, + "learning_rate": 1.8398238092405765e-05, + "loss": 1.046, + "step": 3375 + }, + { + "epoch": 0.20725006906289328, + "grad_norm": 0.6457880146833158, + "learning_rate": 1.8397158532687253e-05, + "loss": 1.0197, + "step": 3376 + }, + { + "epoch": 0.20731145830135977, + "grad_norm": 0.6234184751982313, + "learning_rate": 1.8396078640984148e-05, + "loss": 1.002, + "step": 3377 + }, + { + "epoch": 0.20737284753982627, + "grad_norm": 0.6996989997128436, + "learning_rate": 1.839499841733915e-05, + "loss": 1.0201, + "step": 3378 + }, + { + "epoch": 0.20743423677829276, + "grad_norm": 0.6457803447555459, + "learning_rate": 1.8393917861794966e-05, + "loss": 1.0042, + "step": 3379 + }, + { + "epoch": 0.20749562601675925, + "grad_norm": 0.624974049271767, + "learning_rate": 1.839283697439432e-05, + "loss": 0.9437, + "step": 3380 + }, + { + "epoch": 0.20755701525522577, + "grad_norm": 0.6281538681300513, + "learning_rate": 1.8391755755179935e-05, + "loss": 0.9694, + "step": 3381 + }, + { + "epoch": 0.20761840449369226, + "grad_norm": 0.639033577193254, + "learning_rate": 1.8390674204194563e-05, + "loss": 0.932, + "step": 3382 + }, + { + "epoch": 0.20767979373215875, + "grad_norm": 0.6472058515694421, + "learning_rate": 1.8389592321480963e-05, + "loss": 0.921, + "step": 3383 + }, + { + "epoch": 0.20774118297062524, + "grad_norm": 0.7370767388836102, + "learning_rate": 1.8388510107081908e-05, + "loss": 1.0146, + "step": 3384 + }, + { + "epoch": 0.20780257220909173, + "grad_norm": 0.6555013938895078, + "learning_rate": 1.8387427561040184e-05, + "loss": 0.987, + "step": 3385 + }, + { + "epoch": 0.20786396144755825, + "grad_norm": 0.7022562021700581, + "learning_rate": 1.838634468339859e-05, + "loss": 0.9931, + "step": 3386 + }, + { + "epoch": 0.20792535068602475, + "grad_norm": 0.6886920260535343, + "learning_rate": 1.8385261474199935e-05, + "loss": 1.0086, + "step": 3387 + }, + { + "epoch": 0.20798673992449124, + "grad_norm": 0.6455716760064756, + "learning_rate": 1.838417793348705e-05, + "loss": 0.9882, + "step": 3388 + }, + { + "epoch": 0.20804812916295773, + "grad_norm": 0.6390467685964427, + "learning_rate": 1.8383094061302767e-05, + "loss": 0.9395, + "step": 3389 + }, + { + "epoch": 0.20810951840142422, + "grad_norm": 0.6206955471282745, + "learning_rate": 1.8382009857689942e-05, + "loss": 0.98, + "step": 3390 + }, + { + "epoch": 0.20817090763989074, + "grad_norm": 0.6728336206365523, + "learning_rate": 1.8380925322691435e-05, + "loss": 1.0179, + "step": 3391 + }, + { + "epoch": 0.20823229687835723, + "grad_norm": 0.6379402316375339, + "learning_rate": 1.8379840456350126e-05, + "loss": 0.9538, + "step": 3392 + }, + { + "epoch": 0.20829368611682372, + "grad_norm": 0.6373625560333777, + "learning_rate": 1.8378755258708905e-05, + "loss": 1.0273, + "step": 3393 + }, + { + "epoch": 0.20835507535529021, + "grad_norm": 0.6693402345100853, + "learning_rate": 1.8377669729810676e-05, + "loss": 1.0025, + "step": 3394 + }, + { + "epoch": 0.2084164645937567, + "grad_norm": 0.5812233478824428, + "learning_rate": 1.8376583869698356e-05, + "loss": 1.0047, + "step": 3395 + }, + { + "epoch": 0.2084778538322232, + "grad_norm": 0.6884885282552333, + "learning_rate": 1.8375497678414877e-05, + "loss": 1.0489, + "step": 3396 + }, + { + "epoch": 0.20853924307068972, + "grad_norm": 0.6711092817912963, + "learning_rate": 1.8374411156003176e-05, + "loss": 0.9914, + "step": 3397 + }, + { + "epoch": 0.2086006323091562, + "grad_norm": 0.6146249454618907, + "learning_rate": 1.8373324302506214e-05, + "loss": 0.9127, + "step": 3398 + }, + { + "epoch": 0.2086620215476227, + "grad_norm": 0.6045565630795694, + "learning_rate": 1.8372237117966957e-05, + "loss": 0.9476, + "step": 3399 + }, + { + "epoch": 0.2087234107860892, + "grad_norm": 0.6818176439313733, + "learning_rate": 1.837114960242839e-05, + "loss": 0.9893, + "step": 3400 + }, + { + "epoch": 0.20878480002455568, + "grad_norm": 0.6431200166689177, + "learning_rate": 1.837006175593351e-05, + "loss": 0.9731, + "step": 3401 + }, + { + "epoch": 0.2088461892630222, + "grad_norm": 0.6069579419473463, + "learning_rate": 1.8368973578525318e-05, + "loss": 0.9714, + "step": 3402 + }, + { + "epoch": 0.2089075785014887, + "grad_norm": 0.8451568178284042, + "learning_rate": 1.836788507024684e-05, + "loss": 0.7271, + "step": 3403 + }, + { + "epoch": 0.20896896773995519, + "grad_norm": 0.7181752021467817, + "learning_rate": 1.8366796231141113e-05, + "loss": 1.0452, + "step": 3404 + }, + { + "epoch": 0.20903035697842168, + "grad_norm": 0.7082060615662727, + "learning_rate": 1.836570706125118e-05, + "loss": 1.0279, + "step": 3405 + }, + { + "epoch": 0.20909174621688817, + "grad_norm": 0.6458387561356148, + "learning_rate": 1.836461756062011e-05, + "loss": 1.0124, + "step": 3406 + }, + { + "epoch": 0.2091531354553547, + "grad_norm": 0.5891413726009969, + "learning_rate": 1.8363527729290965e-05, + "loss": 1.0066, + "step": 3407 + }, + { + "epoch": 0.20921452469382118, + "grad_norm": 0.6223490176767532, + "learning_rate": 1.836243756730684e-05, + "loss": 0.9658, + "step": 3408 + }, + { + "epoch": 0.20927591393228767, + "grad_norm": 0.6730693760358406, + "learning_rate": 1.836134707471083e-05, + "loss": 0.9837, + "step": 3409 + }, + { + "epoch": 0.20933730317075416, + "grad_norm": 0.6487692936962279, + "learning_rate": 1.836025625154605e-05, + "loss": 0.9785, + "step": 3410 + }, + { + "epoch": 0.20939869240922065, + "grad_norm": 0.6593781080338538, + "learning_rate": 1.835916509785563e-05, + "loss": 1.0088, + "step": 3411 + }, + { + "epoch": 0.20946008164768717, + "grad_norm": 0.6193298668603376, + "learning_rate": 1.8358073613682705e-05, + "loss": 0.9818, + "step": 3412 + }, + { + "epoch": 0.20952147088615367, + "grad_norm": 0.6959666599893539, + "learning_rate": 1.8356981799070427e-05, + "loss": 0.9911, + "step": 3413 + }, + { + "epoch": 0.20958286012462016, + "grad_norm": 0.6442717533724176, + "learning_rate": 1.835588965406196e-05, + "loss": 1.0533, + "step": 3414 + }, + { + "epoch": 0.20964424936308665, + "grad_norm": 0.6000268893104708, + "learning_rate": 1.8354797178700487e-05, + "loss": 0.9826, + "step": 3415 + }, + { + "epoch": 0.20970563860155314, + "grad_norm": 0.6786361066438695, + "learning_rate": 1.83537043730292e-05, + "loss": 0.9925, + "step": 3416 + }, + { + "epoch": 0.20976702784001963, + "grad_norm": 0.69146330580774, + "learning_rate": 1.8352611237091296e-05, + "loss": 1.0288, + "step": 3417 + }, + { + "epoch": 0.20982841707848615, + "grad_norm": 0.6191641257607803, + "learning_rate": 1.8351517770929997e-05, + "loss": 0.977, + "step": 3418 + }, + { + "epoch": 0.20988980631695264, + "grad_norm": 0.671043505511043, + "learning_rate": 1.8350423974588536e-05, + "loss": 1.0186, + "step": 3419 + }, + { + "epoch": 0.20995119555541913, + "grad_norm": 0.6568170451958278, + "learning_rate": 1.834932984811015e-05, + "loss": 0.952, + "step": 3420 + }, + { + "epoch": 0.21001258479388563, + "grad_norm": 0.6408111787320495, + "learning_rate": 1.8348235391538104e-05, + "loss": 0.9908, + "step": 3421 + }, + { + "epoch": 0.21007397403235212, + "grad_norm": 0.6845143831674741, + "learning_rate": 1.8347140604915662e-05, + "loss": 0.9783, + "step": 3422 + }, + { + "epoch": 0.21013536327081864, + "grad_norm": 0.6773415307615154, + "learning_rate": 1.8346045488286108e-05, + "loss": 0.9985, + "step": 3423 + }, + { + "epoch": 0.21019675250928513, + "grad_norm": 0.6350943177910647, + "learning_rate": 1.834495004169274e-05, + "loss": 0.9604, + "step": 3424 + }, + { + "epoch": 0.21025814174775162, + "grad_norm": 0.6214150237316015, + "learning_rate": 1.8343854265178863e-05, + "loss": 0.9944, + "step": 3425 + }, + { + "epoch": 0.2103195309862181, + "grad_norm": 0.6862254322415876, + "learning_rate": 1.83427581587878e-05, + "loss": 1.0238, + "step": 3426 + }, + { + "epoch": 0.2103809202246846, + "grad_norm": 0.6200588787283227, + "learning_rate": 1.8341661722562886e-05, + "loss": 0.9587, + "step": 3427 + }, + { + "epoch": 0.21044230946315112, + "grad_norm": 0.6667716724737237, + "learning_rate": 1.834056495654747e-05, + "loss": 0.9553, + "step": 3428 + }, + { + "epoch": 0.21050369870161761, + "grad_norm": 0.6703646809199449, + "learning_rate": 1.8339467860784913e-05, + "loss": 1.0585, + "step": 3429 + }, + { + "epoch": 0.2105650879400841, + "grad_norm": 0.614383911163635, + "learning_rate": 1.8338370435318592e-05, + "loss": 1.002, + "step": 3430 + }, + { + "epoch": 0.2106264771785506, + "grad_norm": 0.6126011835155786, + "learning_rate": 1.833727268019189e-05, + "loss": 0.9092, + "step": 3431 + }, + { + "epoch": 0.2106878664170171, + "grad_norm": 0.6580207030399831, + "learning_rate": 1.8336174595448205e-05, + "loss": 1.0439, + "step": 3432 + }, + { + "epoch": 0.21074925565548358, + "grad_norm": 0.6431888427033132, + "learning_rate": 1.8335076181130956e-05, + "loss": 0.9992, + "step": 3433 + }, + { + "epoch": 0.2108106448939501, + "grad_norm": 0.6416052382150644, + "learning_rate": 1.8333977437283566e-05, + "loss": 1.0087, + "step": 3434 + }, + { + "epoch": 0.2108720341324166, + "grad_norm": 0.646484113962192, + "learning_rate": 1.8332878363949476e-05, + "loss": 0.9515, + "step": 3435 + }, + { + "epoch": 0.21093342337088308, + "grad_norm": 0.6689359775279639, + "learning_rate": 1.8331778961172134e-05, + "loss": 1.011, + "step": 3436 + }, + { + "epoch": 0.21099481260934957, + "grad_norm": 0.6275289496097619, + "learning_rate": 1.8330679228995008e-05, + "loss": 0.9683, + "step": 3437 + }, + { + "epoch": 0.21105620184781607, + "grad_norm": 0.6258301988361255, + "learning_rate": 1.832957916746158e-05, + "loss": 0.9483, + "step": 3438 + }, + { + "epoch": 0.21111759108628259, + "grad_norm": 0.6392744003013142, + "learning_rate": 1.8328478776615336e-05, + "loss": 0.9802, + "step": 3439 + }, + { + "epoch": 0.21117898032474908, + "grad_norm": 0.6397760468231835, + "learning_rate": 1.8327378056499784e-05, + "loss": 0.9398, + "step": 3440 + }, + { + "epoch": 0.21124036956321557, + "grad_norm": 0.6561648378177793, + "learning_rate": 1.8326277007158436e-05, + "loss": 0.9421, + "step": 3441 + }, + { + "epoch": 0.21130175880168206, + "grad_norm": 0.655915242536614, + "learning_rate": 1.8325175628634826e-05, + "loss": 1.0184, + "step": 3442 + }, + { + "epoch": 0.21136314804014855, + "grad_norm": 0.5973654139831943, + "learning_rate": 1.83240739209725e-05, + "loss": 0.9515, + "step": 3443 + }, + { + "epoch": 0.21142453727861507, + "grad_norm": 0.5732189008888544, + "learning_rate": 1.8322971884215008e-05, + "loss": 0.9479, + "step": 3444 + }, + { + "epoch": 0.21148592651708156, + "grad_norm": 0.698123882055986, + "learning_rate": 1.8321869518405926e-05, + "loss": 1.0268, + "step": 3445 + }, + { + "epoch": 0.21154731575554805, + "grad_norm": 0.6527757547505405, + "learning_rate": 1.832076682358883e-05, + "loss": 1.005, + "step": 3446 + }, + { + "epoch": 0.21160870499401455, + "grad_norm": 0.6747483935218956, + "learning_rate": 1.8319663799807322e-05, + "loss": 0.987, + "step": 3447 + }, + { + "epoch": 0.21167009423248104, + "grad_norm": 0.6593669939496444, + "learning_rate": 1.8318560447105008e-05, + "loss": 0.9511, + "step": 3448 + }, + { + "epoch": 0.21173148347094753, + "grad_norm": 0.651068868603995, + "learning_rate": 1.8317456765525506e-05, + "loss": 1.0059, + "step": 3449 + }, + { + "epoch": 0.21179287270941405, + "grad_norm": 0.7302928775561306, + "learning_rate": 1.8316352755112456e-05, + "loss": 1.0289, + "step": 3450 + }, + { + "epoch": 0.21185426194788054, + "grad_norm": 0.6561849825730505, + "learning_rate": 1.8315248415909503e-05, + "loss": 1.0282, + "step": 3451 + }, + { + "epoch": 0.21191565118634703, + "grad_norm": 0.5640431863355685, + "learning_rate": 1.8314143747960303e-05, + "loss": 0.9371, + "step": 3452 + }, + { + "epoch": 0.21197704042481352, + "grad_norm": 0.6704343578369638, + "learning_rate": 1.8313038751308537e-05, + "loss": 1.0049, + "step": 3453 + }, + { + "epoch": 0.21203842966328001, + "grad_norm": 0.5980751048772239, + "learning_rate": 1.8311933425997884e-05, + "loss": 0.9425, + "step": 3454 + }, + { + "epoch": 0.21209981890174653, + "grad_norm": 0.6138887332523466, + "learning_rate": 1.8310827772072054e-05, + "loss": 1.0026, + "step": 3455 + }, + { + "epoch": 0.21216120814021303, + "grad_norm": 0.6449279234798353, + "learning_rate": 1.8309721789574748e-05, + "loss": 0.9813, + "step": 3456 + }, + { + "epoch": 0.21222259737867952, + "grad_norm": 0.6276997751127451, + "learning_rate": 1.8308615478549696e-05, + "loss": 0.9887, + "step": 3457 + }, + { + "epoch": 0.212283986617146, + "grad_norm": 0.6727817865037056, + "learning_rate": 1.8307508839040638e-05, + "loss": 1.0738, + "step": 3458 + }, + { + "epoch": 0.2123453758556125, + "grad_norm": 0.6398465520269784, + "learning_rate": 1.8306401871091323e-05, + "loss": 1.0279, + "step": 3459 + }, + { + "epoch": 0.21240676509407902, + "grad_norm": 0.6334875169955066, + "learning_rate": 1.8305294574745515e-05, + "loss": 0.9753, + "step": 3460 + }, + { + "epoch": 0.2124681543325455, + "grad_norm": 0.5954939025009091, + "learning_rate": 1.8304186950046995e-05, + "loss": 0.9689, + "step": 3461 + }, + { + "epoch": 0.212529543571012, + "grad_norm": 0.6610984832280425, + "learning_rate": 1.830307899703955e-05, + "loss": 0.9846, + "step": 3462 + }, + { + "epoch": 0.2125909328094785, + "grad_norm": 0.6824521298283888, + "learning_rate": 1.8301970715766984e-05, + "loss": 1.0444, + "step": 3463 + }, + { + "epoch": 0.21265232204794499, + "grad_norm": 0.6079497363304154, + "learning_rate": 1.8300862106273113e-05, + "loss": 0.9943, + "step": 3464 + }, + { + "epoch": 0.2127137112864115, + "grad_norm": 0.6404934805527042, + "learning_rate": 1.829975316860177e-05, + "loss": 1.0556, + "step": 3465 + }, + { + "epoch": 0.212775100524878, + "grad_norm": 0.6454163599131517, + "learning_rate": 1.829864390279679e-05, + "loss": 1.018, + "step": 3466 + }, + { + "epoch": 0.2128364897633445, + "grad_norm": 0.6175661036487102, + "learning_rate": 1.8297534308902035e-05, + "loss": 1.027, + "step": 3467 + }, + { + "epoch": 0.21289787900181098, + "grad_norm": 0.651138208164395, + "learning_rate": 1.829642438696137e-05, + "loss": 1.047, + "step": 3468 + }, + { + "epoch": 0.21295926824027747, + "grad_norm": 0.6306347728608364, + "learning_rate": 1.8295314137018674e-05, + "loss": 1.0123, + "step": 3469 + }, + { + "epoch": 0.21302065747874396, + "grad_norm": 0.6622623463144162, + "learning_rate": 1.829420355911785e-05, + "loss": 1.0208, + "step": 3470 + }, + { + "epoch": 0.21308204671721048, + "grad_norm": 0.6320528579032723, + "learning_rate": 1.8293092653302795e-05, + "loss": 0.9671, + "step": 3471 + }, + { + "epoch": 0.21314343595567697, + "grad_norm": 0.6699510897247124, + "learning_rate": 1.829198141961743e-05, + "loss": 1.0488, + "step": 3472 + }, + { + "epoch": 0.21320482519414347, + "grad_norm": 0.6379339198414051, + "learning_rate": 1.8290869858105694e-05, + "loss": 0.9941, + "step": 3473 + }, + { + "epoch": 0.21326621443260996, + "grad_norm": 0.6261381832710119, + "learning_rate": 1.828975796881153e-05, + "loss": 0.9584, + "step": 3474 + }, + { + "epoch": 0.21332760367107645, + "grad_norm": 0.666445418769599, + "learning_rate": 1.8288645751778894e-05, + "loss": 1.0014, + "step": 3475 + }, + { + "epoch": 0.21338899290954297, + "grad_norm": 0.664360794290101, + "learning_rate": 1.8287533207051764e-05, + "loss": 0.9658, + "step": 3476 + }, + { + "epoch": 0.21345038214800946, + "grad_norm": 0.6972666588722243, + "learning_rate": 1.8286420334674118e-05, + "loss": 1.0677, + "step": 3477 + }, + { + "epoch": 0.21351177138647595, + "grad_norm": 0.6148996546606124, + "learning_rate": 1.828530713468996e-05, + "loss": 0.9806, + "step": 3478 + }, + { + "epoch": 0.21357316062494244, + "grad_norm": 0.6235305475369936, + "learning_rate": 1.82841936071433e-05, + "loss": 0.9517, + "step": 3479 + }, + { + "epoch": 0.21363454986340893, + "grad_norm": 0.6921065146837462, + "learning_rate": 1.8283079752078155e-05, + "loss": 1.0095, + "step": 3480 + }, + { + "epoch": 0.21369593910187545, + "grad_norm": 0.6530360793107947, + "learning_rate": 1.8281965569538567e-05, + "loss": 1.0062, + "step": 3481 + }, + { + "epoch": 0.21375732834034195, + "grad_norm": 0.678629210619757, + "learning_rate": 1.8280851059568587e-05, + "loss": 1.0028, + "step": 3482 + }, + { + "epoch": 0.21381871757880844, + "grad_norm": 0.6817040369217939, + "learning_rate": 1.8279736222212276e-05, + "loss": 1.0364, + "step": 3483 + }, + { + "epoch": 0.21388010681727493, + "grad_norm": 0.6436462112165525, + "learning_rate": 1.8278621057513705e-05, + "loss": 1.0132, + "step": 3484 + }, + { + "epoch": 0.21394149605574142, + "grad_norm": 0.6211955104508734, + "learning_rate": 1.827750556551697e-05, + "loss": 1.0212, + "step": 3485 + }, + { + "epoch": 0.2140028852942079, + "grad_norm": 0.6240099145164697, + "learning_rate": 1.827638974626617e-05, + "loss": 0.9857, + "step": 3486 + }, + { + "epoch": 0.21406427453267443, + "grad_norm": 0.6615811004628653, + "learning_rate": 1.8275273599805413e-05, + "loss": 0.9919, + "step": 3487 + }, + { + "epoch": 0.21412566377114092, + "grad_norm": 0.6136848884197893, + "learning_rate": 1.8274157126178837e-05, + "loss": 1.0093, + "step": 3488 + }, + { + "epoch": 0.21418705300960741, + "grad_norm": 0.655611657900653, + "learning_rate": 1.8273040325430575e-05, + "loss": 0.9772, + "step": 3489 + }, + { + "epoch": 0.2142484422480739, + "grad_norm": 0.6538960836309551, + "learning_rate": 1.827192319760478e-05, + "loss": 0.9667, + "step": 3490 + }, + { + "epoch": 0.2143098314865404, + "grad_norm": 0.7214657666309647, + "learning_rate": 1.827080574274562e-05, + "loss": 1.0168, + "step": 3491 + }, + { + "epoch": 0.21437122072500692, + "grad_norm": 0.7441539654713001, + "learning_rate": 1.8269687960897272e-05, + "loss": 1.0488, + "step": 3492 + }, + { + "epoch": 0.2144326099634734, + "grad_norm": 0.5941923216268924, + "learning_rate": 1.8268569852103932e-05, + "loss": 0.939, + "step": 3493 + }, + { + "epoch": 0.2144939992019399, + "grad_norm": 0.6656473110238461, + "learning_rate": 1.8267451416409803e-05, + "loss": 0.9919, + "step": 3494 + }, + { + "epoch": 0.2145553884404064, + "grad_norm": 0.6838870465600836, + "learning_rate": 1.82663326538591e-05, + "loss": 0.9249, + "step": 3495 + }, + { + "epoch": 0.21461677767887288, + "grad_norm": 0.6873342814657631, + "learning_rate": 1.8265213564496056e-05, + "loss": 1.0057, + "step": 3496 + }, + { + "epoch": 0.2146781669173394, + "grad_norm": 0.7304550137165378, + "learning_rate": 1.8264094148364916e-05, + "loss": 1.0107, + "step": 3497 + }, + { + "epoch": 0.2147395561558059, + "grad_norm": 0.6731285149046975, + "learning_rate": 1.8262974405509936e-05, + "loss": 1.0241, + "step": 3498 + }, + { + "epoch": 0.21480094539427239, + "grad_norm": 0.7040037442372399, + "learning_rate": 1.826185433597538e-05, + "loss": 1.0622, + "step": 3499 + }, + { + "epoch": 0.21486233463273888, + "grad_norm": 0.6264961029388458, + "learning_rate": 1.8260733939805535e-05, + "loss": 0.9325, + "step": 3500 + }, + { + "epoch": 0.21492372387120537, + "grad_norm": 0.6251448924463754, + "learning_rate": 1.8259613217044698e-05, + "loss": 0.9763, + "step": 3501 + }, + { + "epoch": 0.2149851131096719, + "grad_norm": 0.6821923065397031, + "learning_rate": 1.8258492167737175e-05, + "loss": 1.0381, + "step": 3502 + }, + { + "epoch": 0.21504650234813838, + "grad_norm": 0.6667738375580915, + "learning_rate": 1.8257370791927288e-05, + "loss": 1.0455, + "step": 3503 + }, + { + "epoch": 0.21510789158660487, + "grad_norm": 0.6156912195120748, + "learning_rate": 1.825624908965937e-05, + "loss": 0.962, + "step": 3504 + }, + { + "epoch": 0.21516928082507136, + "grad_norm": 0.7003368334835437, + "learning_rate": 1.825512706097776e-05, + "loss": 1.055, + "step": 3505 + }, + { + "epoch": 0.21523067006353785, + "grad_norm": 0.6499345798923457, + "learning_rate": 1.8254004705926836e-05, + "loss": 1.0352, + "step": 3506 + }, + { + "epoch": 0.21529205930200435, + "grad_norm": 0.6051437413199641, + "learning_rate": 1.8252882024550955e-05, + "loss": 0.9674, + "step": 3507 + }, + { + "epoch": 0.21535344854047087, + "grad_norm": 0.6405380531923638, + "learning_rate": 1.825175901689451e-05, + "loss": 0.9879, + "step": 3508 + }, + { + "epoch": 0.21541483777893736, + "grad_norm": 0.6172277101380781, + "learning_rate": 1.8250635683001897e-05, + "loss": 0.9636, + "step": 3509 + }, + { + "epoch": 0.21547622701740385, + "grad_norm": 0.7093597008636796, + "learning_rate": 1.8249512022917528e-05, + "loss": 1.0269, + "step": 3510 + }, + { + "epoch": 0.21553761625587034, + "grad_norm": 0.6265795351031158, + "learning_rate": 1.8248388036685827e-05, + "loss": 0.9932, + "step": 3511 + }, + { + "epoch": 0.21559900549433683, + "grad_norm": 0.6407851050034952, + "learning_rate": 1.8247263724351236e-05, + "loss": 0.9543, + "step": 3512 + }, + { + "epoch": 0.21566039473280335, + "grad_norm": 0.6209599181236191, + "learning_rate": 1.8246139085958196e-05, + "loss": 1.0411, + "step": 3513 + }, + { + "epoch": 0.21572178397126984, + "grad_norm": 0.5734406367616853, + "learning_rate": 1.8245014121551173e-05, + "loss": 0.9543, + "step": 3514 + }, + { + "epoch": 0.21578317320973633, + "grad_norm": 0.6498857385977831, + "learning_rate": 1.8243888831174644e-05, + "loss": 0.9995, + "step": 3515 + }, + { + "epoch": 0.21584456244820283, + "grad_norm": 0.638754308384953, + "learning_rate": 1.8242763214873102e-05, + "loss": 1.0001, + "step": 3516 + }, + { + "epoch": 0.21590595168666932, + "grad_norm": 0.688789463315737, + "learning_rate": 1.8241637272691042e-05, + "loss": 1.0202, + "step": 3517 + }, + { + "epoch": 0.21596734092513584, + "grad_norm": 0.6556722235474886, + "learning_rate": 1.8240511004672985e-05, + "loss": 1.0448, + "step": 3518 + }, + { + "epoch": 0.21602873016360233, + "grad_norm": 0.6066423051319082, + "learning_rate": 1.823938441086345e-05, + "loss": 0.9324, + "step": 3519 + }, + { + "epoch": 0.21609011940206882, + "grad_norm": 0.6433082927105871, + "learning_rate": 1.8238257491306984e-05, + "loss": 1.0154, + "step": 3520 + }, + { + "epoch": 0.2161515086405353, + "grad_norm": 0.6283921116733128, + "learning_rate": 1.8237130246048137e-05, + "loss": 1.0431, + "step": 3521 + }, + { + "epoch": 0.2162128978790018, + "grad_norm": 0.6746911320284448, + "learning_rate": 1.8236002675131478e-05, + "loss": 1.0222, + "step": 3522 + }, + { + "epoch": 0.2162742871174683, + "grad_norm": 0.6190405485133362, + "learning_rate": 1.8234874778601582e-05, + "loss": 0.9607, + "step": 3523 + }, + { + "epoch": 0.21633567635593481, + "grad_norm": 0.6220886779946555, + "learning_rate": 1.8233746556503046e-05, + "loss": 0.9686, + "step": 3524 + }, + { + "epoch": 0.2163970655944013, + "grad_norm": 0.6336925402287447, + "learning_rate": 1.8232618008880468e-05, + "loss": 0.9785, + "step": 3525 + }, + { + "epoch": 0.2164584548328678, + "grad_norm": 0.6348382545945167, + "learning_rate": 1.823148913577847e-05, + "loss": 0.9564, + "step": 3526 + }, + { + "epoch": 0.2165198440713343, + "grad_norm": 0.6487580721448576, + "learning_rate": 1.823035993724168e-05, + "loss": 0.9441, + "step": 3527 + }, + { + "epoch": 0.21658123330980078, + "grad_norm": 0.6222205156868046, + "learning_rate": 1.8229230413314748e-05, + "loss": 0.9466, + "step": 3528 + }, + { + "epoch": 0.2166426225482673, + "grad_norm": 0.6576988838611821, + "learning_rate": 1.822810056404232e-05, + "loss": 0.9999, + "step": 3529 + }, + { + "epoch": 0.2167040117867338, + "grad_norm": 0.7010786099516905, + "learning_rate": 1.822697038946907e-05, + "loss": 1.0114, + "step": 3530 + }, + { + "epoch": 0.21676540102520028, + "grad_norm": 0.7220319705576449, + "learning_rate": 1.822583988963968e-05, + "loss": 1.0309, + "step": 3531 + }, + { + "epoch": 0.21682679026366677, + "grad_norm": 0.6819737134509395, + "learning_rate": 1.8224709064598846e-05, + "loss": 1.0011, + "step": 3532 + }, + { + "epoch": 0.21688817950213327, + "grad_norm": 0.6782582866709022, + "learning_rate": 1.822357791439127e-05, + "loss": 0.983, + "step": 3533 + }, + { + "epoch": 0.21694956874059979, + "grad_norm": 0.6986702987144818, + "learning_rate": 1.822244643906168e-05, + "loss": 1.0573, + "step": 3534 + }, + { + "epoch": 0.21701095797906628, + "grad_norm": 0.6787104318150837, + "learning_rate": 1.8221314638654805e-05, + "loss": 0.9707, + "step": 3535 + }, + { + "epoch": 0.21707234721753277, + "grad_norm": 0.6677269246328777, + "learning_rate": 1.822018251321539e-05, + "loss": 1.0147, + "step": 3536 + }, + { + "epoch": 0.21713373645599926, + "grad_norm": 0.6319274514411168, + "learning_rate": 1.8219050062788194e-05, + "loss": 0.9449, + "step": 3537 + }, + { + "epoch": 0.21719512569446575, + "grad_norm": 0.6582803296860795, + "learning_rate": 1.8217917287417995e-05, + "loss": 0.9673, + "step": 3538 + }, + { + "epoch": 0.21725651493293224, + "grad_norm": 0.9600779116989973, + "learning_rate": 1.821678418714957e-05, + "loss": 0.8131, + "step": 3539 + }, + { + "epoch": 0.21731790417139876, + "grad_norm": 0.6278394608741483, + "learning_rate": 1.8215650762027725e-05, + "loss": 0.9442, + "step": 3540 + }, + { + "epoch": 0.21737929340986525, + "grad_norm": 0.6635163018872167, + "learning_rate": 1.8214517012097256e-05, + "loss": 0.9804, + "step": 3541 + }, + { + "epoch": 0.21744068264833175, + "grad_norm": 0.6455057034290647, + "learning_rate": 1.8213382937403002e-05, + "loss": 1.0039, + "step": 3542 + }, + { + "epoch": 0.21750207188679824, + "grad_norm": 0.6380622902282755, + "learning_rate": 1.821224853798979e-05, + "loss": 0.9682, + "step": 3543 + }, + { + "epoch": 0.21756346112526473, + "grad_norm": 0.7068970264705494, + "learning_rate": 1.821111381390247e-05, + "loss": 1.0564, + "step": 3544 + }, + { + "epoch": 0.21762485036373125, + "grad_norm": 0.6501733054740078, + "learning_rate": 1.820997876518591e-05, + "loss": 0.9953, + "step": 3545 + }, + { + "epoch": 0.21768623960219774, + "grad_norm": 0.6230846665092254, + "learning_rate": 1.8208843391884975e-05, + "loss": 0.9496, + "step": 3546 + }, + { + "epoch": 0.21774762884066423, + "grad_norm": 0.6762162925405562, + "learning_rate": 1.8207707694044554e-05, + "loss": 1.0616, + "step": 3547 + }, + { + "epoch": 0.21780901807913072, + "grad_norm": 0.649398983800339, + "learning_rate": 1.820657167170955e-05, + "loss": 1.0236, + "step": 3548 + }, + { + "epoch": 0.21787040731759721, + "grad_norm": 0.6755528076300551, + "learning_rate": 1.8205435324924884e-05, + "loss": 1.0232, + "step": 3549 + }, + { + "epoch": 0.21793179655606373, + "grad_norm": 0.6348230824010099, + "learning_rate": 1.8204298653735467e-05, + "loss": 0.9991, + "step": 3550 + }, + { + "epoch": 0.21799318579453023, + "grad_norm": 0.5931130128754976, + "learning_rate": 1.8203161658186246e-05, + "loss": 1.0024, + "step": 3551 + }, + { + "epoch": 0.21805457503299672, + "grad_norm": 0.6514307644869146, + "learning_rate": 1.820202433832217e-05, + "loss": 0.9846, + "step": 3552 + }, + { + "epoch": 0.2181159642714632, + "grad_norm": 0.652415159287201, + "learning_rate": 1.8200886694188206e-05, + "loss": 1.0128, + "step": 3553 + }, + { + "epoch": 0.2181773535099297, + "grad_norm": 0.6253738969247573, + "learning_rate": 1.819974872582933e-05, + "loss": 0.9816, + "step": 3554 + }, + { + "epoch": 0.21823874274839622, + "grad_norm": 0.6563629089268324, + "learning_rate": 1.8198610433290532e-05, + "loss": 0.9995, + "step": 3555 + }, + { + "epoch": 0.2183001319868627, + "grad_norm": 0.66479034286128, + "learning_rate": 1.8197471816616815e-05, + "loss": 1.0199, + "step": 3556 + }, + { + "epoch": 0.2183615212253292, + "grad_norm": 0.7015944395691068, + "learning_rate": 1.8196332875853187e-05, + "loss": 1.0584, + "step": 3557 + }, + { + "epoch": 0.2184229104637957, + "grad_norm": 0.5876799200176379, + "learning_rate": 1.819519361104469e-05, + "loss": 0.9361, + "step": 3558 + }, + { + "epoch": 0.21848429970226219, + "grad_norm": 0.5965674300124643, + "learning_rate": 1.819405402223636e-05, + "loss": 0.9345, + "step": 3559 + }, + { + "epoch": 0.21854568894072868, + "grad_norm": 0.6700455153290156, + "learning_rate": 1.8192914109473247e-05, + "loss": 1.0253, + "step": 3560 + }, + { + "epoch": 0.2186070781791952, + "grad_norm": 0.606898758895833, + "learning_rate": 1.819177387280042e-05, + "loss": 0.9674, + "step": 3561 + }, + { + "epoch": 0.2186684674176617, + "grad_norm": 0.6320494946255933, + "learning_rate": 1.8190633312262957e-05, + "loss": 0.9885, + "step": 3562 + }, + { + "epoch": 0.21872985665612818, + "grad_norm": 0.623916336759922, + "learning_rate": 1.818949242790596e-05, + "loss": 1.0139, + "step": 3563 + }, + { + "epoch": 0.21879124589459467, + "grad_norm": 0.6557443671420812, + "learning_rate": 1.818835121977452e-05, + "loss": 0.9976, + "step": 3564 + }, + { + "epoch": 0.21885263513306116, + "grad_norm": 0.6328118116995208, + "learning_rate": 1.818720968791376e-05, + "loss": 1.0067, + "step": 3565 + }, + { + "epoch": 0.21891402437152768, + "grad_norm": 0.6877409928802968, + "learning_rate": 1.8186067832368816e-05, + "loss": 1.0352, + "step": 3566 + }, + { + "epoch": 0.21897541360999417, + "grad_norm": 0.6508622184101454, + "learning_rate": 1.818492565318483e-05, + "loss": 1.0181, + "step": 3567 + }, + { + "epoch": 0.21903680284846067, + "grad_norm": 0.6369778158192374, + "learning_rate": 1.8183783150406956e-05, + "loss": 1.032, + "step": 3568 + }, + { + "epoch": 0.21909819208692716, + "grad_norm": 0.6342010676977173, + "learning_rate": 1.8182640324080366e-05, + "loss": 1.0455, + "step": 3569 + }, + { + "epoch": 0.21915958132539365, + "grad_norm": 0.6630442739843699, + "learning_rate": 1.8181497174250236e-05, + "loss": 0.9319, + "step": 3570 + }, + { + "epoch": 0.21922097056386017, + "grad_norm": 0.6288153514213537, + "learning_rate": 1.8180353700961764e-05, + "loss": 0.9597, + "step": 3571 + }, + { + "epoch": 0.21928235980232666, + "grad_norm": 0.6485524434606713, + "learning_rate": 1.8179209904260165e-05, + "loss": 1.0476, + "step": 3572 + }, + { + "epoch": 0.21934374904079315, + "grad_norm": 0.6846317330479593, + "learning_rate": 1.8178065784190647e-05, + "loss": 1.027, + "step": 3573 + }, + { + "epoch": 0.21940513827925964, + "grad_norm": 0.6788876165016992, + "learning_rate": 1.817692134079845e-05, + "loss": 0.9586, + "step": 3574 + }, + { + "epoch": 0.21946652751772613, + "grad_norm": 0.7066884555825759, + "learning_rate": 1.8175776574128826e-05, + "loss": 1.0364, + "step": 3575 + }, + { + "epoch": 0.21952791675619263, + "grad_norm": 0.6378304513953327, + "learning_rate": 1.817463148422702e-05, + "loss": 0.941, + "step": 3576 + }, + { + "epoch": 0.21958930599465915, + "grad_norm": 0.6442504426007964, + "learning_rate": 1.8173486071138313e-05, + "loss": 1.0202, + "step": 3577 + }, + { + "epoch": 0.21965069523312564, + "grad_norm": 0.6129480818530546, + "learning_rate": 1.8172340334907986e-05, + "loss": 0.9811, + "step": 3578 + }, + { + "epoch": 0.21971208447159213, + "grad_norm": 0.647058042997989, + "learning_rate": 1.8171194275581336e-05, + "loss": 0.9358, + "step": 3579 + }, + { + "epoch": 0.21977347371005862, + "grad_norm": 0.6689885790690824, + "learning_rate": 1.8170047893203672e-05, + "loss": 1.0152, + "step": 3580 + }, + { + "epoch": 0.2198348629485251, + "grad_norm": 0.6268594558312572, + "learning_rate": 1.816890118782032e-05, + "loss": 0.9899, + "step": 3581 + }, + { + "epoch": 0.21989625218699163, + "grad_norm": 0.6376963819604851, + "learning_rate": 1.8167754159476615e-05, + "loss": 1.0248, + "step": 3582 + }, + { + "epoch": 0.21995764142545812, + "grad_norm": 0.6192552153288544, + "learning_rate": 1.8166606808217906e-05, + "loss": 0.7544, + "step": 3583 + }, + { + "epoch": 0.22001903066392461, + "grad_norm": 0.6092958103030711, + "learning_rate": 1.816545913408955e-05, + "loss": 0.9417, + "step": 3584 + }, + { + "epoch": 0.2200804199023911, + "grad_norm": 0.6446342908343732, + "learning_rate": 1.816431113713692e-05, + "loss": 0.9739, + "step": 3585 + }, + { + "epoch": 0.2201418091408576, + "grad_norm": 0.6582809592862996, + "learning_rate": 1.8163162817405407e-05, + "loss": 1.0132, + "step": 3586 + }, + { + "epoch": 0.22020319837932412, + "grad_norm": 0.7247523942895859, + "learning_rate": 1.8162014174940406e-05, + "loss": 1.0321, + "step": 3587 + }, + { + "epoch": 0.2202645876177906, + "grad_norm": 0.6095223260196444, + "learning_rate": 1.8160865209787335e-05, + "loss": 0.9391, + "step": 3588 + }, + { + "epoch": 0.2203259768562571, + "grad_norm": 0.5987058499689552, + "learning_rate": 1.8159715921991612e-05, + "loss": 0.9465, + "step": 3589 + }, + { + "epoch": 0.2203873660947236, + "grad_norm": 0.7033733227370992, + "learning_rate": 1.8158566311598677e-05, + "loss": 0.9825, + "step": 3590 + }, + { + "epoch": 0.22044875533319008, + "grad_norm": 0.6528646259131231, + "learning_rate": 1.8157416378653984e-05, + "loss": 0.9995, + "step": 3591 + }, + { + "epoch": 0.2205101445716566, + "grad_norm": 0.6538441002590044, + "learning_rate": 1.815626612320299e-05, + "loss": 1.0254, + "step": 3592 + }, + { + "epoch": 0.2205715338101231, + "grad_norm": 0.6540630053258839, + "learning_rate": 1.8155115545291174e-05, + "loss": 0.9908, + "step": 3593 + }, + { + "epoch": 0.22063292304858959, + "grad_norm": 0.6672071155162077, + "learning_rate": 1.8153964644964023e-05, + "loss": 0.9504, + "step": 3594 + }, + { + "epoch": 0.22069431228705608, + "grad_norm": 0.6201307991648914, + "learning_rate": 1.8152813422267038e-05, + "loss": 1.0001, + "step": 3595 + }, + { + "epoch": 0.22075570152552257, + "grad_norm": 0.5655099631088493, + "learning_rate": 1.8151661877245733e-05, + "loss": 0.9364, + "step": 3596 + }, + { + "epoch": 0.22081709076398906, + "grad_norm": 0.6234700623801873, + "learning_rate": 1.815051000994564e-05, + "loss": 0.7519, + "step": 3597 + }, + { + "epoch": 0.22087848000245558, + "grad_norm": 0.6812584484149697, + "learning_rate": 1.8149357820412296e-05, + "loss": 1.0113, + "step": 3598 + }, + { + "epoch": 0.22093986924092207, + "grad_norm": 0.6074159005718798, + "learning_rate": 1.8148205308691248e-05, + "loss": 0.9419, + "step": 3599 + }, + { + "epoch": 0.22100125847938856, + "grad_norm": 0.6514620756904365, + "learning_rate": 1.8147052474828062e-05, + "loss": 0.9409, + "step": 3600 + }, + { + "epoch": 0.22106264771785505, + "grad_norm": 0.6372654354273967, + "learning_rate": 1.8145899318868324e-05, + "loss": 0.9908, + "step": 3601 + }, + { + "epoch": 0.22112403695632155, + "grad_norm": 0.6098528705819033, + "learning_rate": 1.8144745840857615e-05, + "loss": 0.9416, + "step": 3602 + }, + { + "epoch": 0.22118542619478807, + "grad_norm": 0.6710614149601619, + "learning_rate": 1.8143592040841542e-05, + "loss": 0.9839, + "step": 3603 + }, + { + "epoch": 0.22124681543325456, + "grad_norm": 0.6016733011146221, + "learning_rate": 1.814243791886572e-05, + "loss": 0.9699, + "step": 3604 + }, + { + "epoch": 0.22130820467172105, + "grad_norm": 0.711132089759516, + "learning_rate": 1.814128347497578e-05, + "loss": 1.0861, + "step": 3605 + }, + { + "epoch": 0.22136959391018754, + "grad_norm": 0.6255705743408322, + "learning_rate": 1.8140128709217362e-05, + "loss": 0.9426, + "step": 3606 + }, + { + "epoch": 0.22143098314865403, + "grad_norm": 0.6887856237611005, + "learning_rate": 1.8138973621636118e-05, + "loss": 1.0003, + "step": 3607 + }, + { + "epoch": 0.22149237238712055, + "grad_norm": 0.6072012580624435, + "learning_rate": 1.813781821227772e-05, + "loss": 0.9741, + "step": 3608 + }, + { + "epoch": 0.22155376162558704, + "grad_norm": 0.6226624072335747, + "learning_rate": 1.8136662481187838e-05, + "loss": 0.9541, + "step": 3609 + }, + { + "epoch": 0.22161515086405353, + "grad_norm": 0.6718798919726411, + "learning_rate": 1.813550642841217e-05, + "loss": 1.02, + "step": 3610 + }, + { + "epoch": 0.22167654010252003, + "grad_norm": 0.630580689165104, + "learning_rate": 1.8134350053996426e-05, + "loss": 1.0209, + "step": 3611 + }, + { + "epoch": 0.22173792934098652, + "grad_norm": 0.6797792303127136, + "learning_rate": 1.8133193357986317e-05, + "loss": 1.0181, + "step": 3612 + }, + { + "epoch": 0.221799318579453, + "grad_norm": 0.6100630377275088, + "learning_rate": 1.8132036340427577e-05, + "loss": 0.9405, + "step": 3613 + }, + { + "epoch": 0.22186070781791953, + "grad_norm": 0.6656138446819866, + "learning_rate": 1.8130879001365944e-05, + "loss": 1.0418, + "step": 3614 + }, + { + "epoch": 0.22192209705638602, + "grad_norm": 0.6335088734856775, + "learning_rate": 1.812972134084718e-05, + "loss": 0.9896, + "step": 3615 + }, + { + "epoch": 0.2219834862948525, + "grad_norm": 0.6142998068566257, + "learning_rate": 1.812856335891705e-05, + "loss": 0.9531, + "step": 3616 + }, + { + "epoch": 0.222044875533319, + "grad_norm": 0.6688732798162604, + "learning_rate": 1.8127405055621336e-05, + "loss": 0.9798, + "step": 3617 + }, + { + "epoch": 0.2221062647717855, + "grad_norm": 0.6926156100512505, + "learning_rate": 1.8126246431005826e-05, + "loss": 1.0109, + "step": 3618 + }, + { + "epoch": 0.222167654010252, + "grad_norm": 0.6524912613580647, + "learning_rate": 1.812508748511634e-05, + "loss": 0.9781, + "step": 3619 + }, + { + "epoch": 0.2222290432487185, + "grad_norm": 0.650332064919951, + "learning_rate": 1.8123928217998685e-05, + "loss": 0.97, + "step": 3620 + }, + { + "epoch": 0.222290432487185, + "grad_norm": 0.6139914830766201, + "learning_rate": 1.81227686296987e-05, + "loss": 0.9916, + "step": 3621 + }, + { + "epoch": 0.2223518217256515, + "grad_norm": 0.6253230449538701, + "learning_rate": 1.8121608720262227e-05, + "loss": 1.0139, + "step": 3622 + }, + { + "epoch": 0.22241321096411798, + "grad_norm": 0.6459508974599169, + "learning_rate": 1.8120448489735122e-05, + "loss": 0.9962, + "step": 3623 + }, + { + "epoch": 0.2224746002025845, + "grad_norm": 0.6464997793367345, + "learning_rate": 1.8119287938163263e-05, + "loss": 1.0257, + "step": 3624 + }, + { + "epoch": 0.222535989441051, + "grad_norm": 0.6625707366567568, + "learning_rate": 1.8118127065592523e-05, + "loss": 0.9779, + "step": 3625 + }, + { + "epoch": 0.22259737867951748, + "grad_norm": 0.6373449822080954, + "learning_rate": 1.8116965872068795e-05, + "loss": 1.012, + "step": 3626 + }, + { + "epoch": 0.22265876791798397, + "grad_norm": 0.6265257392066463, + "learning_rate": 1.8115804357638003e-05, + "loss": 0.9485, + "step": 3627 + }, + { + "epoch": 0.22272015715645047, + "grad_norm": 0.5977128005060963, + "learning_rate": 1.8114642522346055e-05, + "loss": 1.0026, + "step": 3628 + }, + { + "epoch": 0.22278154639491696, + "grad_norm": 0.6766431803253055, + "learning_rate": 1.8113480366238887e-05, + "loss": 0.9889, + "step": 3629 + }, + { + "epoch": 0.22284293563338348, + "grad_norm": 0.6488145354213701, + "learning_rate": 1.811231788936245e-05, + "loss": 1.0348, + "step": 3630 + }, + { + "epoch": 0.22290432487184997, + "grad_norm": 0.6896631622943848, + "learning_rate": 1.8111155091762695e-05, + "loss": 1.0285, + "step": 3631 + }, + { + "epoch": 0.22296571411031646, + "grad_norm": 0.7167523564394006, + "learning_rate": 1.8109991973485598e-05, + "loss": 1.0156, + "step": 3632 + }, + { + "epoch": 0.22302710334878295, + "grad_norm": 0.6085579097689925, + "learning_rate": 1.810882853457714e-05, + "loss": 0.9885, + "step": 3633 + }, + { + "epoch": 0.22308849258724944, + "grad_norm": 0.610855632600552, + "learning_rate": 1.8107664775083327e-05, + "loss": 0.94, + "step": 3634 + }, + { + "epoch": 0.22314988182571596, + "grad_norm": 0.612048253593734, + "learning_rate": 1.810650069505016e-05, + "loss": 0.972, + "step": 3635 + }, + { + "epoch": 0.22321127106418245, + "grad_norm": 0.636855036168795, + "learning_rate": 1.8105336294523662e-05, + "loss": 1.0181, + "step": 3636 + }, + { + "epoch": 0.22327266030264895, + "grad_norm": 0.6748930063726651, + "learning_rate": 1.8104171573549877e-05, + "loss": 0.9964, + "step": 3637 + }, + { + "epoch": 0.22333404954111544, + "grad_norm": 0.6603904722541969, + "learning_rate": 1.810300653217484e-05, + "loss": 0.9921, + "step": 3638 + }, + { + "epoch": 0.22339543877958193, + "grad_norm": 0.6675923435223206, + "learning_rate": 1.8101841170444617e-05, + "loss": 0.9931, + "step": 3639 + }, + { + "epoch": 0.22345682801804845, + "grad_norm": 0.5581698178369127, + "learning_rate": 1.810067548840528e-05, + "loss": 0.8855, + "step": 3640 + }, + { + "epoch": 0.22351821725651494, + "grad_norm": 0.6270692826869559, + "learning_rate": 1.8099509486102918e-05, + "loss": 0.9077, + "step": 3641 + }, + { + "epoch": 0.22357960649498143, + "grad_norm": 0.6576017247461383, + "learning_rate": 1.8098343163583624e-05, + "loss": 0.9692, + "step": 3642 + }, + { + "epoch": 0.22364099573344792, + "grad_norm": 0.6608664024187326, + "learning_rate": 1.8097176520893514e-05, + "loss": 0.9933, + "step": 3643 + }, + { + "epoch": 0.22370238497191441, + "grad_norm": 0.60947947613729, + "learning_rate": 1.8096009558078708e-05, + "loss": 0.9258, + "step": 3644 + }, + { + "epoch": 0.22376377421038093, + "grad_norm": 0.6427843883961177, + "learning_rate": 1.8094842275185344e-05, + "loss": 1.0059, + "step": 3645 + }, + { + "epoch": 0.22382516344884743, + "grad_norm": 0.6429261900549985, + "learning_rate": 1.8093674672259572e-05, + "loss": 0.9735, + "step": 3646 + }, + { + "epoch": 0.22388655268731392, + "grad_norm": 0.7005376383439255, + "learning_rate": 1.809250674934755e-05, + "loss": 1.0285, + "step": 3647 + }, + { + "epoch": 0.2239479419257804, + "grad_norm": 0.6200211701861902, + "learning_rate": 1.8091338506495458e-05, + "loss": 0.9595, + "step": 3648 + }, + { + "epoch": 0.2240093311642469, + "grad_norm": 0.6622744222442423, + "learning_rate": 1.8090169943749477e-05, + "loss": 0.9847, + "step": 3649 + }, + { + "epoch": 0.2240707204027134, + "grad_norm": 0.6457159210344242, + "learning_rate": 1.8089001061155808e-05, + "loss": 0.9864, + "step": 3650 + }, + { + "epoch": 0.2241321096411799, + "grad_norm": 0.6340099414700118, + "learning_rate": 1.8087831858760662e-05, + "loss": 0.9448, + "step": 3651 + }, + { + "epoch": 0.2241934988796464, + "grad_norm": 0.5818150920422858, + "learning_rate": 1.8086662336610273e-05, + "loss": 0.9337, + "step": 3652 + }, + { + "epoch": 0.2242548881181129, + "grad_norm": 0.7145063573112418, + "learning_rate": 1.8085492494750867e-05, + "loss": 1.0313, + "step": 3653 + }, + { + "epoch": 0.22431627735657939, + "grad_norm": 0.6522555623124957, + "learning_rate": 1.8084322333228697e-05, + "loss": 0.9633, + "step": 3654 + }, + { + "epoch": 0.22437766659504588, + "grad_norm": 0.5856574595325513, + "learning_rate": 1.8083151852090028e-05, + "loss": 0.7628, + "step": 3655 + }, + { + "epoch": 0.2244390558335124, + "grad_norm": 0.6485601636243411, + "learning_rate": 1.8081981051381136e-05, + "loss": 0.7908, + "step": 3656 + }, + { + "epoch": 0.2245004450719789, + "grad_norm": 0.677770104025863, + "learning_rate": 1.8080809931148306e-05, + "loss": 1.0232, + "step": 3657 + }, + { + "epoch": 0.22456183431044538, + "grad_norm": 0.7130934689709971, + "learning_rate": 1.807963849143784e-05, + "loss": 0.9981, + "step": 3658 + }, + { + "epoch": 0.22462322354891187, + "grad_norm": 0.6473301305602173, + "learning_rate": 1.8078466732296053e-05, + "loss": 1.0177, + "step": 3659 + }, + { + "epoch": 0.22468461278737836, + "grad_norm": 0.6553211241503377, + "learning_rate": 1.807729465376927e-05, + "loss": 0.9916, + "step": 3660 + }, + { + "epoch": 0.22474600202584488, + "grad_norm": 0.6452572933137362, + "learning_rate": 1.8076122255903827e-05, + "loss": 0.9848, + "step": 3661 + }, + { + "epoch": 0.22480739126431137, + "grad_norm": 0.6799616364486241, + "learning_rate": 1.807494953874608e-05, + "loss": 1.0073, + "step": 3662 + }, + { + "epoch": 0.22486878050277787, + "grad_norm": 0.6238907170431616, + "learning_rate": 1.8073776502342387e-05, + "loss": 0.7204, + "step": 3663 + }, + { + "epoch": 0.22493016974124436, + "grad_norm": 0.6646614839187034, + "learning_rate": 1.8072603146739126e-05, + "loss": 0.9512, + "step": 3664 + }, + { + "epoch": 0.22499155897971085, + "grad_norm": 0.6474178781748559, + "learning_rate": 1.807142947198269e-05, + "loss": 0.986, + "step": 3665 + }, + { + "epoch": 0.22505294821817734, + "grad_norm": 0.6196217994118303, + "learning_rate": 1.807025547811948e-05, + "loss": 0.9778, + "step": 3666 + }, + { + "epoch": 0.22511433745664386, + "grad_norm": 0.6070454289928235, + "learning_rate": 1.80690811651959e-05, + "loss": 0.9867, + "step": 3667 + }, + { + "epoch": 0.22517572669511035, + "grad_norm": 0.7020934196411326, + "learning_rate": 1.806790653325839e-05, + "loss": 1.0067, + "step": 3668 + }, + { + "epoch": 0.22523711593357684, + "grad_norm": 0.6606026089372554, + "learning_rate": 1.806673158235339e-05, + "loss": 1.0231, + "step": 3669 + }, + { + "epoch": 0.22529850517204333, + "grad_norm": 0.6462403385946925, + "learning_rate": 1.806555631252734e-05, + "loss": 0.991, + "step": 3670 + }, + { + "epoch": 0.22535989441050983, + "grad_norm": 0.6488274036921609, + "learning_rate": 1.806438072382671e-05, + "loss": 0.968, + "step": 3671 + }, + { + "epoch": 0.22542128364897634, + "grad_norm": 0.6075539947308406, + "learning_rate": 1.8063204816297982e-05, + "loss": 0.9753, + "step": 3672 + }, + { + "epoch": 0.22548267288744284, + "grad_norm": 0.7010789687448572, + "learning_rate": 1.8062028589987644e-05, + "loss": 1.0611, + "step": 3673 + }, + { + "epoch": 0.22554406212590933, + "grad_norm": 0.6634823621933346, + "learning_rate": 1.8060852044942193e-05, + "loss": 0.9546, + "step": 3674 + }, + { + "epoch": 0.22560545136437582, + "grad_norm": 0.6452285855073696, + "learning_rate": 1.805967518120815e-05, + "loss": 1.0136, + "step": 3675 + }, + { + "epoch": 0.2256668406028423, + "grad_norm": 0.6598034065313301, + "learning_rate": 1.8058497998832044e-05, + "loss": 0.9373, + "step": 3676 + }, + { + "epoch": 0.22572822984130883, + "grad_norm": 0.6351847523386966, + "learning_rate": 1.8057320497860412e-05, + "loss": 0.9254, + "step": 3677 + }, + { + "epoch": 0.22578961907977532, + "grad_norm": 0.7221501671248383, + "learning_rate": 1.8056142678339803e-05, + "loss": 1.0601, + "step": 3678 + }, + { + "epoch": 0.2258510083182418, + "grad_norm": 0.6709237583958846, + "learning_rate": 1.8054964540316788e-05, + "loss": 0.9999, + "step": 3679 + }, + { + "epoch": 0.2259123975567083, + "grad_norm": 0.6540581384794166, + "learning_rate": 1.8053786083837944e-05, + "loss": 0.9567, + "step": 3680 + }, + { + "epoch": 0.2259737867951748, + "grad_norm": 0.7037166586212577, + "learning_rate": 1.805260730894986e-05, + "loss": 1.0679, + "step": 3681 + }, + { + "epoch": 0.22603517603364132, + "grad_norm": 0.6797952489838485, + "learning_rate": 1.8051428215699144e-05, + "loss": 1.0092, + "step": 3682 + }, + { + "epoch": 0.2260965652721078, + "grad_norm": 0.6458571049101457, + "learning_rate": 1.8050248804132406e-05, + "loss": 1.017, + "step": 3683 + }, + { + "epoch": 0.2261579545105743, + "grad_norm": 0.6301163756866218, + "learning_rate": 1.804906907429628e-05, + "loss": 0.9398, + "step": 3684 + }, + { + "epoch": 0.2262193437490408, + "grad_norm": 0.7009367899485793, + "learning_rate": 1.80478890262374e-05, + "loss": 1.0399, + "step": 3685 + }, + { + "epoch": 0.22628073298750728, + "grad_norm": 0.6247877341935746, + "learning_rate": 1.8046708660002424e-05, + "loss": 0.9322, + "step": 3686 + }, + { + "epoch": 0.22634212222597377, + "grad_norm": 0.6754045271184461, + "learning_rate": 1.8045527975638023e-05, + "loss": 0.9892, + "step": 3687 + }, + { + "epoch": 0.2264035114644403, + "grad_norm": 0.6621900179277693, + "learning_rate": 1.8044346973190866e-05, + "loss": 1.0079, + "step": 3688 + }, + { + "epoch": 0.22646490070290679, + "grad_norm": 0.525623596939575, + "learning_rate": 1.804316565270765e-05, + "loss": 0.9054, + "step": 3689 + }, + { + "epoch": 0.22652628994137328, + "grad_norm": 0.6390824208878184, + "learning_rate": 1.804198401423508e-05, + "loss": 0.9117, + "step": 3690 + }, + { + "epoch": 0.22658767917983977, + "grad_norm": 0.6953586440256319, + "learning_rate": 1.8040802057819866e-05, + "loss": 0.8057, + "step": 3691 + }, + { + "epoch": 0.22664906841830626, + "grad_norm": 0.6484760044786274, + "learning_rate": 1.8039619783508744e-05, + "loss": 0.952, + "step": 3692 + }, + { + "epoch": 0.22671045765677278, + "grad_norm": 0.6492910350988161, + "learning_rate": 1.8038437191348454e-05, + "loss": 0.9875, + "step": 3693 + }, + { + "epoch": 0.22677184689523927, + "grad_norm": 0.6025623499045334, + "learning_rate": 1.8037254281385746e-05, + "loss": 0.9295, + "step": 3694 + }, + { + "epoch": 0.22683323613370576, + "grad_norm": 0.6367481382672658, + "learning_rate": 1.8036071053667393e-05, + "loss": 0.9667, + "step": 3695 + }, + { + "epoch": 0.22689462537217225, + "grad_norm": 0.6894346451919087, + "learning_rate": 1.8034887508240172e-05, + "loss": 0.9469, + "step": 3696 + }, + { + "epoch": 0.22695601461063875, + "grad_norm": 0.7049273114370402, + "learning_rate": 1.803370364515087e-05, + "loss": 1.0603, + "step": 3697 + }, + { + "epoch": 0.22701740384910526, + "grad_norm": 0.6521888541395061, + "learning_rate": 1.8032519464446297e-05, + "loss": 0.9949, + "step": 3698 + }, + { + "epoch": 0.22707879308757176, + "grad_norm": 0.6223173347405734, + "learning_rate": 1.8031334966173272e-05, + "loss": 0.9802, + "step": 3699 + }, + { + "epoch": 0.22714018232603825, + "grad_norm": 0.659353056186401, + "learning_rate": 1.8030150150378617e-05, + "loss": 0.9853, + "step": 3700 + }, + { + "epoch": 0.22720157156450474, + "grad_norm": 0.6288566313646327, + "learning_rate": 1.802896501710918e-05, + "loss": 0.7924, + "step": 3701 + }, + { + "epoch": 0.22726296080297123, + "grad_norm": 0.6633084079712785, + "learning_rate": 1.8027779566411812e-05, + "loss": 1.0118, + "step": 3702 + }, + { + "epoch": 0.22732435004143772, + "grad_norm": 0.6858277673575469, + "learning_rate": 1.8026593798333386e-05, + "loss": 1.0263, + "step": 3703 + }, + { + "epoch": 0.22738573927990424, + "grad_norm": 0.606775792593176, + "learning_rate": 1.802540771292078e-05, + "loss": 0.9496, + "step": 3704 + }, + { + "epoch": 0.22744712851837073, + "grad_norm": 0.6540620029427003, + "learning_rate": 1.8024221310220877e-05, + "loss": 1.002, + "step": 3705 + }, + { + "epoch": 0.22750851775683723, + "grad_norm": 0.6621801605085669, + "learning_rate": 1.802303459028059e-05, + "loss": 1.0257, + "step": 3706 + }, + { + "epoch": 0.22756990699530372, + "grad_norm": 0.6294768583104166, + "learning_rate": 1.802184755314684e-05, + "loss": 0.9442, + "step": 3707 + }, + { + "epoch": 0.2276312962337702, + "grad_norm": 0.6401407260913459, + "learning_rate": 1.802066019886655e-05, + "loss": 0.9871, + "step": 3708 + }, + { + "epoch": 0.22769268547223673, + "grad_norm": 0.6700077360998014, + "learning_rate": 1.8019472527486667e-05, + "loss": 0.9519, + "step": 3709 + }, + { + "epoch": 0.22775407471070322, + "grad_norm": 0.6785171231339688, + "learning_rate": 1.8018284539054142e-05, + "loss": 0.9428, + "step": 3710 + }, + { + "epoch": 0.2278154639491697, + "grad_norm": 0.6777543427708438, + "learning_rate": 1.8017096233615942e-05, + "loss": 0.9254, + "step": 3711 + }, + { + "epoch": 0.2278768531876362, + "grad_norm": 0.6858382547713939, + "learning_rate": 1.8015907611219053e-05, + "loss": 1.0224, + "step": 3712 + }, + { + "epoch": 0.2279382424261027, + "grad_norm": 0.6615861797133439, + "learning_rate": 1.8014718671910462e-05, + "loss": 0.9527, + "step": 3713 + }, + { + "epoch": 0.2279996316645692, + "grad_norm": 0.6728800050066247, + "learning_rate": 1.801352941573718e-05, + "loss": 0.9966, + "step": 3714 + }, + { + "epoch": 0.2280610209030357, + "grad_norm": 0.6501886136577669, + "learning_rate": 1.8012339842746215e-05, + "loss": 0.9706, + "step": 3715 + }, + { + "epoch": 0.2281224101415022, + "grad_norm": 0.6372176631927576, + "learning_rate": 1.8011149952984607e-05, + "loss": 0.9671, + "step": 3716 + }, + { + "epoch": 0.2281837993799687, + "grad_norm": 0.6541382149552478, + "learning_rate": 1.8009959746499396e-05, + "loss": 0.9769, + "step": 3717 + }, + { + "epoch": 0.22824518861843518, + "grad_norm": 0.6191269796652672, + "learning_rate": 1.800876922333763e-05, + "loss": 0.9482, + "step": 3718 + }, + { + "epoch": 0.22830657785690167, + "grad_norm": 0.6453743059421819, + "learning_rate": 1.8007578383546388e-05, + "loss": 0.9839, + "step": 3719 + }, + { + "epoch": 0.2283679670953682, + "grad_norm": 0.644219712213957, + "learning_rate": 1.8006387227172744e-05, + "loss": 1.0283, + "step": 3720 + }, + { + "epoch": 0.22842935633383468, + "grad_norm": 0.6549123954996509, + "learning_rate": 1.800519575426379e-05, + "loss": 0.9572, + "step": 3721 + }, + { + "epoch": 0.22849074557230117, + "grad_norm": 0.7113127027862696, + "learning_rate": 1.8004003964866635e-05, + "loss": 0.9997, + "step": 3722 + }, + { + "epoch": 0.22855213481076767, + "grad_norm": 0.6646632803261467, + "learning_rate": 1.800281185902839e-05, + "loss": 0.9444, + "step": 3723 + }, + { + "epoch": 0.22861352404923416, + "grad_norm": 0.6355380372682221, + "learning_rate": 1.8001619436796194e-05, + "loss": 0.9973, + "step": 3724 + }, + { + "epoch": 0.22867491328770068, + "grad_norm": 0.6925687757091316, + "learning_rate": 1.8000426698217186e-05, + "loss": 1.004, + "step": 3725 + }, + { + "epoch": 0.22873630252616717, + "grad_norm": 0.6385434598821704, + "learning_rate": 1.7999233643338524e-05, + "loss": 1.008, + "step": 3726 + }, + { + "epoch": 0.22879769176463366, + "grad_norm": 0.6183379959857657, + "learning_rate": 1.799804027220737e-05, + "loss": 0.9684, + "step": 3727 + }, + { + "epoch": 0.22885908100310015, + "grad_norm": 0.6462267561642169, + "learning_rate": 1.799684658487091e-05, + "loss": 0.9828, + "step": 3728 + }, + { + "epoch": 0.22892047024156664, + "grad_norm": 0.6957980203134241, + "learning_rate": 1.799565258137633e-05, + "loss": 1.0162, + "step": 3729 + }, + { + "epoch": 0.22898185948003316, + "grad_norm": 0.6469809787840315, + "learning_rate": 1.7994458261770844e-05, + "loss": 0.9809, + "step": 3730 + }, + { + "epoch": 0.22904324871849965, + "grad_norm": 0.5884835108568296, + "learning_rate": 1.799326362610166e-05, + "loss": 0.9305, + "step": 3731 + }, + { + "epoch": 0.22910463795696615, + "grad_norm": 0.7464839517570434, + "learning_rate": 1.7992068674416017e-05, + "loss": 1.0337, + "step": 3732 + }, + { + "epoch": 0.22916602719543264, + "grad_norm": 0.6657050216299418, + "learning_rate": 1.7990873406761156e-05, + "loss": 0.9892, + "step": 3733 + }, + { + "epoch": 0.22922741643389913, + "grad_norm": 0.6771656694180163, + "learning_rate": 1.798967782318433e-05, + "loss": 0.9707, + "step": 3734 + }, + { + "epoch": 0.22928880567236565, + "grad_norm": 0.6664954987855839, + "learning_rate": 1.798848192373281e-05, + "loss": 0.9768, + "step": 3735 + }, + { + "epoch": 0.22935019491083214, + "grad_norm": 0.6281011766682714, + "learning_rate": 1.7987285708453873e-05, + "loss": 0.9799, + "step": 3736 + }, + { + "epoch": 0.22941158414929863, + "grad_norm": 0.6674711162293449, + "learning_rate": 1.798608917739481e-05, + "loss": 0.972, + "step": 3737 + }, + { + "epoch": 0.22947297338776512, + "grad_norm": 0.6199464849345213, + "learning_rate": 1.798489233060293e-05, + "loss": 0.9561, + "step": 3738 + }, + { + "epoch": 0.22953436262623161, + "grad_norm": 0.6470411913126586, + "learning_rate": 1.7983695168125552e-05, + "loss": 0.9794, + "step": 3739 + }, + { + "epoch": 0.2295957518646981, + "grad_norm": 0.5824356425540745, + "learning_rate": 1.7982497690010004e-05, + "loss": 0.8982, + "step": 3740 + }, + { + "epoch": 0.22965714110316462, + "grad_norm": 0.6491704233009823, + "learning_rate": 1.7981299896303628e-05, + "loss": 1.0132, + "step": 3741 + }, + { + "epoch": 0.22971853034163112, + "grad_norm": 0.6582736899850598, + "learning_rate": 1.7980101787053782e-05, + "loss": 0.9852, + "step": 3742 + }, + { + "epoch": 0.2297799195800976, + "grad_norm": 0.6353293355511678, + "learning_rate": 1.797890336230783e-05, + "loss": 0.966, + "step": 3743 + }, + { + "epoch": 0.2298413088185641, + "grad_norm": 0.6677927579756867, + "learning_rate": 1.7977704622113153e-05, + "loss": 0.9522, + "step": 3744 + }, + { + "epoch": 0.2299026980570306, + "grad_norm": 0.6187141577334488, + "learning_rate": 1.7976505566517146e-05, + "loss": 0.9338, + "step": 3745 + }, + { + "epoch": 0.2299640872954971, + "grad_norm": 0.6371660353946598, + "learning_rate": 1.7975306195567212e-05, + "loss": 0.9738, + "step": 3746 + }, + { + "epoch": 0.2300254765339636, + "grad_norm": 0.6537942579440938, + "learning_rate": 1.7974106509310768e-05, + "loss": 0.9576, + "step": 3747 + }, + { + "epoch": 0.2300868657724301, + "grad_norm": 0.5966995786825815, + "learning_rate": 1.797290650779525e-05, + "loss": 0.9485, + "step": 3748 + }, + { + "epoch": 0.23014825501089659, + "grad_norm": 0.683710048518479, + "learning_rate": 1.797170619106809e-05, + "loss": 1.059, + "step": 3749 + }, + { + "epoch": 0.23020964424936308, + "grad_norm": 0.6774458031230455, + "learning_rate": 1.7970505559176753e-05, + "loss": 1.0245, + "step": 3750 + }, + { + "epoch": 0.2302710334878296, + "grad_norm": 0.6390294824409861, + "learning_rate": 1.7969304612168697e-05, + "loss": 0.7581, + "step": 3751 + }, + { + "epoch": 0.2303324227262961, + "grad_norm": 0.5882246505395632, + "learning_rate": 1.7968103350091412e-05, + "loss": 0.9361, + "step": 3752 + }, + { + "epoch": 0.23039381196476258, + "grad_norm": 0.5930814370450003, + "learning_rate": 1.796690177299238e-05, + "loss": 0.9599, + "step": 3753 + }, + { + "epoch": 0.23045520120322907, + "grad_norm": 0.6608985593421443, + "learning_rate": 1.7965699880919114e-05, + "loss": 0.9836, + "step": 3754 + }, + { + "epoch": 0.23051659044169556, + "grad_norm": 0.7013353226391393, + "learning_rate": 1.7964497673919127e-05, + "loss": 1.0344, + "step": 3755 + }, + { + "epoch": 0.23057797968016205, + "grad_norm": 0.6239381553995218, + "learning_rate": 1.7963295152039952e-05, + "loss": 0.9756, + "step": 3756 + }, + { + "epoch": 0.23063936891862857, + "grad_norm": 0.6077695626760141, + "learning_rate": 1.796209231532913e-05, + "loss": 0.978, + "step": 3757 + }, + { + "epoch": 0.23070075815709506, + "grad_norm": 0.6337122222251049, + "learning_rate": 1.796088916383421e-05, + "loss": 1.0022, + "step": 3758 + }, + { + "epoch": 0.23076214739556156, + "grad_norm": 0.6684800275857378, + "learning_rate": 1.7959685697602765e-05, + "loss": 1.0259, + "step": 3759 + }, + { + "epoch": 0.23082353663402805, + "grad_norm": 0.6118708060384435, + "learning_rate": 1.795848191668238e-05, + "loss": 0.975, + "step": 3760 + }, + { + "epoch": 0.23088492587249454, + "grad_norm": 0.6340182139930204, + "learning_rate": 1.795727782112063e-05, + "loss": 0.969, + "step": 3761 + }, + { + "epoch": 0.23094631511096106, + "grad_norm": 0.655905455111785, + "learning_rate": 1.795607341096513e-05, + "loss": 0.9651, + "step": 3762 + }, + { + "epoch": 0.23100770434942755, + "grad_norm": 0.6025275449476639, + "learning_rate": 1.79548686862635e-05, + "loss": 0.8014, + "step": 3763 + }, + { + "epoch": 0.23106909358789404, + "grad_norm": 0.6303154151241928, + "learning_rate": 1.7953663647063365e-05, + "loss": 0.9797, + "step": 3764 + }, + { + "epoch": 0.23113048282636053, + "grad_norm": 0.6423307987997974, + "learning_rate": 1.795245829341237e-05, + "loss": 0.9842, + "step": 3765 + }, + { + "epoch": 0.23119187206482703, + "grad_norm": 0.6667165720075262, + "learning_rate": 1.7951252625358158e-05, + "loss": 0.9984, + "step": 3766 + }, + { + "epoch": 0.23125326130329354, + "grad_norm": 0.6463405661016115, + "learning_rate": 1.7950046642948407e-05, + "loss": 0.9678, + "step": 3767 + }, + { + "epoch": 0.23131465054176004, + "grad_norm": 0.6836247086112636, + "learning_rate": 1.7948840346230795e-05, + "loss": 0.9797, + "step": 3768 + }, + { + "epoch": 0.23137603978022653, + "grad_norm": 0.594064789828011, + "learning_rate": 1.7947633735253005e-05, + "loss": 0.9438, + "step": 3769 + }, + { + "epoch": 0.23143742901869302, + "grad_norm": 0.6648449909636919, + "learning_rate": 1.794642681006275e-05, + "loss": 1.0299, + "step": 3770 + }, + { + "epoch": 0.2314988182571595, + "grad_norm": 0.6535189042906371, + "learning_rate": 1.7945219570707745e-05, + "loss": 0.9834, + "step": 3771 + }, + { + "epoch": 0.23156020749562603, + "grad_norm": 0.6278978718871491, + "learning_rate": 1.794401201723571e-05, + "loss": 0.9502, + "step": 3772 + }, + { + "epoch": 0.23162159673409252, + "grad_norm": 0.6076121472879209, + "learning_rate": 1.79428041496944e-05, + "loss": 0.9339, + "step": 3773 + }, + { + "epoch": 0.231682985972559, + "grad_norm": 0.6429679816725792, + "learning_rate": 1.7941595968131554e-05, + "loss": 1.0216, + "step": 3774 + }, + { + "epoch": 0.2317443752110255, + "grad_norm": 0.6365398181662585, + "learning_rate": 1.7940387472594948e-05, + "loss": 0.9185, + "step": 3775 + }, + { + "epoch": 0.231805764449492, + "grad_norm": 0.7175711015254052, + "learning_rate": 1.793917866313236e-05, + "loss": 1.0735, + "step": 3776 + }, + { + "epoch": 0.2318671536879585, + "grad_norm": 0.6061800918795572, + "learning_rate": 1.793796953979157e-05, + "loss": 0.9443, + "step": 3777 + }, + { + "epoch": 0.231928542926425, + "grad_norm": 0.5946875711280212, + "learning_rate": 1.7936760102620398e-05, + "loss": 0.771, + "step": 3778 + }, + { + "epoch": 0.2319899321648915, + "grad_norm": 0.6545254133735393, + "learning_rate": 1.7935550351666644e-05, + "loss": 0.9962, + "step": 3779 + }, + { + "epoch": 0.232051321403358, + "grad_norm": 0.7352922774446986, + "learning_rate": 1.7934340286978145e-05, + "loss": 1.0127, + "step": 3780 + }, + { + "epoch": 0.23211271064182448, + "grad_norm": 0.7069115055343351, + "learning_rate": 1.7933129908602738e-05, + "loss": 0.9966, + "step": 3781 + }, + { + "epoch": 0.23217409988029097, + "grad_norm": 0.6453709433995364, + "learning_rate": 1.7931919216588275e-05, + "loss": 0.9803, + "step": 3782 + }, + { + "epoch": 0.2322354891187575, + "grad_norm": 0.6393823840488866, + "learning_rate": 1.7930708210982625e-05, + "loss": 0.9848, + "step": 3783 + }, + { + "epoch": 0.23229687835722398, + "grad_norm": 0.6684539956650891, + "learning_rate": 1.7929496891833662e-05, + "loss": 1.006, + "step": 3784 + }, + { + "epoch": 0.23235826759569048, + "grad_norm": 0.6317004117509044, + "learning_rate": 1.7928285259189275e-05, + "loss": 0.9607, + "step": 3785 + }, + { + "epoch": 0.23241965683415697, + "grad_norm": 1.201643638735053, + "learning_rate": 1.792707331309737e-05, + "loss": 1.0126, + "step": 3786 + }, + { + "epoch": 0.23248104607262346, + "grad_norm": 0.6256220809514461, + "learning_rate": 1.7925861053605856e-05, + "loss": 1.0053, + "step": 3787 + }, + { + "epoch": 0.23254243531108998, + "grad_norm": 0.6897552027981313, + "learning_rate": 1.792464848076267e-05, + "loss": 1.0026, + "step": 3788 + }, + { + "epoch": 0.23260382454955647, + "grad_norm": 0.6447939337974714, + "learning_rate": 1.7923435594615744e-05, + "loss": 0.952, + "step": 3789 + }, + { + "epoch": 0.23266521378802296, + "grad_norm": 0.6334156265633513, + "learning_rate": 1.792222239521303e-05, + "loss": 0.9514, + "step": 3790 + }, + { + "epoch": 0.23272660302648945, + "grad_norm": 0.693230106510601, + "learning_rate": 1.7921008882602495e-05, + "loss": 0.9639, + "step": 3791 + }, + { + "epoch": 0.23278799226495595, + "grad_norm": 0.6892279545646456, + "learning_rate": 1.7919795056832113e-05, + "loss": 1.0036, + "step": 3792 + }, + { + "epoch": 0.23284938150342244, + "grad_norm": 0.6452643545969939, + "learning_rate": 1.7918580917949876e-05, + "loss": 0.9819, + "step": 3793 + }, + { + "epoch": 0.23291077074188896, + "grad_norm": 0.605980121348756, + "learning_rate": 1.7917366466003784e-05, + "loss": 0.9563, + "step": 3794 + }, + { + "epoch": 0.23297215998035545, + "grad_norm": 0.6197240708838897, + "learning_rate": 1.7916151701041847e-05, + "loss": 0.9233, + "step": 3795 + }, + { + "epoch": 0.23303354921882194, + "grad_norm": 0.5994533230828523, + "learning_rate": 1.79149366231121e-05, + "loss": 0.9701, + "step": 3796 + }, + { + "epoch": 0.23309493845728843, + "grad_norm": 0.6464336079050638, + "learning_rate": 1.7913721232262572e-05, + "loss": 0.9764, + "step": 3797 + }, + { + "epoch": 0.23315632769575492, + "grad_norm": 0.681044801530339, + "learning_rate": 1.791250552854132e-05, + "loss": 1.0532, + "step": 3798 + }, + { + "epoch": 0.23321771693422144, + "grad_norm": 0.6451783030379551, + "learning_rate": 1.7911289511996406e-05, + "loss": 0.9899, + "step": 3799 + }, + { + "epoch": 0.23327910617268793, + "grad_norm": 0.6281699460301247, + "learning_rate": 1.7910073182675905e-05, + "loss": 0.989, + "step": 3800 + }, + { + "epoch": 0.23334049541115442, + "grad_norm": 0.614901616519449, + "learning_rate": 1.79088565406279e-05, + "loss": 0.9474, + "step": 3801 + }, + { + "epoch": 0.23340188464962092, + "grad_norm": 0.5893087563704578, + "learning_rate": 1.7907639585900504e-05, + "loss": 0.9536, + "step": 3802 + }, + { + "epoch": 0.2334632738880874, + "grad_norm": 0.6336439659605961, + "learning_rate": 1.790642231854182e-05, + "loss": 0.9718, + "step": 3803 + }, + { + "epoch": 0.23352466312655393, + "grad_norm": 0.6286059236735816, + "learning_rate": 1.790520473859997e-05, + "loss": 0.9959, + "step": 3804 + }, + { + "epoch": 0.23358605236502042, + "grad_norm": 0.7120383918052023, + "learning_rate": 1.7903986846123103e-05, + "loss": 1.0187, + "step": 3805 + }, + { + "epoch": 0.2336474416034869, + "grad_norm": 0.6998843025532181, + "learning_rate": 1.7902768641159357e-05, + "loss": 1.0272, + "step": 3806 + }, + { + "epoch": 0.2337088308419534, + "grad_norm": 0.6482978426517798, + "learning_rate": 1.7901550123756906e-05, + "loss": 0.9757, + "step": 3807 + }, + { + "epoch": 0.2337702200804199, + "grad_norm": 0.6093253980603556, + "learning_rate": 1.7900331293963913e-05, + "loss": 0.9665, + "step": 3808 + }, + { + "epoch": 0.23383160931888639, + "grad_norm": 0.6558589650454237, + "learning_rate": 1.789911215182857e-05, + "loss": 0.9682, + "step": 3809 + }, + { + "epoch": 0.2338929985573529, + "grad_norm": 0.6211529704476131, + "learning_rate": 1.7897892697399083e-05, + "loss": 0.9543, + "step": 3810 + }, + { + "epoch": 0.2339543877958194, + "grad_norm": 0.6422889928120896, + "learning_rate": 1.789667293072365e-05, + "loss": 1.0306, + "step": 3811 + }, + { + "epoch": 0.2340157770342859, + "grad_norm": 0.6628853338038242, + "learning_rate": 1.7895452851850502e-05, + "loss": 0.9359, + "step": 3812 + }, + { + "epoch": 0.23407716627275238, + "grad_norm": 0.6605428974027459, + "learning_rate": 1.7894232460827878e-05, + "loss": 0.9997, + "step": 3813 + }, + { + "epoch": 0.23413855551121887, + "grad_norm": 0.7000196861930328, + "learning_rate": 1.7893011757704022e-05, + "loss": 1.0086, + "step": 3814 + }, + { + "epoch": 0.2341999447496854, + "grad_norm": 0.6903416433210362, + "learning_rate": 1.7891790742527194e-05, + "loss": 1.0532, + "step": 3815 + }, + { + "epoch": 0.23426133398815188, + "grad_norm": 0.7330592801535778, + "learning_rate": 1.789056941534567e-05, + "loss": 1.0379, + "step": 3816 + }, + { + "epoch": 0.23432272322661837, + "grad_norm": 0.6600982865030086, + "learning_rate": 1.788934777620774e-05, + "loss": 0.981, + "step": 3817 + }, + { + "epoch": 0.23438411246508487, + "grad_norm": 0.5934386620225004, + "learning_rate": 1.7888125825161697e-05, + "loss": 0.9099, + "step": 3818 + }, + { + "epoch": 0.23444550170355136, + "grad_norm": 0.6489152254221878, + "learning_rate": 1.7886903562255847e-05, + "loss": 0.9967, + "step": 3819 + }, + { + "epoch": 0.23450689094201788, + "grad_norm": 0.6063044558167893, + "learning_rate": 1.788568098753852e-05, + "loss": 0.9522, + "step": 3820 + }, + { + "epoch": 0.23456828018048437, + "grad_norm": 0.6050185075483994, + "learning_rate": 1.7884458101058047e-05, + "loss": 0.9248, + "step": 3821 + }, + { + "epoch": 0.23462966941895086, + "grad_norm": 0.6754472799137913, + "learning_rate": 1.7883234902862778e-05, + "loss": 1.0463, + "step": 3822 + }, + { + "epoch": 0.23469105865741735, + "grad_norm": 0.6431860166552629, + "learning_rate": 1.7882011393001067e-05, + "loss": 0.9878, + "step": 3823 + }, + { + "epoch": 0.23475244789588384, + "grad_norm": 0.6188267065615692, + "learning_rate": 1.7880787571521293e-05, + "loss": 0.9786, + "step": 3824 + }, + { + "epoch": 0.23481383713435036, + "grad_norm": 0.5939820939758111, + "learning_rate": 1.7879563438471833e-05, + "loss": 0.7758, + "step": 3825 + }, + { + "epoch": 0.23487522637281685, + "grad_norm": 0.6622606394746059, + "learning_rate": 1.7878338993901093e-05, + "loss": 0.9352, + "step": 3826 + }, + { + "epoch": 0.23493661561128334, + "grad_norm": 0.640463319282988, + "learning_rate": 1.787711423785747e-05, + "loss": 0.9482, + "step": 3827 + }, + { + "epoch": 0.23499800484974984, + "grad_norm": 0.5827130300991411, + "learning_rate": 1.7875889170389394e-05, + "loss": 0.9313, + "step": 3828 + }, + { + "epoch": 0.23505939408821633, + "grad_norm": 0.6451126337659848, + "learning_rate": 1.78746637915453e-05, + "loss": 0.9806, + "step": 3829 + }, + { + "epoch": 0.23512078332668282, + "grad_norm": 0.6446409348662013, + "learning_rate": 1.7873438101373626e-05, + "loss": 0.9812, + "step": 3830 + }, + { + "epoch": 0.23518217256514934, + "grad_norm": 0.626968990710014, + "learning_rate": 1.787221209992283e-05, + "loss": 0.9571, + "step": 3831 + }, + { + "epoch": 0.23524356180361583, + "grad_norm": 0.6520650207898104, + "learning_rate": 1.7870985787241394e-05, + "loss": 1.0111, + "step": 3832 + }, + { + "epoch": 0.23530495104208232, + "grad_norm": 0.6474147910708077, + "learning_rate": 1.7869759163377786e-05, + "loss": 0.9578, + "step": 3833 + }, + { + "epoch": 0.2353663402805488, + "grad_norm": 0.7032856356907857, + "learning_rate": 1.786853222838051e-05, + "loss": 0.9943, + "step": 3834 + }, + { + "epoch": 0.2354277295190153, + "grad_norm": 0.650861397538362, + "learning_rate": 1.7867304982298073e-05, + "loss": 1.0203, + "step": 3835 + }, + { + "epoch": 0.23548911875748182, + "grad_norm": 0.6762292556324221, + "learning_rate": 1.7866077425178995e-05, + "loss": 1.0092, + "step": 3836 + }, + { + "epoch": 0.23555050799594832, + "grad_norm": 0.6463819635116702, + "learning_rate": 1.78648495570718e-05, + "loss": 0.9669, + "step": 3837 + }, + { + "epoch": 0.2356118972344148, + "grad_norm": 0.6862183505665362, + "learning_rate": 1.786362137802504e-05, + "loss": 0.9983, + "step": 3838 + }, + { + "epoch": 0.2356732864728813, + "grad_norm": 0.6209438736957993, + "learning_rate": 1.786239288808727e-05, + "loss": 0.9268, + "step": 3839 + }, + { + "epoch": 0.2357346757113478, + "grad_norm": 0.6155213577040862, + "learning_rate": 1.7861164087307056e-05, + "loss": 1.0065, + "step": 3840 + }, + { + "epoch": 0.2357960649498143, + "grad_norm": 0.6339993648995285, + "learning_rate": 1.785993497573298e-05, + "loss": 1.0183, + "step": 3841 + }, + { + "epoch": 0.2358574541882808, + "grad_norm": 0.6958470080296878, + "learning_rate": 1.785870555341364e-05, + "loss": 1.0233, + "step": 3842 + }, + { + "epoch": 0.2359188434267473, + "grad_norm": 0.6553189499652783, + "learning_rate": 1.785747582039764e-05, + "loss": 1.0169, + "step": 3843 + }, + { + "epoch": 0.23598023266521378, + "grad_norm": 0.6769598997961894, + "learning_rate": 1.7856245776733593e-05, + "loss": 0.9883, + "step": 3844 + }, + { + "epoch": 0.23604162190368028, + "grad_norm": 0.646893355437103, + "learning_rate": 1.7855015422470132e-05, + "loss": 0.9976, + "step": 3845 + }, + { + "epoch": 0.23610301114214677, + "grad_norm": 0.6752144110373347, + "learning_rate": 1.7853784757655902e-05, + "loss": 0.9841, + "step": 3846 + }, + { + "epoch": 0.2361644003806133, + "grad_norm": 0.6227857954023789, + "learning_rate": 1.7852553782339553e-05, + "loss": 0.9592, + "step": 3847 + }, + { + "epoch": 0.23622578961907978, + "grad_norm": 0.637362892279412, + "learning_rate": 1.7851322496569755e-05, + "loss": 1.0076, + "step": 3848 + }, + { + "epoch": 0.23628717885754627, + "grad_norm": 0.5999696998014284, + "learning_rate": 1.7850090900395186e-05, + "loss": 0.9579, + "step": 3849 + }, + { + "epoch": 0.23634856809601276, + "grad_norm": 0.645714469137158, + "learning_rate": 1.7848858993864543e-05, + "loss": 1.0032, + "step": 3850 + }, + { + "epoch": 0.23640995733447925, + "grad_norm": 0.6685797426914494, + "learning_rate": 1.784762677702652e-05, + "loss": 1.0189, + "step": 3851 + }, + { + "epoch": 0.23647134657294577, + "grad_norm": 0.675497360208694, + "learning_rate": 1.7846394249929844e-05, + "loss": 0.9776, + "step": 3852 + }, + { + "epoch": 0.23653273581141226, + "grad_norm": 0.6639062760523473, + "learning_rate": 1.7845161412623233e-05, + "loss": 0.9965, + "step": 3853 + }, + { + "epoch": 0.23659412504987876, + "grad_norm": 0.6554401185651391, + "learning_rate": 1.7843928265155435e-05, + "loss": 0.9564, + "step": 3854 + }, + { + "epoch": 0.23665551428834525, + "grad_norm": 0.7263641182205255, + "learning_rate": 1.78426948075752e-05, + "loss": 1.1111, + "step": 3855 + }, + { + "epoch": 0.23671690352681174, + "grad_norm": 0.619172870176827, + "learning_rate": 1.784146103993129e-05, + "loss": 0.9839, + "step": 3856 + }, + { + "epoch": 0.23677829276527826, + "grad_norm": 0.6623260446934407, + "learning_rate": 1.784022696227249e-05, + "loss": 0.9842, + "step": 3857 + }, + { + "epoch": 0.23683968200374475, + "grad_norm": 0.737476124840621, + "learning_rate": 1.7838992574647583e-05, + "loss": 1.0561, + "step": 3858 + }, + { + "epoch": 0.23690107124221124, + "grad_norm": 0.7122106834597491, + "learning_rate": 1.7837757877105378e-05, + "loss": 1.0139, + "step": 3859 + }, + { + "epoch": 0.23696246048067773, + "grad_norm": 0.6546148574866112, + "learning_rate": 1.7836522869694685e-05, + "loss": 0.9269, + "step": 3860 + }, + { + "epoch": 0.23702384971914423, + "grad_norm": 0.6516727652628951, + "learning_rate": 1.7835287552464327e-05, + "loss": 0.979, + "step": 3861 + }, + { + "epoch": 0.23708523895761074, + "grad_norm": 0.6084377881808066, + "learning_rate": 1.7834051925463145e-05, + "loss": 0.9607, + "step": 3862 + }, + { + "epoch": 0.23714662819607724, + "grad_norm": 0.6915944954816843, + "learning_rate": 1.783281598873999e-05, + "loss": 1.0288, + "step": 3863 + }, + { + "epoch": 0.23720801743454373, + "grad_norm": 0.7057802870791623, + "learning_rate": 1.783157974234373e-05, + "loss": 0.9961, + "step": 3864 + }, + { + "epoch": 0.23726940667301022, + "grad_norm": 0.6809548858070458, + "learning_rate": 1.7830343186323235e-05, + "loss": 1.0519, + "step": 3865 + }, + { + "epoch": 0.2373307959114767, + "grad_norm": 0.6557377023866517, + "learning_rate": 1.7829106320727394e-05, + "loss": 0.986, + "step": 3866 + }, + { + "epoch": 0.2373921851499432, + "grad_norm": 0.6155572723006927, + "learning_rate": 1.7827869145605107e-05, + "loss": 0.9624, + "step": 3867 + }, + { + "epoch": 0.23745357438840972, + "grad_norm": 0.6819593794156537, + "learning_rate": 1.782663166100529e-05, + "loss": 1.0436, + "step": 3868 + }, + { + "epoch": 0.2375149636268762, + "grad_norm": 0.6627192928760678, + "learning_rate": 1.7825393866976858e-05, + "loss": 0.9936, + "step": 3869 + }, + { + "epoch": 0.2375763528653427, + "grad_norm": 0.6709448208513522, + "learning_rate": 1.7824155763568755e-05, + "loss": 0.9899, + "step": 3870 + }, + { + "epoch": 0.2376377421038092, + "grad_norm": 0.6069812390795039, + "learning_rate": 1.7822917350829932e-05, + "loss": 0.9526, + "step": 3871 + }, + { + "epoch": 0.2376991313422757, + "grad_norm": 0.6111401621175552, + "learning_rate": 1.782167862880934e-05, + "loss": 0.97, + "step": 3872 + }, + { + "epoch": 0.2377605205807422, + "grad_norm": 0.6526238223171801, + "learning_rate": 1.7820439597555964e-05, + "loss": 0.948, + "step": 3873 + }, + { + "epoch": 0.2378219098192087, + "grad_norm": 0.6384374363539701, + "learning_rate": 1.781920025711878e-05, + "loss": 0.9908, + "step": 3874 + }, + { + "epoch": 0.2378832990576752, + "grad_norm": 0.6073201959657005, + "learning_rate": 1.781796060754679e-05, + "loss": 0.9272, + "step": 3875 + }, + { + "epoch": 0.23794468829614168, + "grad_norm": 0.6479636567515533, + "learning_rate": 1.7816720648889006e-05, + "loss": 0.9182, + "step": 3876 + }, + { + "epoch": 0.23800607753460817, + "grad_norm": 0.6701974323717659, + "learning_rate": 1.781548038119445e-05, + "loss": 0.9985, + "step": 3877 + }, + { + "epoch": 0.2380674667730747, + "grad_norm": 0.719432538338452, + "learning_rate": 1.7814239804512154e-05, + "loss": 1.0493, + "step": 3878 + }, + { + "epoch": 0.23812885601154118, + "grad_norm": 0.6329957052957409, + "learning_rate": 1.7812998918891162e-05, + "loss": 1.0039, + "step": 3879 + }, + { + "epoch": 0.23819024525000768, + "grad_norm": 0.6597814101782793, + "learning_rate": 1.7811757724380534e-05, + "loss": 0.9969, + "step": 3880 + }, + { + "epoch": 0.23825163448847417, + "grad_norm": 0.65514732275793, + "learning_rate": 1.7810516221029347e-05, + "loss": 1.0306, + "step": 3881 + }, + { + "epoch": 0.23831302372694066, + "grad_norm": 0.6498749984262835, + "learning_rate": 1.7809274408886678e-05, + "loss": 0.9956, + "step": 3882 + }, + { + "epoch": 0.23837441296540715, + "grad_norm": 0.7180219429357517, + "learning_rate": 1.7808032288001624e-05, + "loss": 1.007, + "step": 3883 + }, + { + "epoch": 0.23843580220387367, + "grad_norm": 0.6459474156225696, + "learning_rate": 1.7806789858423298e-05, + "loss": 1.0023, + "step": 3884 + }, + { + "epoch": 0.23849719144234016, + "grad_norm": 0.6622680183356141, + "learning_rate": 1.780554712020081e-05, + "loss": 0.9917, + "step": 3885 + }, + { + "epoch": 0.23855858068080665, + "grad_norm": 0.6899406938072355, + "learning_rate": 1.7804304073383298e-05, + "loss": 0.9928, + "step": 3886 + }, + { + "epoch": 0.23861996991927314, + "grad_norm": 0.6859882866197652, + "learning_rate": 1.780306071801991e-05, + "loss": 1.0232, + "step": 3887 + }, + { + "epoch": 0.23868135915773964, + "grad_norm": 0.6689399209641698, + "learning_rate": 1.7801817054159794e-05, + "loss": 0.987, + "step": 3888 + }, + { + "epoch": 0.23874274839620616, + "grad_norm": 0.6438545011439459, + "learning_rate": 1.7800573081852124e-05, + "loss": 0.9529, + "step": 3889 + }, + { + "epoch": 0.23880413763467265, + "grad_norm": 0.6559085423800326, + "learning_rate": 1.779932880114608e-05, + "loss": 1.0043, + "step": 3890 + }, + { + "epoch": 0.23886552687313914, + "grad_norm": 0.615977490876467, + "learning_rate": 1.779808421209085e-05, + "loss": 0.9384, + "step": 3891 + }, + { + "epoch": 0.23892691611160563, + "grad_norm": 0.6712864367023246, + "learning_rate": 1.779683931473565e-05, + "loss": 0.9731, + "step": 3892 + }, + { + "epoch": 0.23898830535007212, + "grad_norm": 0.6039880685724652, + "learning_rate": 1.7795594109129692e-05, + "loss": 0.9572, + "step": 3893 + }, + { + "epoch": 0.23904969458853864, + "grad_norm": 0.6295532324112295, + "learning_rate": 1.77943485953222e-05, + "loss": 0.9838, + "step": 3894 + }, + { + "epoch": 0.23911108382700513, + "grad_norm": 0.6177296161495234, + "learning_rate": 1.7793102773362426e-05, + "loss": 0.9569, + "step": 3895 + }, + { + "epoch": 0.23917247306547162, + "grad_norm": 0.6332662421321268, + "learning_rate": 1.7791856643299617e-05, + "loss": 0.968, + "step": 3896 + }, + { + "epoch": 0.23923386230393812, + "grad_norm": 0.650231466056504, + "learning_rate": 1.779061020518304e-05, + "loss": 0.9303, + "step": 3897 + }, + { + "epoch": 0.2392952515424046, + "grad_norm": 0.6277517944988399, + "learning_rate": 1.7789363459061976e-05, + "loss": 0.9623, + "step": 3898 + }, + { + "epoch": 0.23935664078087113, + "grad_norm": 0.6194446585503963, + "learning_rate": 1.7788116404985714e-05, + "loss": 0.9654, + "step": 3899 + }, + { + "epoch": 0.23941803001933762, + "grad_norm": 0.6426591218083695, + "learning_rate": 1.7786869043003557e-05, + "loss": 0.939, + "step": 3900 + }, + { + "epoch": 0.2394794192578041, + "grad_norm": 0.6448119331087836, + "learning_rate": 1.778562137316482e-05, + "loss": 0.8103, + "step": 3901 + }, + { + "epoch": 0.2395408084962706, + "grad_norm": 0.6419936635458464, + "learning_rate": 1.7784373395518824e-05, + "loss": 0.97, + "step": 3902 + }, + { + "epoch": 0.2396021977347371, + "grad_norm": 0.707225896004649, + "learning_rate": 1.778312511011492e-05, + "loss": 0.9903, + "step": 3903 + }, + { + "epoch": 0.23966358697320359, + "grad_norm": 0.6501405319816714, + "learning_rate": 1.778187651700245e-05, + "loss": 0.9873, + "step": 3904 + }, + { + "epoch": 0.2397249762116701, + "grad_norm": 0.5480447376560867, + "learning_rate": 1.7780627616230785e-05, + "loss": 0.7539, + "step": 3905 + }, + { + "epoch": 0.2397863654501366, + "grad_norm": 0.6071559758231996, + "learning_rate": 1.7779378407849293e-05, + "loss": 0.9028, + "step": 3906 + }, + { + "epoch": 0.2398477546886031, + "grad_norm": 0.6782742820310091, + "learning_rate": 1.7778128891907365e-05, + "loss": 1.016, + "step": 3907 + }, + { + "epoch": 0.23990914392706958, + "grad_norm": 0.6477133595877598, + "learning_rate": 1.7776879068454406e-05, + "loss": 0.9569, + "step": 3908 + }, + { + "epoch": 0.23997053316553607, + "grad_norm": 0.6636491279651426, + "learning_rate": 1.777562893753982e-05, + "loss": 1.002, + "step": 3909 + }, + { + "epoch": 0.2400319224040026, + "grad_norm": 0.6954300604839189, + "learning_rate": 1.7774378499213037e-05, + "loss": 1.0011, + "step": 3910 + }, + { + "epoch": 0.24009331164246908, + "grad_norm": 0.6474785882782211, + "learning_rate": 1.777312775352349e-05, + "loss": 0.9861, + "step": 3911 + }, + { + "epoch": 0.24015470088093557, + "grad_norm": 0.6169376406999316, + "learning_rate": 1.7771876700520628e-05, + "loss": 0.9657, + "step": 3912 + }, + { + "epoch": 0.24021609011940206, + "grad_norm": 0.6939096796110458, + "learning_rate": 1.7770625340253915e-05, + "loss": 1.0406, + "step": 3913 + }, + { + "epoch": 0.24027747935786856, + "grad_norm": 0.7019602661727256, + "learning_rate": 1.7769373672772824e-05, + "loss": 1.0128, + "step": 3914 + }, + { + "epoch": 0.24033886859633508, + "grad_norm": 0.6444705228616655, + "learning_rate": 1.7768121698126836e-05, + "loss": 0.9749, + "step": 3915 + }, + { + "epoch": 0.24040025783480157, + "grad_norm": 0.6814464634369113, + "learning_rate": 1.776686941636545e-05, + "loss": 1.0378, + "step": 3916 + }, + { + "epoch": 0.24046164707326806, + "grad_norm": 0.7031541639199707, + "learning_rate": 1.7765616827538178e-05, + "loss": 0.9557, + "step": 3917 + }, + { + "epoch": 0.24052303631173455, + "grad_norm": 0.647321605477806, + "learning_rate": 1.776436393169454e-05, + "loss": 0.9777, + "step": 3918 + }, + { + "epoch": 0.24058442555020104, + "grad_norm": 0.7026972511940877, + "learning_rate": 1.7763110728884062e-05, + "loss": 0.9326, + "step": 3919 + }, + { + "epoch": 0.24064581478866753, + "grad_norm": 0.6294709337246422, + "learning_rate": 1.7761857219156303e-05, + "loss": 0.9471, + "step": 3920 + }, + { + "epoch": 0.24070720402713405, + "grad_norm": 0.6392598609752448, + "learning_rate": 1.7760603402560813e-05, + "loss": 0.9701, + "step": 3921 + }, + { + "epoch": 0.24076859326560054, + "grad_norm": 0.6230010159467468, + "learning_rate": 1.7759349279147167e-05, + "loss": 0.9229, + "step": 3922 + }, + { + "epoch": 0.24082998250406704, + "grad_norm": 0.6788401958338708, + "learning_rate": 1.775809484896494e-05, + "loss": 0.986, + "step": 3923 + }, + { + "epoch": 0.24089137174253353, + "grad_norm": 0.7291160008183838, + "learning_rate": 1.7756840112063735e-05, + "loss": 1.0331, + "step": 3924 + }, + { + "epoch": 0.24095276098100002, + "grad_norm": 0.6833668679730858, + "learning_rate": 1.775558506849315e-05, + "loss": 1.0069, + "step": 3925 + }, + { + "epoch": 0.24101415021946654, + "grad_norm": 0.6412646254139903, + "learning_rate": 1.7754329718302808e-05, + "loss": 0.9538, + "step": 3926 + }, + { + "epoch": 0.24107553945793303, + "grad_norm": 0.651667118167698, + "learning_rate": 1.7753074061542338e-05, + "loss": 0.9678, + "step": 3927 + }, + { + "epoch": 0.24113692869639952, + "grad_norm": 0.6102175593380651, + "learning_rate": 1.7751818098261386e-05, + "loss": 0.9349, + "step": 3928 + }, + { + "epoch": 0.241198317934866, + "grad_norm": 0.6446567215222085, + "learning_rate": 1.7750561828509606e-05, + "loss": 0.9666, + "step": 3929 + }, + { + "epoch": 0.2412597071733325, + "grad_norm": 0.6617125969500979, + "learning_rate": 1.774930525233666e-05, + "loss": 1.0002, + "step": 3930 + }, + { + "epoch": 0.24132109641179902, + "grad_norm": 0.7226722865794152, + "learning_rate": 1.7748048369792235e-05, + "loss": 0.9671, + "step": 3931 + }, + { + "epoch": 0.24138248565026552, + "grad_norm": 0.6310115514186874, + "learning_rate": 1.7746791180926017e-05, + "loss": 0.9472, + "step": 3932 + }, + { + "epoch": 0.241443874888732, + "grad_norm": 0.6638723317350712, + "learning_rate": 1.7745533685787712e-05, + "loss": 0.9755, + "step": 3933 + }, + { + "epoch": 0.2415052641271985, + "grad_norm": 0.6537035965379066, + "learning_rate": 1.7744275884427033e-05, + "loss": 0.9789, + "step": 3934 + }, + { + "epoch": 0.241566653365665, + "grad_norm": 0.632177749468534, + "learning_rate": 1.7743017776893706e-05, + "loss": 0.9653, + "step": 3935 + }, + { + "epoch": 0.24162804260413148, + "grad_norm": 0.6833880144750085, + "learning_rate": 1.774175936323748e-05, + "loss": 1.0221, + "step": 3936 + }, + { + "epoch": 0.241689431842598, + "grad_norm": 0.6274787680826331, + "learning_rate": 1.7740500643508095e-05, + "loss": 0.9577, + "step": 3937 + }, + { + "epoch": 0.2417508210810645, + "grad_norm": 0.6043930391999444, + "learning_rate": 1.7739241617755325e-05, + "loss": 0.9548, + "step": 3938 + }, + { + "epoch": 0.24181221031953098, + "grad_norm": 0.6729951284101372, + "learning_rate": 1.7737982286028938e-05, + "loss": 0.7839, + "step": 3939 + }, + { + "epoch": 0.24187359955799748, + "grad_norm": 0.6929163134685303, + "learning_rate": 1.773672264837873e-05, + "loss": 0.9858, + "step": 3940 + }, + { + "epoch": 0.24193498879646397, + "grad_norm": 0.6780381384525793, + "learning_rate": 1.7735462704854492e-05, + "loss": 1.0268, + "step": 3941 + }, + { + "epoch": 0.2419963780349305, + "grad_norm": 0.6802951031374462, + "learning_rate": 1.7734202455506044e-05, + "loss": 1.0431, + "step": 3942 + }, + { + "epoch": 0.24205776727339698, + "grad_norm": 0.6829549911466861, + "learning_rate": 1.773294190038321e-05, + "loss": 1.0171, + "step": 3943 + }, + { + "epoch": 0.24211915651186347, + "grad_norm": 0.6430660332315098, + "learning_rate": 1.7731681039535815e-05, + "loss": 0.9837, + "step": 3944 + }, + { + "epoch": 0.24218054575032996, + "grad_norm": 0.6313041215884203, + "learning_rate": 1.7730419873013725e-05, + "loss": 0.9742, + "step": 3945 + }, + { + "epoch": 0.24224193498879645, + "grad_norm": 0.5449862975169789, + "learning_rate": 1.7729158400866787e-05, + "loss": 0.9259, + "step": 3946 + }, + { + "epoch": 0.24230332422726297, + "grad_norm": 0.6822903300609724, + "learning_rate": 1.7727896623144883e-05, + "loss": 1.0093, + "step": 3947 + }, + { + "epoch": 0.24236471346572946, + "grad_norm": 0.6734626536466253, + "learning_rate": 1.772663453989789e-05, + "loss": 1.0689, + "step": 3948 + }, + { + "epoch": 0.24242610270419596, + "grad_norm": 0.6391336163122519, + "learning_rate": 1.772537215117571e-05, + "loss": 0.9375, + "step": 3949 + }, + { + "epoch": 0.24248749194266245, + "grad_norm": 0.6811238970781446, + "learning_rate": 1.7724109457028255e-05, + "loss": 1.0319, + "step": 3950 + }, + { + "epoch": 0.24254888118112894, + "grad_norm": 0.6189167447053012, + "learning_rate": 1.7722846457505438e-05, + "loss": 0.9369, + "step": 3951 + }, + { + "epoch": 0.24261027041959546, + "grad_norm": 0.623327994865422, + "learning_rate": 1.7721583152657197e-05, + "loss": 0.9589, + "step": 3952 + }, + { + "epoch": 0.24267165965806195, + "grad_norm": 0.7201619494245363, + "learning_rate": 1.7720319542533472e-05, + "loss": 1.0543, + "step": 3953 + }, + { + "epoch": 0.24273304889652844, + "grad_norm": 0.6502657112911384, + "learning_rate": 1.771905562718423e-05, + "loss": 0.9567, + "step": 3954 + }, + { + "epoch": 0.24279443813499493, + "grad_norm": 0.6207680157885488, + "learning_rate": 1.771779140665943e-05, + "loss": 0.9764, + "step": 3955 + }, + { + "epoch": 0.24285582737346142, + "grad_norm": 0.6179602756276438, + "learning_rate": 1.771652688100906e-05, + "loss": 0.9542, + "step": 3956 + }, + { + "epoch": 0.24291721661192792, + "grad_norm": 0.6919495614504059, + "learning_rate": 1.7715262050283114e-05, + "loss": 0.9839, + "step": 3957 + }, + { + "epoch": 0.24297860585039444, + "grad_norm": 0.6951290699943337, + "learning_rate": 1.771399691453159e-05, + "loss": 1.0102, + "step": 3958 + }, + { + "epoch": 0.24303999508886093, + "grad_norm": 0.6354328645596682, + "learning_rate": 1.7712731473804514e-05, + "loss": 0.931, + "step": 3959 + }, + { + "epoch": 0.24310138432732742, + "grad_norm": 0.7377250536695379, + "learning_rate": 1.771146572815191e-05, + "loss": 1.0019, + "step": 3960 + }, + { + "epoch": 0.2431627735657939, + "grad_norm": 0.7280178907081989, + "learning_rate": 1.7710199677623826e-05, + "loss": 0.7158, + "step": 3961 + }, + { + "epoch": 0.2432241628042604, + "grad_norm": 0.6576454016047454, + "learning_rate": 1.770893332227031e-05, + "loss": 1.0049, + "step": 3962 + }, + { + "epoch": 0.24328555204272692, + "grad_norm": 0.7093206021229088, + "learning_rate": 1.7707666662141427e-05, + "loss": 0.9842, + "step": 3963 + }, + { + "epoch": 0.2433469412811934, + "grad_norm": 0.7476887568066791, + "learning_rate": 1.770639969728726e-05, + "loss": 1.0033, + "step": 3964 + }, + { + "epoch": 0.2434083305196599, + "grad_norm": 0.6449104385806504, + "learning_rate": 1.7705132427757895e-05, + "loss": 0.9913, + "step": 3965 + }, + { + "epoch": 0.2434697197581264, + "grad_norm": 0.7175955555498044, + "learning_rate": 1.7703864853603433e-05, + "loss": 0.9927, + "step": 3966 + }, + { + "epoch": 0.2435311089965929, + "grad_norm": 0.654894375808212, + "learning_rate": 1.7702596974873995e-05, + "loss": 0.95, + "step": 3967 + }, + { + "epoch": 0.2435924982350594, + "grad_norm": 0.6505736619915508, + "learning_rate": 1.77013287916197e-05, + "loss": 0.9833, + "step": 3968 + }, + { + "epoch": 0.2436538874735259, + "grad_norm": 0.6270762206816201, + "learning_rate": 1.7700060303890685e-05, + "loss": 0.966, + "step": 3969 + }, + { + "epoch": 0.2437152767119924, + "grad_norm": 0.6571146830034021, + "learning_rate": 1.769879151173711e-05, + "loss": 1.0289, + "step": 3970 + }, + { + "epoch": 0.24377666595045888, + "grad_norm": 0.6919783626981154, + "learning_rate": 1.7697522415209125e-05, + "loss": 1.0002, + "step": 3971 + }, + { + "epoch": 0.24383805518892537, + "grad_norm": 0.6389836949419567, + "learning_rate": 1.7696253014356914e-05, + "loss": 0.9955, + "step": 3972 + }, + { + "epoch": 0.24389944442739186, + "grad_norm": 0.6551742793886666, + "learning_rate": 1.7694983309230654e-05, + "loss": 0.97, + "step": 3973 + }, + { + "epoch": 0.24396083366585838, + "grad_norm": 0.6807047701586235, + "learning_rate": 1.769371329988055e-05, + "loss": 0.9874, + "step": 3974 + }, + { + "epoch": 0.24402222290432488, + "grad_norm": 0.6528578985927633, + "learning_rate": 1.769244298635681e-05, + "loss": 1.0022, + "step": 3975 + }, + { + "epoch": 0.24408361214279137, + "grad_norm": 0.6848287410291178, + "learning_rate": 1.769117236870966e-05, + "loss": 0.9906, + "step": 3976 + }, + { + "epoch": 0.24414500138125786, + "grad_norm": 0.6573168562745247, + "learning_rate": 1.768990144698933e-05, + "loss": 0.9356, + "step": 3977 + }, + { + "epoch": 0.24420639061972435, + "grad_norm": 0.6495149277683728, + "learning_rate": 1.7688630221246064e-05, + "loss": 0.927, + "step": 3978 + }, + { + "epoch": 0.24426777985819087, + "grad_norm": 0.6559330998404854, + "learning_rate": 1.7687358691530127e-05, + "loss": 0.9593, + "step": 3979 + }, + { + "epoch": 0.24432916909665736, + "grad_norm": 0.8145169532486409, + "learning_rate": 1.7686086857891786e-05, + "loss": 0.7458, + "step": 3980 + }, + { + "epoch": 0.24439055833512385, + "grad_norm": 0.6443776441196395, + "learning_rate": 1.7684814720381317e-05, + "loss": 0.9713, + "step": 3981 + }, + { + "epoch": 0.24445194757359034, + "grad_norm": 0.7089071142376565, + "learning_rate": 1.7683542279049027e-05, + "loss": 1.0127, + "step": 3982 + }, + { + "epoch": 0.24451333681205684, + "grad_norm": 0.7479221840029016, + "learning_rate": 1.7682269533945216e-05, + "loss": 1.0301, + "step": 3983 + }, + { + "epoch": 0.24457472605052336, + "grad_norm": 0.6485396915305336, + "learning_rate": 1.7680996485120202e-05, + "loss": 0.9969, + "step": 3984 + }, + { + "epoch": 0.24463611528898985, + "grad_norm": 0.6530859605707474, + "learning_rate": 1.7679723132624315e-05, + "loss": 0.9854, + "step": 3985 + }, + { + "epoch": 0.24469750452745634, + "grad_norm": 0.615532907306524, + "learning_rate": 1.7678449476507902e-05, + "loss": 1.0026, + "step": 3986 + }, + { + "epoch": 0.24475889376592283, + "grad_norm": 0.6423336108541018, + "learning_rate": 1.767717551682131e-05, + "loss": 0.9788, + "step": 3987 + }, + { + "epoch": 0.24482028300438932, + "grad_norm": 0.6597774354528992, + "learning_rate": 1.7675901253614913e-05, + "loss": 0.9687, + "step": 3988 + }, + { + "epoch": 0.24488167224285584, + "grad_norm": 0.6342718949142283, + "learning_rate": 1.767462668693908e-05, + "loss": 0.974, + "step": 3989 + }, + { + "epoch": 0.24494306148132233, + "grad_norm": 0.6509861573875781, + "learning_rate": 1.767335181684421e-05, + "loss": 1.0012, + "step": 3990 + }, + { + "epoch": 0.24500445071978882, + "grad_norm": 0.6913645059278399, + "learning_rate": 1.7672076643380705e-05, + "loss": 0.9455, + "step": 3991 + }, + { + "epoch": 0.24506583995825532, + "grad_norm": 0.6570748341808641, + "learning_rate": 1.7670801166598976e-05, + "loss": 0.9636, + "step": 3992 + }, + { + "epoch": 0.2451272291967218, + "grad_norm": 0.7133482590926321, + "learning_rate": 1.766952538654945e-05, + "loss": 0.9775, + "step": 3993 + }, + { + "epoch": 0.2451886184351883, + "grad_norm": 0.6977255796575348, + "learning_rate": 1.7668249303282568e-05, + "loss": 1.0611, + "step": 3994 + }, + { + "epoch": 0.24525000767365482, + "grad_norm": 0.6755577747844298, + "learning_rate": 1.7666972916848776e-05, + "loss": 0.9977, + "step": 3995 + }, + { + "epoch": 0.2453113969121213, + "grad_norm": 0.6716365362803004, + "learning_rate": 1.766569622729854e-05, + "loss": 1.0184, + "step": 3996 + }, + { + "epoch": 0.2453727861505878, + "grad_norm": 0.6632701457106855, + "learning_rate": 1.766441923468233e-05, + "loss": 1.0206, + "step": 3997 + }, + { + "epoch": 0.2454341753890543, + "grad_norm": 0.6650445431847728, + "learning_rate": 1.766314193905064e-05, + "loss": 1.0056, + "step": 3998 + }, + { + "epoch": 0.24549556462752078, + "grad_norm": 0.5806869672641353, + "learning_rate": 1.766186434045396e-05, + "loss": 0.9221, + "step": 3999 + }, + { + "epoch": 0.2455569538659873, + "grad_norm": 0.6642159535656275, + "learning_rate": 1.7660586438942807e-05, + "loss": 0.9986, + "step": 4000 + }, + { + "epoch": 0.2456183431044538, + "grad_norm": 0.6391540703096708, + "learning_rate": 1.76593082345677e-05, + "loss": 1.0186, + "step": 4001 + }, + { + "epoch": 0.2456797323429203, + "grad_norm": 0.773650774614839, + "learning_rate": 1.765802972737917e-05, + "loss": 0.8098, + "step": 4002 + }, + { + "epoch": 0.24574112158138678, + "grad_norm": 0.6726410968053004, + "learning_rate": 1.7656750917427772e-05, + "loss": 0.9899, + "step": 4003 + }, + { + "epoch": 0.24580251081985327, + "grad_norm": 0.7468795794890584, + "learning_rate": 1.7655471804764056e-05, + "loss": 1.0306, + "step": 4004 + }, + { + "epoch": 0.2458639000583198, + "grad_norm": 0.6850503901344843, + "learning_rate": 1.7654192389438596e-05, + "loss": 0.9954, + "step": 4005 + }, + { + "epoch": 0.24592528929678628, + "grad_norm": 0.6477160679374071, + "learning_rate": 1.7652912671501975e-05, + "loss": 0.9677, + "step": 4006 + }, + { + "epoch": 0.24598667853525277, + "grad_norm": 0.6532886542473816, + "learning_rate": 1.7651632651004783e-05, + "loss": 0.9158, + "step": 4007 + }, + { + "epoch": 0.24604806777371926, + "grad_norm": 0.7077810866302168, + "learning_rate": 1.7650352327997627e-05, + "loss": 1.0124, + "step": 4008 + }, + { + "epoch": 0.24610945701218576, + "grad_norm": 0.6984754764601129, + "learning_rate": 1.764907170253113e-05, + "loss": 0.9791, + "step": 4009 + }, + { + "epoch": 0.24617084625065225, + "grad_norm": 0.6902583148490398, + "learning_rate": 1.7647790774655917e-05, + "loss": 0.9886, + "step": 4010 + }, + { + "epoch": 0.24623223548911877, + "grad_norm": 0.6916290933869971, + "learning_rate": 1.7646509544422633e-05, + "loss": 0.961, + "step": 4011 + }, + { + "epoch": 0.24629362472758526, + "grad_norm": 0.6215075461926092, + "learning_rate": 1.764522801188193e-05, + "loss": 0.912, + "step": 4012 + }, + { + "epoch": 0.24635501396605175, + "grad_norm": 0.6590362587740327, + "learning_rate": 1.764394617708447e-05, + "loss": 0.9849, + "step": 4013 + }, + { + "epoch": 0.24641640320451824, + "grad_norm": 0.6953792349269962, + "learning_rate": 1.764266404008094e-05, + "loss": 0.9763, + "step": 4014 + }, + { + "epoch": 0.24647779244298473, + "grad_norm": 0.7661203239256476, + "learning_rate": 1.7641381600922024e-05, + "loss": 1.0417, + "step": 4015 + }, + { + "epoch": 0.24653918168145125, + "grad_norm": 0.6832464023159073, + "learning_rate": 1.764009885965842e-05, + "loss": 0.9804, + "step": 4016 + }, + { + "epoch": 0.24660057091991774, + "grad_norm": 0.6228496324138776, + "learning_rate": 1.763881581634085e-05, + "loss": 0.941, + "step": 4017 + }, + { + "epoch": 0.24666196015838424, + "grad_norm": 0.6557919285086347, + "learning_rate": 1.7637532471020032e-05, + "loss": 0.9509, + "step": 4018 + }, + { + "epoch": 0.24672334939685073, + "grad_norm": 0.6788015131855792, + "learning_rate": 1.763624882374671e-05, + "loss": 0.9646, + "step": 4019 + }, + { + "epoch": 0.24678473863531722, + "grad_norm": 0.720228726794301, + "learning_rate": 1.7634964874571633e-05, + "loss": 0.9986, + "step": 4020 + }, + { + "epoch": 0.24684612787378374, + "grad_norm": 0.7035751623161948, + "learning_rate": 1.7633680623545556e-05, + "loss": 0.973, + "step": 4021 + }, + { + "epoch": 0.24690751711225023, + "grad_norm": 0.67140986947101, + "learning_rate": 1.763239607071926e-05, + "loss": 0.9658, + "step": 4022 + }, + { + "epoch": 0.24696890635071672, + "grad_norm": 0.6910701348849227, + "learning_rate": 1.763111121614352e-05, + "loss": 0.9971, + "step": 4023 + }, + { + "epoch": 0.2470302955891832, + "grad_norm": 0.6201248596394634, + "learning_rate": 1.7629826059869142e-05, + "loss": 0.9374, + "step": 4024 + }, + { + "epoch": 0.2470916848276497, + "grad_norm": 0.6174099621076207, + "learning_rate": 1.7628540601946934e-05, + "loss": 0.9559, + "step": 4025 + }, + { + "epoch": 0.2471530740661162, + "grad_norm": 0.6030921529257675, + "learning_rate": 1.7627254842427714e-05, + "loss": 0.9567, + "step": 4026 + }, + { + "epoch": 0.24721446330458272, + "grad_norm": 0.6593974636506922, + "learning_rate": 1.762596878136232e-05, + "loss": 0.966, + "step": 4027 + }, + { + "epoch": 0.2472758525430492, + "grad_norm": 0.6415101384184025, + "learning_rate": 1.7624682418801592e-05, + "loss": 0.9548, + "step": 4028 + }, + { + "epoch": 0.2473372417815157, + "grad_norm": 0.6546267496834318, + "learning_rate": 1.7623395754796386e-05, + "loss": 0.9201, + "step": 4029 + }, + { + "epoch": 0.2473986310199822, + "grad_norm": 0.6482817046534144, + "learning_rate": 1.7622108789397577e-05, + "loss": 0.9839, + "step": 4030 + }, + { + "epoch": 0.24746002025844868, + "grad_norm": 0.6070348066929404, + "learning_rate": 1.762082152265604e-05, + "loss": 1.0039, + "step": 4031 + }, + { + "epoch": 0.2475214094969152, + "grad_norm": 0.6864815554384363, + "learning_rate": 1.761953395462267e-05, + "loss": 1.0451, + "step": 4032 + }, + { + "epoch": 0.2475827987353817, + "grad_norm": 0.6479468193409306, + "learning_rate": 1.7618246085348364e-05, + "loss": 0.9959, + "step": 4033 + }, + { + "epoch": 0.24764418797384818, + "grad_norm": 0.6538757165816844, + "learning_rate": 1.761695791488405e-05, + "loss": 0.9542, + "step": 4034 + }, + { + "epoch": 0.24770557721231468, + "grad_norm": 0.6104528894298669, + "learning_rate": 1.7615669443280652e-05, + "loss": 0.9484, + "step": 4035 + }, + { + "epoch": 0.24776696645078117, + "grad_norm": 0.6230394956153237, + "learning_rate": 1.761438067058911e-05, + "loss": 1.011, + "step": 4036 + }, + { + "epoch": 0.2478283556892477, + "grad_norm": 0.6742346060495303, + "learning_rate": 1.7613091596860375e-05, + "loss": 1.0368, + "step": 4037 + }, + { + "epoch": 0.24788974492771418, + "grad_norm": 0.6311573245268197, + "learning_rate": 1.761180222214541e-05, + "loss": 0.9587, + "step": 4038 + }, + { + "epoch": 0.24795113416618067, + "grad_norm": 0.8881090962867004, + "learning_rate": 1.7610512546495195e-05, + "loss": 1.035, + "step": 4039 + }, + { + "epoch": 0.24801252340464716, + "grad_norm": 0.6501381060997725, + "learning_rate": 1.7609222569960712e-05, + "loss": 0.956, + "step": 4040 + }, + { + "epoch": 0.24807391264311365, + "grad_norm": 0.6816275146242676, + "learning_rate": 1.7607932292592965e-05, + "loss": 1.0184, + "step": 4041 + }, + { + "epoch": 0.24813530188158017, + "grad_norm": 0.6802034455455118, + "learning_rate": 1.7606641714442967e-05, + "loss": 0.9299, + "step": 4042 + }, + { + "epoch": 0.24819669112004666, + "grad_norm": 0.6320427601394795, + "learning_rate": 1.7605350835561735e-05, + "loss": 1.0115, + "step": 4043 + }, + { + "epoch": 0.24825808035851316, + "grad_norm": 0.6813260817935998, + "learning_rate": 1.7604059656000313e-05, + "loss": 1.0011, + "step": 4044 + }, + { + "epoch": 0.24831946959697965, + "grad_norm": 0.6625483170840523, + "learning_rate": 1.7602768175809738e-05, + "loss": 0.9552, + "step": 4045 + }, + { + "epoch": 0.24838085883544614, + "grad_norm": 0.7148935121196673, + "learning_rate": 1.7601476395041078e-05, + "loss": 0.9633, + "step": 4046 + }, + { + "epoch": 0.24844224807391263, + "grad_norm": 0.6788109400688029, + "learning_rate": 1.76001843137454e-05, + "loss": 0.9814, + "step": 4047 + }, + { + "epoch": 0.24850363731237915, + "grad_norm": 0.6259266551139377, + "learning_rate": 1.7598891931973784e-05, + "loss": 0.9543, + "step": 4048 + }, + { + "epoch": 0.24856502655084564, + "grad_norm": 0.6525233242384579, + "learning_rate": 1.759759924977733e-05, + "loss": 0.9388, + "step": 4049 + }, + { + "epoch": 0.24862641578931213, + "grad_norm": 0.678100030975004, + "learning_rate": 1.7596306267207147e-05, + "loss": 1.0083, + "step": 4050 + }, + { + "epoch": 0.24868780502777862, + "grad_norm": 0.6554497076821438, + "learning_rate": 1.7595012984314345e-05, + "loss": 0.9216, + "step": 4051 + }, + { + "epoch": 0.24874919426624512, + "grad_norm": 0.6496068702411235, + "learning_rate": 1.7593719401150063e-05, + "loss": 0.9849, + "step": 4052 + }, + { + "epoch": 0.24881058350471164, + "grad_norm": 0.6474629837388057, + "learning_rate": 1.7592425517765433e-05, + "loss": 0.9369, + "step": 4053 + }, + { + "epoch": 0.24887197274317813, + "grad_norm": 0.67303302583857, + "learning_rate": 1.7591131334211618e-05, + "loss": 1.0007, + "step": 4054 + }, + { + "epoch": 0.24893336198164462, + "grad_norm": 0.6152475667834508, + "learning_rate": 1.758983685053978e-05, + "loss": 0.945, + "step": 4055 + }, + { + "epoch": 0.2489947512201111, + "grad_norm": 0.6904207091618073, + "learning_rate": 1.75885420668011e-05, + "loss": 0.9489, + "step": 4056 + }, + { + "epoch": 0.2490561404585776, + "grad_norm": 0.6887066069973526, + "learning_rate": 1.7587246983046766e-05, + "loss": 1.0207, + "step": 4057 + }, + { + "epoch": 0.24911752969704412, + "grad_norm": 0.6757834607296864, + "learning_rate": 1.758595159932798e-05, + "loss": 0.9316, + "step": 4058 + }, + { + "epoch": 0.2491789189355106, + "grad_norm": 0.6147664242350226, + "learning_rate": 1.758465591569595e-05, + "loss": 0.9406, + "step": 4059 + }, + { + "epoch": 0.2492403081739771, + "grad_norm": 0.6225985556111016, + "learning_rate": 1.758335993220191e-05, + "loss": 0.9089, + "step": 4060 + }, + { + "epoch": 0.2493016974124436, + "grad_norm": 0.5627659732667961, + "learning_rate": 1.7582063648897092e-05, + "loss": 0.9547, + "step": 4061 + }, + { + "epoch": 0.2493630866509101, + "grad_norm": 0.592488010342095, + "learning_rate": 1.758076706583275e-05, + "loss": 0.9599, + "step": 4062 + }, + { + "epoch": 0.24942447588937658, + "grad_norm": 0.6312140311917193, + "learning_rate": 1.7579470183060135e-05, + "loss": 0.9549, + "step": 4063 + }, + { + "epoch": 0.2494858651278431, + "grad_norm": 0.7276536976774928, + "learning_rate": 1.7578173000630528e-05, + "loss": 0.9668, + "step": 4064 + }, + { + "epoch": 0.2495472543663096, + "grad_norm": 0.6967587335888961, + "learning_rate": 1.757687551859521e-05, + "loss": 1.0025, + "step": 4065 + }, + { + "epoch": 0.24960864360477608, + "grad_norm": 0.7063513111096579, + "learning_rate": 1.7575577737005484e-05, + "loss": 0.987, + "step": 4066 + }, + { + "epoch": 0.24967003284324257, + "grad_norm": 0.6256624457130551, + "learning_rate": 1.7574279655912646e-05, + "loss": 0.9619, + "step": 4067 + }, + { + "epoch": 0.24973142208170906, + "grad_norm": 0.6761587894993678, + "learning_rate": 1.757298127536803e-05, + "loss": 0.9973, + "step": 4068 + }, + { + "epoch": 0.24979281132017558, + "grad_norm": 0.6954224196931738, + "learning_rate": 1.7571682595422956e-05, + "loss": 1.0278, + "step": 4069 + }, + { + "epoch": 0.24985420055864208, + "grad_norm": 0.6130900269645342, + "learning_rate": 1.7570383616128775e-05, + "loss": 0.9865, + "step": 4070 + }, + { + "epoch": 0.24991558979710857, + "grad_norm": 0.6462550204600293, + "learning_rate": 1.756908433753684e-05, + "loss": 0.9727, + "step": 4071 + }, + { + "epoch": 0.24997697903557506, + "grad_norm": 0.6700140644041167, + "learning_rate": 1.756778475969852e-05, + "loss": 0.9752, + "step": 4072 + }, + { + "epoch": 0.2500383682740416, + "grad_norm": 0.6284938754052731, + "learning_rate": 1.7566484882665192e-05, + "loss": 0.9601, + "step": 4073 + }, + { + "epoch": 0.25009975751250807, + "grad_norm": 0.5776492946884954, + "learning_rate": 1.756518470648825e-05, + "loss": 0.9293, + "step": 4074 + }, + { + "epoch": 0.25016114675097456, + "grad_norm": 0.6911050850140678, + "learning_rate": 1.756388423121909e-05, + "loss": 0.9679, + "step": 4075 + }, + { + "epoch": 0.25022253598944105, + "grad_norm": 0.6459880232319027, + "learning_rate": 1.7562583456909135e-05, + "loss": 0.9282, + "step": 4076 + }, + { + "epoch": 0.25028392522790754, + "grad_norm": 0.6113401509608319, + "learning_rate": 1.756128238360981e-05, + "loss": 0.9685, + "step": 4077 + }, + { + "epoch": 0.25034531446637404, + "grad_norm": 0.727424199621434, + "learning_rate": 1.7559981011372548e-05, + "loss": 0.9988, + "step": 4078 + }, + { + "epoch": 0.2504067037048405, + "grad_norm": 0.6473720705500292, + "learning_rate": 1.7558679340248806e-05, + "loss": 0.9475, + "step": 4079 + }, + { + "epoch": 0.250468092943307, + "grad_norm": 0.6251695531854573, + "learning_rate": 1.755737737029004e-05, + "loss": 0.9342, + "step": 4080 + }, + { + "epoch": 0.2505294821817735, + "grad_norm": 0.6434720929939863, + "learning_rate": 1.7556075101547732e-05, + "loss": 0.969, + "step": 4081 + }, + { + "epoch": 0.25059087142024006, + "grad_norm": 0.634413918687103, + "learning_rate": 1.7554772534073355e-05, + "loss": 0.9976, + "step": 4082 + }, + { + "epoch": 0.25065226065870655, + "grad_norm": 0.6420950519506369, + "learning_rate": 1.755346966791842e-05, + "loss": 1.0098, + "step": 4083 + }, + { + "epoch": 0.25071364989717304, + "grad_norm": 0.6619180007007655, + "learning_rate": 1.755216650313443e-05, + "loss": 0.9816, + "step": 4084 + }, + { + "epoch": 0.25077503913563953, + "grad_norm": 0.6776932201633491, + "learning_rate": 1.7550863039772907e-05, + "loss": 0.9787, + "step": 4085 + }, + { + "epoch": 0.250836428374106, + "grad_norm": 0.6640321338177296, + "learning_rate": 1.754955927788538e-05, + "loss": 0.992, + "step": 4086 + }, + { + "epoch": 0.2508978176125725, + "grad_norm": 0.6794236201222419, + "learning_rate": 1.7548255217523397e-05, + "loss": 1.0051, + "step": 4087 + }, + { + "epoch": 0.250959206851039, + "grad_norm": 1.3446734994991332, + "learning_rate": 1.7546950858738515e-05, + "loss": 0.9349, + "step": 4088 + }, + { + "epoch": 0.2510205960895055, + "grad_norm": 0.6817656251381036, + "learning_rate": 1.7545646201582304e-05, + "loss": 0.9401, + "step": 4089 + }, + { + "epoch": 0.251081985327972, + "grad_norm": 0.6089367190175141, + "learning_rate": 1.7544341246106337e-05, + "loss": 0.9865, + "step": 4090 + }, + { + "epoch": 0.2511433745664385, + "grad_norm": 0.6901847807598618, + "learning_rate": 1.7543035992362216e-05, + "loss": 1.0636, + "step": 4091 + }, + { + "epoch": 0.251204763804905, + "grad_norm": 0.6964600435686247, + "learning_rate": 1.7541730440401537e-05, + "loss": 1.0001, + "step": 4092 + }, + { + "epoch": 0.2512661530433715, + "grad_norm": 0.7227484066188392, + "learning_rate": 1.7540424590275917e-05, + "loss": 1.0104, + "step": 4093 + }, + { + "epoch": 0.251327542281838, + "grad_norm": 0.6895072545386599, + "learning_rate": 1.7539118442036983e-05, + "loss": 0.9889, + "step": 4094 + }, + { + "epoch": 0.2513889315203045, + "grad_norm": 0.7261104812107334, + "learning_rate": 1.7537811995736374e-05, + "loss": 1.054, + "step": 4095 + }, + { + "epoch": 0.251450320758771, + "grad_norm": 0.613326000230567, + "learning_rate": 1.7536505251425743e-05, + "loss": 0.9317, + "step": 4096 + }, + { + "epoch": 0.2515117099972375, + "grad_norm": 0.6454642152970775, + "learning_rate": 1.7535198209156754e-05, + "loss": 0.9565, + "step": 4097 + }, + { + "epoch": 0.251573099235704, + "grad_norm": 0.6562576693705926, + "learning_rate": 1.753389086898108e-05, + "loss": 1.0434, + "step": 4098 + }, + { + "epoch": 0.25163448847417047, + "grad_norm": 0.6443244930225317, + "learning_rate": 1.75325832309504e-05, + "loss": 1.0109, + "step": 4099 + }, + { + "epoch": 0.25169587771263696, + "grad_norm": 0.6407681637423779, + "learning_rate": 1.7531275295116424e-05, + "loss": 0.9485, + "step": 4100 + }, + { + "epoch": 0.25175726695110345, + "grad_norm": 0.645752806747452, + "learning_rate": 1.752996706153085e-05, + "loss": 0.9784, + "step": 4101 + }, + { + "epoch": 0.25181865618956994, + "grad_norm": 0.621834130156784, + "learning_rate": 1.752865853024541e-05, + "loss": 0.9595, + "step": 4102 + }, + { + "epoch": 0.2518800454280365, + "grad_norm": 0.5982296883281867, + "learning_rate": 1.7527349701311823e-05, + "loss": 0.9084, + "step": 4103 + }, + { + "epoch": 0.251941434666503, + "grad_norm": 0.6929052846699219, + "learning_rate": 1.7526040574781854e-05, + "loss": 1.0045, + "step": 4104 + }, + { + "epoch": 0.2520028239049695, + "grad_norm": 0.6066869574648924, + "learning_rate": 1.7524731150707243e-05, + "loss": 0.9976, + "step": 4105 + }, + { + "epoch": 0.25206421314343597, + "grad_norm": 0.6489896475759729, + "learning_rate": 1.7523421429139766e-05, + "loss": 0.9723, + "step": 4106 + }, + { + "epoch": 0.25212560238190246, + "grad_norm": 0.6149510797490689, + "learning_rate": 1.75221114101312e-05, + "loss": 0.96, + "step": 4107 + }, + { + "epoch": 0.25218699162036895, + "grad_norm": 0.6622104596023083, + "learning_rate": 1.7520801093733343e-05, + "loss": 0.9966, + "step": 4108 + }, + { + "epoch": 0.25224838085883544, + "grad_norm": 0.5961733305572784, + "learning_rate": 1.7519490479997992e-05, + "loss": 0.8151, + "step": 4109 + }, + { + "epoch": 0.25230977009730193, + "grad_norm": 0.6084362349785822, + "learning_rate": 1.7518179568976964e-05, + "loss": 0.9525, + "step": 4110 + }, + { + "epoch": 0.2523711593357684, + "grad_norm": 0.652556170251605, + "learning_rate": 1.751686836072209e-05, + "loss": 0.9724, + "step": 4111 + }, + { + "epoch": 0.2524325485742349, + "grad_norm": 0.674757078965023, + "learning_rate": 1.7515556855285205e-05, + "loss": 0.9777, + "step": 4112 + }, + { + "epoch": 0.2524939378127014, + "grad_norm": 0.6613027440042395, + "learning_rate": 1.7514245052718164e-05, + "loss": 0.9811, + "step": 4113 + }, + { + "epoch": 0.25255532705116795, + "grad_norm": 0.6595756304365834, + "learning_rate": 1.7512932953072826e-05, + "loss": 0.9384, + "step": 4114 + }, + { + "epoch": 0.25261671628963445, + "grad_norm": 0.6443351233530469, + "learning_rate": 1.7511620556401064e-05, + "loss": 0.9593, + "step": 4115 + }, + { + "epoch": 0.25267810552810094, + "grad_norm": 0.6495020647071725, + "learning_rate": 1.751030786275477e-05, + "loss": 0.9389, + "step": 4116 + }, + { + "epoch": 0.25273949476656743, + "grad_norm": 0.7321062331417828, + "learning_rate": 1.7508994872185836e-05, + "loss": 1.0189, + "step": 4117 + }, + { + "epoch": 0.2528008840050339, + "grad_norm": 0.6891674728343891, + "learning_rate": 1.7507681584746176e-05, + "loss": 1.0256, + "step": 4118 + }, + { + "epoch": 0.2528622732435004, + "grad_norm": 0.6705411530561163, + "learning_rate": 1.7506368000487706e-05, + "loss": 1.0115, + "step": 4119 + }, + { + "epoch": 0.2529236624819669, + "grad_norm": 0.6870742889798702, + "learning_rate": 1.7505054119462363e-05, + "loss": 0.9929, + "step": 4120 + }, + { + "epoch": 0.2529850517204334, + "grad_norm": 0.6492320106510099, + "learning_rate": 1.750373994172209e-05, + "loss": 0.9145, + "step": 4121 + }, + { + "epoch": 0.2530464409588999, + "grad_norm": 0.6963231634573152, + "learning_rate": 1.7502425467318847e-05, + "loss": 0.9443, + "step": 4122 + }, + { + "epoch": 0.2531078301973664, + "grad_norm": 0.6605450954256673, + "learning_rate": 1.7501110696304598e-05, + "loss": 0.9331, + "step": 4123 + }, + { + "epoch": 0.2531692194358329, + "grad_norm": 0.7008756766269351, + "learning_rate": 1.7499795628731324e-05, + "loss": 1.0338, + "step": 4124 + }, + { + "epoch": 0.2532306086742994, + "grad_norm": 0.6199604806286285, + "learning_rate": 1.7498480264651017e-05, + "loss": 0.7823, + "step": 4125 + }, + { + "epoch": 0.2532919979127659, + "grad_norm": 0.7027450052053493, + "learning_rate": 1.749716460411568e-05, + "loss": 0.9592, + "step": 4126 + }, + { + "epoch": 0.2533533871512324, + "grad_norm": 0.6184506775062958, + "learning_rate": 1.749584864717733e-05, + "loss": 0.9488, + "step": 4127 + }, + { + "epoch": 0.2534147763896989, + "grad_norm": 0.6940343431682321, + "learning_rate": 1.749453239388799e-05, + "loss": 0.9972, + "step": 4128 + }, + { + "epoch": 0.2534761656281654, + "grad_norm": 0.6711441775885393, + "learning_rate": 1.7493215844299706e-05, + "loss": 1.0321, + "step": 4129 + }, + { + "epoch": 0.2535375548666319, + "grad_norm": 0.6330663113232173, + "learning_rate": 1.7491898998464517e-05, + "loss": 0.9607, + "step": 4130 + }, + { + "epoch": 0.25359894410509837, + "grad_norm": 0.6299605986450921, + "learning_rate": 1.7490581856434494e-05, + "loss": 0.9545, + "step": 4131 + }, + { + "epoch": 0.25366033334356486, + "grad_norm": 0.6828054599051264, + "learning_rate": 1.748926441826171e-05, + "loss": 1.0166, + "step": 4132 + }, + { + "epoch": 0.25372172258203135, + "grad_norm": 0.6482053826442058, + "learning_rate": 1.7487946683998246e-05, + "loss": 0.9148, + "step": 4133 + }, + { + "epoch": 0.25378311182049784, + "grad_norm": 0.6458538017008448, + "learning_rate": 1.74866286536962e-05, + "loss": 0.9703, + "step": 4134 + }, + { + "epoch": 0.2538445010589644, + "grad_norm": 0.6592842087121228, + "learning_rate": 1.7485310327407685e-05, + "loss": 0.9979, + "step": 4135 + }, + { + "epoch": 0.2539058902974309, + "grad_norm": 0.6465971513929082, + "learning_rate": 1.748399170518481e-05, + "loss": 0.9459, + "step": 4136 + }, + { + "epoch": 0.2539672795358974, + "grad_norm": 0.6670354385503535, + "learning_rate": 1.7482672787079726e-05, + "loss": 0.9876, + "step": 4137 + }, + { + "epoch": 0.25402866877436386, + "grad_norm": 0.6449672713161051, + "learning_rate": 1.7481353573144562e-05, + "loss": 0.948, + "step": 4138 + }, + { + "epoch": 0.25409005801283036, + "grad_norm": 0.6803293613404126, + "learning_rate": 1.748003406343148e-05, + "loss": 0.9927, + "step": 4139 + }, + { + "epoch": 0.25415144725129685, + "grad_norm": 0.6725822027011801, + "learning_rate": 1.7478714257992643e-05, + "loss": 0.9968, + "step": 4140 + }, + { + "epoch": 0.25421283648976334, + "grad_norm": 0.6235897203080033, + "learning_rate": 1.7477394156880236e-05, + "loss": 0.9311, + "step": 4141 + }, + { + "epoch": 0.25427422572822983, + "grad_norm": 0.6328906896746289, + "learning_rate": 1.7476073760146445e-05, + "loss": 0.9461, + "step": 4142 + }, + { + "epoch": 0.2543356149666963, + "grad_norm": 0.7229015938777948, + "learning_rate": 1.7474753067843472e-05, + "loss": 1.0401, + "step": 4143 + }, + { + "epoch": 0.2543970042051628, + "grad_norm": 0.6507864044879601, + "learning_rate": 1.747343208002353e-05, + "loss": 0.9725, + "step": 4144 + }, + { + "epoch": 0.2544583934436293, + "grad_norm": 0.6402501641733134, + "learning_rate": 1.747211079673885e-05, + "loss": 0.9595, + "step": 4145 + }, + { + "epoch": 0.25451978268209585, + "grad_norm": 0.6229179712197148, + "learning_rate": 1.7470789218041668e-05, + "loss": 0.9713, + "step": 4146 + }, + { + "epoch": 0.25458117192056234, + "grad_norm": 0.682246382024044, + "learning_rate": 1.746946734398423e-05, + "loss": 1.0343, + "step": 4147 + }, + { + "epoch": 0.25464256115902884, + "grad_norm": 0.6034639362925975, + "learning_rate": 1.74681451746188e-05, + "loss": 0.9848, + "step": 4148 + }, + { + "epoch": 0.2547039503974953, + "grad_norm": 0.6494666496634367, + "learning_rate": 1.7466822709997643e-05, + "loss": 1.0069, + "step": 4149 + }, + { + "epoch": 0.2547653396359618, + "grad_norm": 0.6377401960404157, + "learning_rate": 1.7465499950173054e-05, + "loss": 0.9427, + "step": 4150 + }, + { + "epoch": 0.2548267288744283, + "grad_norm": 0.621806230370042, + "learning_rate": 1.7464176895197323e-05, + "loss": 0.9512, + "step": 4151 + }, + { + "epoch": 0.2548881181128948, + "grad_norm": 0.6019722052720626, + "learning_rate": 1.746285354512276e-05, + "loss": 0.9287, + "step": 4152 + }, + { + "epoch": 0.2549495073513613, + "grad_norm": 0.6865998848407309, + "learning_rate": 1.746152990000168e-05, + "loss": 0.9593, + "step": 4153 + }, + { + "epoch": 0.2550108965898278, + "grad_norm": 0.6576462285448281, + "learning_rate": 1.7460205959886416e-05, + "loss": 0.9734, + "step": 4154 + }, + { + "epoch": 0.2550722858282943, + "grad_norm": 0.7021324268815209, + "learning_rate": 1.745888172482931e-05, + "loss": 0.9933, + "step": 4155 + }, + { + "epoch": 0.2551336750667608, + "grad_norm": 0.6268589290099015, + "learning_rate": 1.7457557194882717e-05, + "loss": 0.9358, + "step": 4156 + }, + { + "epoch": 0.2551950643052273, + "grad_norm": 0.6812847932754543, + "learning_rate": 1.7456232370099003e-05, + "loss": 0.9545, + "step": 4157 + }, + { + "epoch": 0.2552564535436938, + "grad_norm": 0.700574509736593, + "learning_rate": 1.7454907250530544e-05, + "loss": 0.9444, + "step": 4158 + }, + { + "epoch": 0.2553178427821603, + "grad_norm": 0.6305961486176421, + "learning_rate": 1.745358183622973e-05, + "loss": 0.9403, + "step": 4159 + }, + { + "epoch": 0.2553792320206268, + "grad_norm": 0.6647719413163681, + "learning_rate": 1.745225612724896e-05, + "loss": 1.0137, + "step": 4160 + }, + { + "epoch": 0.2554406212590933, + "grad_norm": 0.687030949265232, + "learning_rate": 1.745093012364065e-05, + "loss": 1.0199, + "step": 4161 + }, + { + "epoch": 0.2555020104975598, + "grad_norm": 0.7045177759045019, + "learning_rate": 1.744960382545722e-05, + "loss": 0.982, + "step": 4162 + }, + { + "epoch": 0.25556339973602626, + "grad_norm": 0.6340454338233545, + "learning_rate": 1.744827723275111e-05, + "loss": 0.9211, + "step": 4163 + }, + { + "epoch": 0.25562478897449276, + "grad_norm": 0.6963743675511521, + "learning_rate": 1.7446950345574762e-05, + "loss": 1.019, + "step": 4164 + }, + { + "epoch": 0.25568617821295925, + "grad_norm": 0.6824440593417945, + "learning_rate": 1.744562316398064e-05, + "loss": 0.9441, + "step": 4165 + }, + { + "epoch": 0.25574756745142574, + "grad_norm": 0.6931366379647875, + "learning_rate": 1.744429568802121e-05, + "loss": 1.0034, + "step": 4166 + }, + { + "epoch": 0.2558089566898923, + "grad_norm": 0.6633459728203122, + "learning_rate": 1.744296791774896e-05, + "loss": 1.0068, + "step": 4167 + }, + { + "epoch": 0.2558703459283588, + "grad_norm": 0.6194084645810488, + "learning_rate": 1.7441639853216375e-05, + "loss": 0.7904, + "step": 4168 + }, + { + "epoch": 0.25593173516682527, + "grad_norm": 0.6344956192450086, + "learning_rate": 1.744031149447597e-05, + "loss": 0.9637, + "step": 4169 + }, + { + "epoch": 0.25599312440529176, + "grad_norm": 0.6643203965606593, + "learning_rate": 1.743898284158026e-05, + "loss": 0.9862, + "step": 4170 + }, + { + "epoch": 0.25605451364375825, + "grad_norm": 0.6449320472592891, + "learning_rate": 1.7437653894581767e-05, + "loss": 0.9419, + "step": 4171 + }, + { + "epoch": 0.25611590288222474, + "grad_norm": 0.5924852411291216, + "learning_rate": 1.7436324653533038e-05, + "loss": 0.9043, + "step": 4172 + }, + { + "epoch": 0.25617729212069124, + "grad_norm": 0.600072450864282, + "learning_rate": 1.7434995118486622e-05, + "loss": 0.9201, + "step": 4173 + }, + { + "epoch": 0.2562386813591577, + "grad_norm": 0.5975455196719348, + "learning_rate": 1.7433665289495085e-05, + "loss": 0.9303, + "step": 4174 + }, + { + "epoch": 0.2563000705976242, + "grad_norm": 0.6404731434201519, + "learning_rate": 1.7432335166611003e-05, + "loss": 0.966, + "step": 4175 + }, + { + "epoch": 0.2563614598360907, + "grad_norm": 0.6815916329089907, + "learning_rate": 1.7431004749886956e-05, + "loss": 0.9724, + "step": 4176 + }, + { + "epoch": 0.25642284907455726, + "grad_norm": 0.6390279109882322, + "learning_rate": 1.7429674039375552e-05, + "loss": 0.9778, + "step": 4177 + }, + { + "epoch": 0.25648423831302375, + "grad_norm": 0.662995210183873, + "learning_rate": 1.7428343035129395e-05, + "loss": 0.9761, + "step": 4178 + }, + { + "epoch": 0.25654562755149024, + "grad_norm": 0.6398193125405977, + "learning_rate": 1.742701173720111e-05, + "loss": 0.977, + "step": 4179 + }, + { + "epoch": 0.25660701678995673, + "grad_norm": 0.656588530252091, + "learning_rate": 1.7425680145643328e-05, + "loss": 0.9848, + "step": 4180 + }, + { + "epoch": 0.2566684060284232, + "grad_norm": 0.6769727390490597, + "learning_rate": 1.742434826050869e-05, + "loss": 0.9356, + "step": 4181 + }, + { + "epoch": 0.2567297952668897, + "grad_norm": 0.668410119827695, + "learning_rate": 1.742301608184986e-05, + "loss": 0.9603, + "step": 4182 + }, + { + "epoch": 0.2567911845053562, + "grad_norm": 0.676208009852156, + "learning_rate": 1.7421683609719506e-05, + "loss": 1.0194, + "step": 4183 + }, + { + "epoch": 0.2568525737438227, + "grad_norm": 0.7380206041934645, + "learning_rate": 1.7420350844170305e-05, + "loss": 1.0271, + "step": 4184 + }, + { + "epoch": 0.2569139629822892, + "grad_norm": 0.6043463718060456, + "learning_rate": 1.7419017785254945e-05, + "loss": 0.7768, + "step": 4185 + }, + { + "epoch": 0.2569753522207557, + "grad_norm": 0.6321975112539273, + "learning_rate": 1.7417684433026133e-05, + "loss": 0.9134, + "step": 4186 + }, + { + "epoch": 0.2570367414592222, + "grad_norm": 0.6643252884825896, + "learning_rate": 1.741635078753658e-05, + "loss": 1.0144, + "step": 4187 + }, + { + "epoch": 0.2570981306976887, + "grad_norm": 0.6330263733287377, + "learning_rate": 1.741501684883902e-05, + "loss": 0.9851, + "step": 4188 + }, + { + "epoch": 0.2571595199361552, + "grad_norm": 0.6319465997601831, + "learning_rate": 1.7413682616986185e-05, + "loss": 0.9266, + "step": 4189 + }, + { + "epoch": 0.2572209091746217, + "grad_norm": 0.6707605854465487, + "learning_rate": 1.741234809203082e-05, + "loss": 0.9691, + "step": 4190 + }, + { + "epoch": 0.2572822984130882, + "grad_norm": 0.602316491325829, + "learning_rate": 1.7411013274025698e-05, + "loss": 0.9668, + "step": 4191 + }, + { + "epoch": 0.2573436876515547, + "grad_norm": 0.6575486323530102, + "learning_rate": 1.7409678163023576e-05, + "loss": 0.9676, + "step": 4192 + }, + { + "epoch": 0.2574050768900212, + "grad_norm": 0.6384939470566469, + "learning_rate": 1.7408342759077255e-05, + "loss": 0.9619, + "step": 4193 + }, + { + "epoch": 0.25746646612848767, + "grad_norm": 0.6473502915475952, + "learning_rate": 1.7407007062239517e-05, + "loss": 0.9726, + "step": 4194 + }, + { + "epoch": 0.25752785536695416, + "grad_norm": 0.6209246464190266, + "learning_rate": 1.7405671072563177e-05, + "loss": 0.9261, + "step": 4195 + }, + { + "epoch": 0.25758924460542065, + "grad_norm": 0.6089025244727462, + "learning_rate": 1.740433479010105e-05, + "loss": 0.9316, + "step": 4196 + }, + { + "epoch": 0.25765063384388714, + "grad_norm": 0.6635236775867256, + "learning_rate": 1.7402998214905968e-05, + "loss": 0.9757, + "step": 4197 + }, + { + "epoch": 0.25771202308235364, + "grad_norm": 0.6918290907738482, + "learning_rate": 1.740166134703077e-05, + "loss": 1.0277, + "step": 4198 + }, + { + "epoch": 0.2577734123208202, + "grad_norm": 0.6694929979103365, + "learning_rate": 1.7400324186528316e-05, + "loss": 0.9744, + "step": 4199 + }, + { + "epoch": 0.2578348015592867, + "grad_norm": 0.6461866971639144, + "learning_rate": 1.7398986733451466e-05, + "loss": 0.9446, + "step": 4200 + }, + { + "epoch": 0.25789619079775317, + "grad_norm": 0.6578367493969184, + "learning_rate": 1.73976489878531e-05, + "loss": 0.9596, + "step": 4201 + }, + { + "epoch": 0.25795758003621966, + "grad_norm": 0.6464261337914712, + "learning_rate": 1.73963109497861e-05, + "loss": 0.9444, + "step": 4202 + }, + { + "epoch": 0.25801896927468615, + "grad_norm": 0.6670176419790108, + "learning_rate": 1.739497261930337e-05, + "loss": 0.9812, + "step": 4203 + }, + { + "epoch": 0.25808035851315264, + "grad_norm": 0.6846576727790231, + "learning_rate": 1.7393633996457825e-05, + "loss": 0.9547, + "step": 4204 + }, + { + "epoch": 0.25814174775161913, + "grad_norm": 0.6217961075388467, + "learning_rate": 1.739229508130238e-05, + "loss": 0.8972, + "step": 4205 + }, + { + "epoch": 0.2582031369900856, + "grad_norm": 0.636302816056945, + "learning_rate": 1.7390955873889974e-05, + "loss": 0.9573, + "step": 4206 + }, + { + "epoch": 0.2582645262285521, + "grad_norm": 0.7369294804108919, + "learning_rate": 1.7389616374273553e-05, + "loss": 0.9997, + "step": 4207 + }, + { + "epoch": 0.2583259154670186, + "grad_norm": 0.6834151872438878, + "learning_rate": 1.7388276582506078e-05, + "loss": 0.9951, + "step": 4208 + }, + { + "epoch": 0.25838730470548515, + "grad_norm": 0.7255522040217044, + "learning_rate": 1.7386936498640513e-05, + "loss": 0.951, + "step": 4209 + }, + { + "epoch": 0.25844869394395165, + "grad_norm": 0.6215078064993604, + "learning_rate": 1.7385596122729837e-05, + "loss": 0.976, + "step": 4210 + }, + { + "epoch": 0.25851008318241814, + "grad_norm": 0.6422919444438635, + "learning_rate": 1.738425545482705e-05, + "loss": 0.9508, + "step": 4211 + }, + { + "epoch": 0.25857147242088463, + "grad_norm": 0.6215484040866932, + "learning_rate": 1.7382914494985147e-05, + "loss": 0.9554, + "step": 4212 + }, + { + "epoch": 0.2586328616593511, + "grad_norm": 0.6770885338170612, + "learning_rate": 1.7381573243257145e-05, + "loss": 0.9574, + "step": 4213 + }, + { + "epoch": 0.2586942508978176, + "grad_norm": 0.6721468033042755, + "learning_rate": 1.738023169969608e-05, + "loss": 1.0079, + "step": 4214 + }, + { + "epoch": 0.2587556401362841, + "grad_norm": 0.6530194558320838, + "learning_rate": 1.7378889864354978e-05, + "loss": 1.0245, + "step": 4215 + }, + { + "epoch": 0.2588170293747506, + "grad_norm": 0.631074282189236, + "learning_rate": 1.73775477372869e-05, + "loss": 0.9188, + "step": 4216 + }, + { + "epoch": 0.2588784186132171, + "grad_norm": 0.6778257966439327, + "learning_rate": 1.73762053185449e-05, + "loss": 1.0167, + "step": 4217 + }, + { + "epoch": 0.2589398078516836, + "grad_norm": 0.6407171222659519, + "learning_rate": 1.737486260818205e-05, + "loss": 0.8286, + "step": 4218 + }, + { + "epoch": 0.25900119709015007, + "grad_norm": 0.621576377749488, + "learning_rate": 1.7373519606251443e-05, + "loss": 0.9473, + "step": 4219 + }, + { + "epoch": 0.2590625863286166, + "grad_norm": 0.656109892471139, + "learning_rate": 1.7372176312806164e-05, + "loss": 0.9709, + "step": 4220 + }, + { + "epoch": 0.2591239755670831, + "grad_norm": 0.6421024119603636, + "learning_rate": 1.737083272789933e-05, + "loss": 0.9256, + "step": 4221 + }, + { + "epoch": 0.2591853648055496, + "grad_norm": 0.6327476312909681, + "learning_rate": 1.7369488851584053e-05, + "loss": 0.9538, + "step": 4222 + }, + { + "epoch": 0.2592467540440161, + "grad_norm": 0.5931387931044668, + "learning_rate": 1.736814468391347e-05, + "loss": 0.8971, + "step": 4223 + }, + { + "epoch": 0.2593081432824826, + "grad_norm": 0.6754060294403068, + "learning_rate": 1.736680022494072e-05, + "loss": 0.7661, + "step": 4224 + }, + { + "epoch": 0.2593695325209491, + "grad_norm": 0.622347424795531, + "learning_rate": 1.7365455474718957e-05, + "loss": 0.9202, + "step": 4225 + }, + { + "epoch": 0.25943092175941557, + "grad_norm": 0.6920380273679084, + "learning_rate": 1.7364110433301343e-05, + "loss": 1.0014, + "step": 4226 + }, + { + "epoch": 0.25949231099788206, + "grad_norm": 0.6782049899948444, + "learning_rate": 1.736276510074106e-05, + "loss": 0.9742, + "step": 4227 + }, + { + "epoch": 0.25955370023634855, + "grad_norm": 0.6076704078642302, + "learning_rate": 1.736141947709129e-05, + "loss": 0.9601, + "step": 4228 + }, + { + "epoch": 0.25961508947481504, + "grad_norm": 0.6966422259573749, + "learning_rate": 1.736007356240524e-05, + "loss": 0.9529, + "step": 4229 + }, + { + "epoch": 0.2596764787132816, + "grad_norm": 0.762963041602391, + "learning_rate": 1.7358727356736116e-05, + "loss": 0.9869, + "step": 4230 + }, + { + "epoch": 0.2597378679517481, + "grad_norm": 0.6337575109611633, + "learning_rate": 1.7357380860137146e-05, + "loss": 0.9827, + "step": 4231 + }, + { + "epoch": 0.25979925719021457, + "grad_norm": 0.7334194110816822, + "learning_rate": 1.7356034072661557e-05, + "loss": 0.9854, + "step": 4232 + }, + { + "epoch": 0.25986064642868106, + "grad_norm": 0.6471596859574236, + "learning_rate": 1.73546869943626e-05, + "loss": 0.9449, + "step": 4233 + }, + { + "epoch": 0.25992203566714756, + "grad_norm": 0.5990281615725248, + "learning_rate": 1.7353339625293527e-05, + "loss": 0.9267, + "step": 4234 + }, + { + "epoch": 0.25998342490561405, + "grad_norm": 0.6281474418872841, + "learning_rate": 1.7351991965507613e-05, + "loss": 0.9723, + "step": 4235 + }, + { + "epoch": 0.26004481414408054, + "grad_norm": 0.67696177571771, + "learning_rate": 1.7350644015058135e-05, + "loss": 0.9839, + "step": 4236 + }, + { + "epoch": 0.26010620338254703, + "grad_norm": 0.6799570323709193, + "learning_rate": 1.7349295773998385e-05, + "loss": 0.992, + "step": 4237 + }, + { + "epoch": 0.2601675926210135, + "grad_norm": 0.5818089388587316, + "learning_rate": 1.7347947242381665e-05, + "loss": 0.9433, + "step": 4238 + }, + { + "epoch": 0.26022898185948, + "grad_norm": 0.69384215515116, + "learning_rate": 1.7346598420261294e-05, + "loss": 0.9871, + "step": 4239 + }, + { + "epoch": 0.2602903710979465, + "grad_norm": 0.6555368433166715, + "learning_rate": 1.734524930769059e-05, + "loss": 0.9208, + "step": 4240 + }, + { + "epoch": 0.26035176033641305, + "grad_norm": 0.6747532350057683, + "learning_rate": 1.7343899904722903e-05, + "loss": 1.027, + "step": 4241 + }, + { + "epoch": 0.26041314957487954, + "grad_norm": 0.6422019746416486, + "learning_rate": 1.7342550211411572e-05, + "loss": 0.9509, + "step": 4242 + }, + { + "epoch": 0.26047453881334603, + "grad_norm": 0.6425439924933637, + "learning_rate": 1.7341200227809958e-05, + "loss": 0.9665, + "step": 4243 + }, + { + "epoch": 0.2605359280518125, + "grad_norm": 0.6480803151733157, + "learning_rate": 1.7339849953971436e-05, + "loss": 1.0036, + "step": 4244 + }, + { + "epoch": 0.260597317290279, + "grad_norm": 0.5878909848746734, + "learning_rate": 1.733849938994939e-05, + "loss": 0.9775, + "step": 4245 + }, + { + "epoch": 0.2606587065287455, + "grad_norm": 0.6410146080723423, + "learning_rate": 1.7337148535797215e-05, + "loss": 0.937, + "step": 4246 + }, + { + "epoch": 0.260720095767212, + "grad_norm": 0.6216663735457623, + "learning_rate": 1.7335797391568318e-05, + "loss": 0.982, + "step": 4247 + }, + { + "epoch": 0.2607814850056785, + "grad_norm": 0.6541781154974181, + "learning_rate": 1.733444595731611e-05, + "loss": 0.9458, + "step": 4248 + }, + { + "epoch": 0.260842874244145, + "grad_norm": 0.6165707261282056, + "learning_rate": 1.733309423309403e-05, + "loss": 0.9186, + "step": 4249 + }, + { + "epoch": 0.2609042634826115, + "grad_norm": 0.6779705111812921, + "learning_rate": 1.7331742218955513e-05, + "loss": 0.9735, + "step": 4250 + }, + { + "epoch": 0.26096565272107797, + "grad_norm": 0.7142741042061367, + "learning_rate": 1.7330389914954015e-05, + "loss": 1.0013, + "step": 4251 + }, + { + "epoch": 0.2610270419595445, + "grad_norm": 0.6751665450898274, + "learning_rate": 1.7329037321142995e-05, + "loss": 0.9792, + "step": 4252 + }, + { + "epoch": 0.261088431198011, + "grad_norm": 0.6547646602745651, + "learning_rate": 1.7327684437575933e-05, + "loss": 0.9484, + "step": 4253 + }, + { + "epoch": 0.2611498204364775, + "grad_norm": 0.6155959717719883, + "learning_rate": 1.7326331264306316e-05, + "loss": 0.951, + "step": 4254 + }, + { + "epoch": 0.261211209674944, + "grad_norm": 0.7065446881016867, + "learning_rate": 1.7324977801387637e-05, + "loss": 1.038, + "step": 4255 + }, + { + "epoch": 0.2612725989134105, + "grad_norm": 0.6631786661872281, + "learning_rate": 1.732362404887341e-05, + "loss": 0.9773, + "step": 4256 + }, + { + "epoch": 0.261333988151877, + "grad_norm": 0.6459275315067019, + "learning_rate": 1.7322270006817158e-05, + "loss": 0.9558, + "step": 4257 + }, + { + "epoch": 0.26139537739034346, + "grad_norm": 0.6964994086701408, + "learning_rate": 1.7320915675272406e-05, + "loss": 0.9958, + "step": 4258 + }, + { + "epoch": 0.26145676662880996, + "grad_norm": 0.6675034155026017, + "learning_rate": 1.73195610542927e-05, + "loss": 0.9808, + "step": 4259 + }, + { + "epoch": 0.26151815586727645, + "grad_norm": 0.7369942560110105, + "learning_rate": 1.7318206143931605e-05, + "loss": 1.0221, + "step": 4260 + }, + { + "epoch": 0.26157954510574294, + "grad_norm": 0.6599176471756022, + "learning_rate": 1.7316850944242677e-05, + "loss": 0.941, + "step": 4261 + }, + { + "epoch": 0.2616409343442095, + "grad_norm": 0.6438417046548394, + "learning_rate": 1.7315495455279498e-05, + "loss": 0.9636, + "step": 4262 + }, + { + "epoch": 0.261702323582676, + "grad_norm": 0.5867897752066397, + "learning_rate": 1.7314139677095655e-05, + "loss": 0.9337, + "step": 4263 + }, + { + "epoch": 0.26176371282114247, + "grad_norm": 0.6295231884138991, + "learning_rate": 1.7312783609744753e-05, + "loss": 0.9231, + "step": 4264 + }, + { + "epoch": 0.26182510205960896, + "grad_norm": 0.6984643117518795, + "learning_rate": 1.7311427253280407e-05, + "loss": 1.016, + "step": 4265 + }, + { + "epoch": 0.26188649129807545, + "grad_norm": 0.6234724470453903, + "learning_rate": 1.7310070607756236e-05, + "loss": 0.8972, + "step": 4266 + }, + { + "epoch": 0.26194788053654194, + "grad_norm": 0.6549253429804569, + "learning_rate": 1.7308713673225877e-05, + "loss": 0.9532, + "step": 4267 + }, + { + "epoch": 0.26200926977500844, + "grad_norm": 0.6491898770082011, + "learning_rate": 1.7307356449742975e-05, + "loss": 0.9986, + "step": 4268 + }, + { + "epoch": 0.2620706590134749, + "grad_norm": 0.6927321728418083, + "learning_rate": 1.730599893736119e-05, + "loss": 0.9791, + "step": 4269 + }, + { + "epoch": 0.2621320482519414, + "grad_norm": 0.5867770429621578, + "learning_rate": 1.7304641136134192e-05, + "loss": 0.9492, + "step": 4270 + }, + { + "epoch": 0.2621934374904079, + "grad_norm": 0.6925660038108911, + "learning_rate": 1.7303283046115663e-05, + "loss": 0.9762, + "step": 4271 + }, + { + "epoch": 0.2622548267288744, + "grad_norm": 0.637761863275505, + "learning_rate": 1.7301924667359292e-05, + "loss": 0.9241, + "step": 4272 + }, + { + "epoch": 0.26231621596734095, + "grad_norm": 0.7053502846222424, + "learning_rate": 1.730056599991879e-05, + "loss": 0.9784, + "step": 4273 + }, + { + "epoch": 0.26237760520580744, + "grad_norm": 0.6644916764332782, + "learning_rate": 1.7299207043847864e-05, + "loss": 0.9975, + "step": 4274 + }, + { + "epoch": 0.26243899444427393, + "grad_norm": 0.7043014137827021, + "learning_rate": 1.7297847799200245e-05, + "loss": 1.0033, + "step": 4275 + }, + { + "epoch": 0.2625003836827404, + "grad_norm": 0.6830783213695387, + "learning_rate": 1.7296488266029674e-05, + "loss": 1.0294, + "step": 4276 + }, + { + "epoch": 0.2625617729212069, + "grad_norm": 0.6373866306623979, + "learning_rate": 1.7295128444389896e-05, + "loss": 0.9413, + "step": 4277 + }, + { + "epoch": 0.2626231621596734, + "grad_norm": 0.7171047577070323, + "learning_rate": 1.729376833433467e-05, + "loss": 1.0481, + "step": 4278 + }, + { + "epoch": 0.2626845513981399, + "grad_norm": 0.5911684810561845, + "learning_rate": 1.7292407935917776e-05, + "loss": 0.9303, + "step": 4279 + }, + { + "epoch": 0.2627459406366064, + "grad_norm": 0.6276678139324962, + "learning_rate": 1.7291047249192993e-05, + "loss": 0.9191, + "step": 4280 + }, + { + "epoch": 0.2628073298750729, + "grad_norm": 0.6754000625517528, + "learning_rate": 1.7289686274214116e-05, + "loss": 0.9992, + "step": 4281 + }, + { + "epoch": 0.2628687191135394, + "grad_norm": 0.6098611141022308, + "learning_rate": 1.7288325011034956e-05, + "loss": 0.9887, + "step": 4282 + }, + { + "epoch": 0.2629301083520059, + "grad_norm": 0.6683940363726829, + "learning_rate": 1.7286963459709322e-05, + "loss": 0.9544, + "step": 4283 + }, + { + "epoch": 0.2629914975904724, + "grad_norm": 0.6405893395673129, + "learning_rate": 1.7285601620291052e-05, + "loss": 0.9739, + "step": 4284 + }, + { + "epoch": 0.2630528868289389, + "grad_norm": 0.7033016288766897, + "learning_rate": 1.7284239492833984e-05, + "loss": 1.0048, + "step": 4285 + }, + { + "epoch": 0.2631142760674054, + "grad_norm": 0.6820100727139042, + "learning_rate": 1.728287707739197e-05, + "loss": 0.9791, + "step": 4286 + }, + { + "epoch": 0.2631756653058719, + "grad_norm": 0.626138585450269, + "learning_rate": 1.7281514374018872e-05, + "loss": 0.9318, + "step": 4287 + }, + { + "epoch": 0.2632370545443384, + "grad_norm": 0.6916996209396742, + "learning_rate": 1.7280151382768568e-05, + "loss": 0.9993, + "step": 4288 + }, + { + "epoch": 0.26329844378280487, + "grad_norm": 0.6846666557316672, + "learning_rate": 1.7278788103694944e-05, + "loss": 0.9847, + "step": 4289 + }, + { + "epoch": 0.26335983302127136, + "grad_norm": 0.6710552071871122, + "learning_rate": 1.727742453685189e-05, + "loss": 0.9641, + "step": 4290 + }, + { + "epoch": 0.26342122225973785, + "grad_norm": 0.6654065621447277, + "learning_rate": 1.7276060682293333e-05, + "loss": 0.915, + "step": 4291 + }, + { + "epoch": 0.26348261149820434, + "grad_norm": 0.6761330636587178, + "learning_rate": 1.7274696540073172e-05, + "loss": 0.9959, + "step": 4292 + }, + { + "epoch": 0.26354400073667084, + "grad_norm": 0.6706010229861188, + "learning_rate": 1.7273332110245353e-05, + "loss": 0.9705, + "step": 4293 + }, + { + "epoch": 0.2636053899751374, + "grad_norm": 0.6453193882161512, + "learning_rate": 1.7271967392863815e-05, + "loss": 0.9556, + "step": 4294 + }, + { + "epoch": 0.2636667792136039, + "grad_norm": 0.7007309431346781, + "learning_rate": 1.7270602387982512e-05, + "loss": 0.9887, + "step": 4295 + }, + { + "epoch": 0.26372816845207037, + "grad_norm": 0.6571662485835045, + "learning_rate": 1.7269237095655412e-05, + "loss": 0.9777, + "step": 4296 + }, + { + "epoch": 0.26378955769053686, + "grad_norm": 0.6863289882050382, + "learning_rate": 1.726787151593649e-05, + "loss": 0.9717, + "step": 4297 + }, + { + "epoch": 0.26385094692900335, + "grad_norm": 0.6268301388609762, + "learning_rate": 1.7266505648879735e-05, + "loss": 0.9343, + "step": 4298 + }, + { + "epoch": 0.26391233616746984, + "grad_norm": 0.7066841200442734, + "learning_rate": 1.726513949453915e-05, + "loss": 0.9582, + "step": 4299 + }, + { + "epoch": 0.26397372540593633, + "grad_norm": 0.6656521845166531, + "learning_rate": 1.7263773052968743e-05, + "loss": 0.9955, + "step": 4300 + }, + { + "epoch": 0.2640351146444028, + "grad_norm": 0.696063037150272, + "learning_rate": 1.7262406324222537e-05, + "loss": 0.964, + "step": 4301 + }, + { + "epoch": 0.2640965038828693, + "grad_norm": 0.716973022696932, + "learning_rate": 1.726103930835457e-05, + "loss": 0.9995, + "step": 4302 + }, + { + "epoch": 0.2641578931213358, + "grad_norm": 0.6276792314698942, + "learning_rate": 1.725967200541888e-05, + "loss": 0.898, + "step": 4303 + }, + { + "epoch": 0.26421928235980235, + "grad_norm": 0.591316617713463, + "learning_rate": 1.725830441546953e-05, + "loss": 0.9378, + "step": 4304 + }, + { + "epoch": 0.26428067159826885, + "grad_norm": 0.6962485314066291, + "learning_rate": 1.7256936538560586e-05, + "loss": 0.9667, + "step": 4305 + }, + { + "epoch": 0.26434206083673534, + "grad_norm": 0.7438807727909329, + "learning_rate": 1.725556837474613e-05, + "loss": 1.0347, + "step": 4306 + }, + { + "epoch": 0.26440345007520183, + "grad_norm": 0.6892301518860905, + "learning_rate": 1.725419992408025e-05, + "loss": 1.0012, + "step": 4307 + }, + { + "epoch": 0.2644648393136683, + "grad_norm": 0.7055757535278876, + "learning_rate": 1.725283118661705e-05, + "loss": 1.007, + "step": 4308 + }, + { + "epoch": 0.2645262285521348, + "grad_norm": 0.6774185065377791, + "learning_rate": 1.7251462162410634e-05, + "loss": 0.9292, + "step": 4309 + }, + { + "epoch": 0.2645876177906013, + "grad_norm": 0.7050785265078426, + "learning_rate": 1.7250092851515145e-05, + "loss": 0.9911, + "step": 4310 + }, + { + "epoch": 0.2646490070290678, + "grad_norm": 0.689328742221097, + "learning_rate": 1.7248723253984706e-05, + "loss": 0.9873, + "step": 4311 + }, + { + "epoch": 0.2647103962675343, + "grad_norm": 0.7308875927148824, + "learning_rate": 1.7247353369873465e-05, + "loss": 1.0334, + "step": 4312 + }, + { + "epoch": 0.2647717855060008, + "grad_norm": 0.6804158011022573, + "learning_rate": 1.7245983199235587e-05, + "loss": 0.9678, + "step": 4313 + }, + { + "epoch": 0.26483317474446727, + "grad_norm": 0.7086149176389626, + "learning_rate": 1.7244612742125237e-05, + "loss": 1.0013, + "step": 4314 + }, + { + "epoch": 0.2648945639829338, + "grad_norm": 0.6038084601008153, + "learning_rate": 1.7243241998596598e-05, + "loss": 0.9026, + "step": 4315 + }, + { + "epoch": 0.2649559532214003, + "grad_norm": 0.6740937846959428, + "learning_rate": 1.7241870968703866e-05, + "loss": 1.0201, + "step": 4316 + }, + { + "epoch": 0.2650173424598668, + "grad_norm": 0.6904181651223358, + "learning_rate": 1.7240499652501242e-05, + "loss": 0.7943, + "step": 4317 + }, + { + "epoch": 0.2650787316983333, + "grad_norm": 0.688200315863667, + "learning_rate": 1.723912805004294e-05, + "loss": 0.9984, + "step": 4318 + }, + { + "epoch": 0.2651401209367998, + "grad_norm": 0.6540042252524801, + "learning_rate": 1.723775616138319e-05, + "loss": 1.0137, + "step": 4319 + }, + { + "epoch": 0.2652015101752663, + "grad_norm": 0.6578269165312379, + "learning_rate": 1.7236383986576228e-05, + "loss": 0.9421, + "step": 4320 + }, + { + "epoch": 0.26526289941373277, + "grad_norm": 0.6790879642022961, + "learning_rate": 1.7235011525676304e-05, + "loss": 0.9436, + "step": 4321 + }, + { + "epoch": 0.26532428865219926, + "grad_norm": 0.6925408618493468, + "learning_rate": 1.723363877873768e-05, + "loss": 0.9669, + "step": 4322 + }, + { + "epoch": 0.26538567789066575, + "grad_norm": 0.687590269992648, + "learning_rate": 1.7232265745814626e-05, + "loss": 0.9832, + "step": 4323 + }, + { + "epoch": 0.26544706712913224, + "grad_norm": 0.6676636208771609, + "learning_rate": 1.7230892426961424e-05, + "loss": 0.9209, + "step": 4324 + }, + { + "epoch": 0.26550845636759873, + "grad_norm": 0.6566463813511884, + "learning_rate": 1.7229518822232372e-05, + "loss": 0.9562, + "step": 4325 + }, + { + "epoch": 0.2655698456060653, + "grad_norm": 0.6175697994203041, + "learning_rate": 1.7228144931681777e-05, + "loss": 0.9148, + "step": 4326 + }, + { + "epoch": 0.26563123484453177, + "grad_norm": 0.6165892714691359, + "learning_rate": 1.7226770755363952e-05, + "loss": 0.979, + "step": 4327 + }, + { + "epoch": 0.26569262408299826, + "grad_norm": 0.6422973681008284, + "learning_rate": 1.722539629333323e-05, + "loss": 0.9413, + "step": 4328 + }, + { + "epoch": 0.26575401332146475, + "grad_norm": 0.6777512231774603, + "learning_rate": 1.7224021545643944e-05, + "loss": 0.9618, + "step": 4329 + }, + { + "epoch": 0.26581540255993125, + "grad_norm": 0.6115719984523994, + "learning_rate": 1.7222646512350452e-05, + "loss": 0.8907, + "step": 4330 + }, + { + "epoch": 0.26587679179839774, + "grad_norm": 0.6398836582373342, + "learning_rate": 1.7221271193507118e-05, + "loss": 0.9829, + "step": 4331 + }, + { + "epoch": 0.26593818103686423, + "grad_norm": 0.6362919144328332, + "learning_rate": 1.7219895589168306e-05, + "loss": 0.9655, + "step": 4332 + }, + { + "epoch": 0.2659995702753307, + "grad_norm": 0.684161529418325, + "learning_rate": 1.721851969938841e-05, + "loss": 0.9771, + "step": 4333 + }, + { + "epoch": 0.2660609595137972, + "grad_norm": 0.7126696097693958, + "learning_rate": 1.721714352422182e-05, + "loss": 0.9859, + "step": 4334 + }, + { + "epoch": 0.2661223487522637, + "grad_norm": 0.7836367909902061, + "learning_rate": 1.7215767063722948e-05, + "loss": 0.7256, + "step": 4335 + }, + { + "epoch": 0.26618373799073025, + "grad_norm": 0.7079723637680146, + "learning_rate": 1.721439031794621e-05, + "loss": 0.9535, + "step": 4336 + }, + { + "epoch": 0.26624512722919674, + "grad_norm": 0.6912936853072524, + "learning_rate": 1.721301328694604e-05, + "loss": 0.9478, + "step": 4337 + }, + { + "epoch": 0.26630651646766323, + "grad_norm": 0.6306475030514916, + "learning_rate": 1.7211635970776877e-05, + "loss": 0.7483, + "step": 4338 + }, + { + "epoch": 0.2663679057061297, + "grad_norm": 0.6374179707895314, + "learning_rate": 1.721025836949317e-05, + "loss": 0.9721, + "step": 4339 + }, + { + "epoch": 0.2664292949445962, + "grad_norm": 0.6864241149550515, + "learning_rate": 1.7208880483149388e-05, + "loss": 0.9489, + "step": 4340 + }, + { + "epoch": 0.2664906841830627, + "grad_norm": 0.6245309539862441, + "learning_rate": 1.7207502311800004e-05, + "loss": 0.9586, + "step": 4341 + }, + { + "epoch": 0.2665520734215292, + "grad_norm": 0.7059573923496241, + "learning_rate": 1.7206123855499506e-05, + "loss": 1.0148, + "step": 4342 + }, + { + "epoch": 0.2666134626599957, + "grad_norm": 0.7175482694583752, + "learning_rate": 1.7204745114302395e-05, + "loss": 0.9794, + "step": 4343 + }, + { + "epoch": 0.2666748518984622, + "grad_norm": 0.6750303943366939, + "learning_rate": 1.720336608826317e-05, + "loss": 0.9435, + "step": 4344 + }, + { + "epoch": 0.2667362411369287, + "grad_norm": 0.691351395374602, + "learning_rate": 1.720198677743636e-05, + "loss": 0.9876, + "step": 4345 + }, + { + "epoch": 0.26679763037539517, + "grad_norm": 0.6704212750339976, + "learning_rate": 1.7200607181876492e-05, + "loss": 0.9222, + "step": 4346 + }, + { + "epoch": 0.2668590196138617, + "grad_norm": 0.6694781458325737, + "learning_rate": 1.7199227301638113e-05, + "loss": 0.9764, + "step": 4347 + }, + { + "epoch": 0.2669204088523282, + "grad_norm": 0.6321602003459564, + "learning_rate": 1.7197847136775775e-05, + "loss": 0.9242, + "step": 4348 + }, + { + "epoch": 0.2669817980907947, + "grad_norm": 0.6661673189006966, + "learning_rate": 1.719646668734404e-05, + "loss": 0.9235, + "step": 4349 + }, + { + "epoch": 0.2670431873292612, + "grad_norm": 0.6455471729061483, + "learning_rate": 1.7195085953397486e-05, + "loss": 0.9611, + "step": 4350 + }, + { + "epoch": 0.2671045765677277, + "grad_norm": 0.5849740117145663, + "learning_rate": 1.7193704934990707e-05, + "loss": 0.9085, + "step": 4351 + }, + { + "epoch": 0.26716596580619417, + "grad_norm": 0.6591137084665474, + "learning_rate": 1.7192323632178294e-05, + "loss": 0.9337, + "step": 4352 + }, + { + "epoch": 0.26722735504466066, + "grad_norm": 0.6444058134229363, + "learning_rate": 1.719094204501486e-05, + "loss": 0.9461, + "step": 4353 + }, + { + "epoch": 0.26728874428312716, + "grad_norm": 0.6151181263238588, + "learning_rate": 1.7189560173555034e-05, + "loss": 0.9154, + "step": 4354 + }, + { + "epoch": 0.26735013352159365, + "grad_norm": 0.6996850841060177, + "learning_rate": 1.7188178017853438e-05, + "loss": 0.9604, + "step": 4355 + }, + { + "epoch": 0.26741152276006014, + "grad_norm": 0.595316055207236, + "learning_rate": 1.7186795577964718e-05, + "loss": 0.9301, + "step": 4356 + }, + { + "epoch": 0.2674729119985267, + "grad_norm": 0.6971137830010755, + "learning_rate": 1.718541285394353e-05, + "loss": 0.8227, + "step": 4357 + }, + { + "epoch": 0.2675343012369932, + "grad_norm": 0.6786290153966079, + "learning_rate": 1.7184029845844543e-05, + "loss": 1.0202, + "step": 4358 + }, + { + "epoch": 0.26759569047545967, + "grad_norm": 0.599522119285186, + "learning_rate": 1.7182646553722432e-05, + "loss": 0.9158, + "step": 4359 + }, + { + "epoch": 0.26765707971392616, + "grad_norm": 0.7214880665894954, + "learning_rate": 1.718126297763189e-05, + "loss": 0.9535, + "step": 4360 + }, + { + "epoch": 0.26771846895239265, + "grad_norm": 0.619505861296002, + "learning_rate": 1.7179879117627615e-05, + "loss": 0.9296, + "step": 4361 + }, + { + "epoch": 0.26777985819085914, + "grad_norm": 0.6399284880077001, + "learning_rate": 1.7178494973764314e-05, + "loss": 0.928, + "step": 4362 + }, + { + "epoch": 0.26784124742932564, + "grad_norm": 0.6396779398277717, + "learning_rate": 1.7177110546096716e-05, + "loss": 0.9367, + "step": 4363 + }, + { + "epoch": 0.2679026366677921, + "grad_norm": 0.6416443765248651, + "learning_rate": 1.7175725834679552e-05, + "loss": 1.022, + "step": 4364 + }, + { + "epoch": 0.2679640259062586, + "grad_norm": 0.6081323151498927, + "learning_rate": 1.7174340839567567e-05, + "loss": 0.9405, + "step": 4365 + }, + { + "epoch": 0.2680254151447251, + "grad_norm": 0.6594753642691894, + "learning_rate": 1.7172955560815517e-05, + "loss": 0.9751, + "step": 4366 + }, + { + "epoch": 0.2680868043831916, + "grad_norm": 0.6692909988570706, + "learning_rate": 1.717156999847817e-05, + "loss": 0.9818, + "step": 4367 + }, + { + "epoch": 0.26814819362165815, + "grad_norm": 0.621932734997202, + "learning_rate": 1.7170184152610306e-05, + "loss": 0.9034, + "step": 4368 + }, + { + "epoch": 0.26820958286012464, + "grad_norm": 0.6372447922910564, + "learning_rate": 1.7168798023266713e-05, + "loss": 0.9737, + "step": 4369 + }, + { + "epoch": 0.26827097209859113, + "grad_norm": 0.6184522489201164, + "learning_rate": 1.7167411610502193e-05, + "loss": 0.9608, + "step": 4370 + }, + { + "epoch": 0.2683323613370576, + "grad_norm": 0.645910610391719, + "learning_rate": 1.716602491437156e-05, + "loss": 0.9152, + "step": 4371 + }, + { + "epoch": 0.2683937505755241, + "grad_norm": 0.6453482411569753, + "learning_rate": 1.716463793492963e-05, + "loss": 0.8828, + "step": 4372 + }, + { + "epoch": 0.2684551398139906, + "grad_norm": 0.6440627774702062, + "learning_rate": 1.7163250672231245e-05, + "loss": 0.9729, + "step": 4373 + }, + { + "epoch": 0.2685165290524571, + "grad_norm": 0.5902176959274533, + "learning_rate": 1.7161863126331252e-05, + "loss": 0.9165, + "step": 4374 + }, + { + "epoch": 0.2685779182909236, + "grad_norm": 0.6687804907388208, + "learning_rate": 1.7160475297284503e-05, + "loss": 0.9601, + "step": 4375 + }, + { + "epoch": 0.2686393075293901, + "grad_norm": 0.6642594362845902, + "learning_rate": 1.715908718514587e-05, + "loss": 0.9466, + "step": 4376 + }, + { + "epoch": 0.2687006967678566, + "grad_norm": 0.6763019976665089, + "learning_rate": 1.7157698789970233e-05, + "loss": 0.9536, + "step": 4377 + }, + { + "epoch": 0.26876208600632306, + "grad_norm": 0.6680085463026061, + "learning_rate": 1.7156310111812477e-05, + "loss": 0.9836, + "step": 4378 + }, + { + "epoch": 0.2688234752447896, + "grad_norm": 0.6248159420879685, + "learning_rate": 1.715492115072751e-05, + "loss": 0.8842, + "step": 4379 + }, + { + "epoch": 0.2688848644832561, + "grad_norm": 0.6297134334311126, + "learning_rate": 1.715353190677024e-05, + "loss": 0.9667, + "step": 4380 + }, + { + "epoch": 0.2689462537217226, + "grad_norm": 0.6357733288574523, + "learning_rate": 1.715214237999559e-05, + "loss": 0.944, + "step": 4381 + }, + { + "epoch": 0.2690076429601891, + "grad_norm": 0.6518505567639035, + "learning_rate": 1.715075257045851e-05, + "loss": 0.9444, + "step": 4382 + }, + { + "epoch": 0.2690690321986556, + "grad_norm": 0.7282583183494407, + "learning_rate": 1.7149362478213933e-05, + "loss": 1.0245, + "step": 4383 + }, + { + "epoch": 0.26913042143712207, + "grad_norm": 0.6837401275296855, + "learning_rate": 1.7147972103316816e-05, + "loss": 0.9912, + "step": 4384 + }, + { + "epoch": 0.26919181067558856, + "grad_norm": 0.6226332067835475, + "learning_rate": 1.714658144582213e-05, + "loss": 0.9133, + "step": 4385 + }, + { + "epoch": 0.26925319991405505, + "grad_norm": 0.6156007652440239, + "learning_rate": 1.7145190505784863e-05, + "loss": 0.9391, + "step": 4386 + }, + { + "epoch": 0.26931458915252154, + "grad_norm": 0.6479083528893598, + "learning_rate": 1.714379928326e-05, + "loss": 0.9306, + "step": 4387 + }, + { + "epoch": 0.26937597839098804, + "grad_norm": 0.6679207246635062, + "learning_rate": 1.714240777830254e-05, + "loss": 0.9617, + "step": 4388 + }, + { + "epoch": 0.2694373676294546, + "grad_norm": 0.6435911728076094, + "learning_rate": 1.71410159909675e-05, + "loss": 0.9194, + "step": 4389 + }, + { + "epoch": 0.2694987568679211, + "grad_norm": 0.6629326616874318, + "learning_rate": 1.7139623921309904e-05, + "loss": 0.9409, + "step": 4390 + }, + { + "epoch": 0.26956014610638757, + "grad_norm": 0.6286189944406786, + "learning_rate": 1.7138231569384793e-05, + "loss": 0.9339, + "step": 4391 + }, + { + "epoch": 0.26962153534485406, + "grad_norm": 0.607838176380513, + "learning_rate": 1.7136838935247206e-05, + "loss": 0.9327, + "step": 4392 + }, + { + "epoch": 0.26968292458332055, + "grad_norm": 0.6048443726771551, + "learning_rate": 1.713544601895221e-05, + "loss": 0.9621, + "step": 4393 + }, + { + "epoch": 0.26974431382178704, + "grad_norm": 0.6499555410872031, + "learning_rate": 1.7134052820554868e-05, + "loss": 0.9247, + "step": 4394 + }, + { + "epoch": 0.26980570306025353, + "grad_norm": 0.6813417048156323, + "learning_rate": 1.713265934011026e-05, + "loss": 0.9765, + "step": 4395 + }, + { + "epoch": 0.26986709229872, + "grad_norm": 0.7576672047161576, + "learning_rate": 1.7131265577673482e-05, + "loss": 0.9855, + "step": 4396 + }, + { + "epoch": 0.2699284815371865, + "grad_norm": 0.6085475724846574, + "learning_rate": 1.7129871533299635e-05, + "loss": 0.8782, + "step": 4397 + }, + { + "epoch": 0.269989870775653, + "grad_norm": 0.6786754110104776, + "learning_rate": 1.7128477207043835e-05, + "loss": 0.9153, + "step": 4398 + }, + { + "epoch": 0.2700512600141195, + "grad_norm": 0.7278135332305797, + "learning_rate": 1.7127082598961203e-05, + "loss": 1.0266, + "step": 4399 + }, + { + "epoch": 0.27011264925258605, + "grad_norm": 0.6725598670642765, + "learning_rate": 1.7125687709106878e-05, + "loss": 0.8027, + "step": 4400 + }, + { + "epoch": 0.27017403849105254, + "grad_norm": 0.645430278354678, + "learning_rate": 1.712429253753601e-05, + "loss": 0.9794, + "step": 4401 + }, + { + "epoch": 0.27023542772951903, + "grad_norm": 0.6902265804149427, + "learning_rate": 1.712289708430375e-05, + "loss": 0.9813, + "step": 4402 + }, + { + "epoch": 0.2702968169679855, + "grad_norm": 0.6149453691320239, + "learning_rate": 1.7121501349465274e-05, + "loss": 0.9537, + "step": 4403 + }, + { + "epoch": 0.270358206206452, + "grad_norm": 0.6711181176304358, + "learning_rate": 1.712010533307576e-05, + "loss": 0.9766, + "step": 4404 + }, + { + "epoch": 0.2704195954449185, + "grad_norm": 0.6503682806287121, + "learning_rate": 1.71187090351904e-05, + "loss": 0.9747, + "step": 4405 + }, + { + "epoch": 0.270480984683385, + "grad_norm": 0.6479658830834861, + "learning_rate": 1.71173124558644e-05, + "loss": 0.9419, + "step": 4406 + }, + { + "epoch": 0.2705423739218515, + "grad_norm": 0.6184243093145234, + "learning_rate": 1.7115915595152977e-05, + "loss": 0.9327, + "step": 4407 + }, + { + "epoch": 0.270603763160318, + "grad_norm": 0.656143527891453, + "learning_rate": 1.7114518453111347e-05, + "loss": 0.975, + "step": 4408 + }, + { + "epoch": 0.27066515239878447, + "grad_norm": 0.6087962667202653, + "learning_rate": 1.711312102979475e-05, + "loss": 0.8999, + "step": 4409 + }, + { + "epoch": 0.270726541637251, + "grad_norm": 0.6349427674053666, + "learning_rate": 1.711172332525844e-05, + "loss": 0.9188, + "step": 4410 + }, + { + "epoch": 0.2707879308757175, + "grad_norm": 0.6500042517191001, + "learning_rate": 1.7110325339557666e-05, + "loss": 0.9669, + "step": 4411 + }, + { + "epoch": 0.270849320114184, + "grad_norm": 0.6512615693583554, + "learning_rate": 1.7108927072747708e-05, + "loss": 0.9723, + "step": 4412 + }, + { + "epoch": 0.2709107093526505, + "grad_norm": 0.7209610863551567, + "learning_rate": 1.710752852488384e-05, + "loss": 0.9389, + "step": 4413 + }, + { + "epoch": 0.270972098591117, + "grad_norm": 0.7373614171623002, + "learning_rate": 1.7106129696021353e-05, + "loss": 1.002, + "step": 4414 + }, + { + "epoch": 0.2710334878295835, + "grad_norm": 0.7298178220047494, + "learning_rate": 1.7104730586215553e-05, + "loss": 1.0013, + "step": 4415 + }, + { + "epoch": 0.27109487706804997, + "grad_norm": 0.628301216737785, + "learning_rate": 1.7103331195521754e-05, + "loss": 1.01, + "step": 4416 + }, + { + "epoch": 0.27115626630651646, + "grad_norm": 0.6551233388345951, + "learning_rate": 1.7101931523995284e-05, + "loss": 0.9747, + "step": 4417 + }, + { + "epoch": 0.27121765554498295, + "grad_norm": 0.7126266616272631, + "learning_rate": 1.7100531571691476e-05, + "loss": 0.9824, + "step": 4418 + }, + { + "epoch": 0.27127904478344944, + "grad_norm": 0.6476577114390848, + "learning_rate": 1.709913133866568e-05, + "loss": 0.9442, + "step": 4419 + }, + { + "epoch": 0.27134043402191593, + "grad_norm": 0.7043268276297645, + "learning_rate": 1.7097730824973247e-05, + "loss": 0.9346, + "step": 4420 + }, + { + "epoch": 0.2714018232603825, + "grad_norm": 0.6650716061053495, + "learning_rate": 1.709633003066956e-05, + "loss": 0.9475, + "step": 4421 + }, + { + "epoch": 0.27146321249884897, + "grad_norm": 0.6602382694450318, + "learning_rate": 1.7094928955809994e-05, + "loss": 0.9737, + "step": 4422 + }, + { + "epoch": 0.27152460173731546, + "grad_norm": 0.6327149851369893, + "learning_rate": 1.7093527600449936e-05, + "loss": 0.9316, + "step": 4423 + }, + { + "epoch": 0.27158599097578195, + "grad_norm": 0.6645337638734312, + "learning_rate": 1.7092125964644794e-05, + "loss": 0.9571, + "step": 4424 + }, + { + "epoch": 0.27164738021424845, + "grad_norm": 0.7053858847859588, + "learning_rate": 1.709072404844998e-05, + "loss": 1.0178, + "step": 4425 + }, + { + "epoch": 0.27170876945271494, + "grad_norm": 0.6762084951214351, + "learning_rate": 1.7089321851920924e-05, + "loss": 0.9679, + "step": 4426 + }, + { + "epoch": 0.27177015869118143, + "grad_norm": 0.6733894151182306, + "learning_rate": 1.7087919375113055e-05, + "loss": 0.9329, + "step": 4427 + }, + { + "epoch": 0.2718315479296479, + "grad_norm": 0.6267880824976584, + "learning_rate": 1.708651661808183e-05, + "loss": 0.925, + "step": 4428 + }, + { + "epoch": 0.2718929371681144, + "grad_norm": 0.6529592488262449, + "learning_rate": 1.7085113580882695e-05, + "loss": 0.9665, + "step": 4429 + }, + { + "epoch": 0.2719543264065809, + "grad_norm": 0.7008521088675216, + "learning_rate": 1.7083710263571128e-05, + "loss": 0.9621, + "step": 4430 + }, + { + "epoch": 0.2720157156450474, + "grad_norm": 0.6419604309011087, + "learning_rate": 1.708230666620261e-05, + "loss": 0.9324, + "step": 4431 + }, + { + "epoch": 0.27207710488351394, + "grad_norm": 0.6250183838162459, + "learning_rate": 1.708090278883263e-05, + "loss": 0.9552, + "step": 4432 + }, + { + "epoch": 0.27213849412198043, + "grad_norm": 0.6685090155974586, + "learning_rate": 1.7079498631516692e-05, + "loss": 0.9404, + "step": 4433 + }, + { + "epoch": 0.2721998833604469, + "grad_norm": 0.599580660720696, + "learning_rate": 1.7078094194310305e-05, + "loss": 0.9418, + "step": 4434 + }, + { + "epoch": 0.2722612725989134, + "grad_norm": 0.6997313966604481, + "learning_rate": 1.7076689477269e-05, + "loss": 0.9629, + "step": 4435 + }, + { + "epoch": 0.2723226618373799, + "grad_norm": 0.6518911197414524, + "learning_rate": 1.7075284480448314e-05, + "loss": 0.9692, + "step": 4436 + }, + { + "epoch": 0.2723840510758464, + "grad_norm": 0.6119042310809021, + "learning_rate": 1.707387920390379e-05, + "loss": 0.9585, + "step": 4437 + }, + { + "epoch": 0.2724454403143129, + "grad_norm": 0.6344164207073727, + "learning_rate": 1.707247364769099e-05, + "loss": 1.0266, + "step": 4438 + }, + { + "epoch": 0.2725068295527794, + "grad_norm": 0.6621029710836858, + "learning_rate": 1.7071067811865477e-05, + "loss": 0.9332, + "step": 4439 + }, + { + "epoch": 0.2725682187912459, + "grad_norm": 0.6131421255571555, + "learning_rate": 1.7069661696482836e-05, + "loss": 0.8915, + "step": 4440 + }, + { + "epoch": 0.27262960802971237, + "grad_norm": 0.6900299229255011, + "learning_rate": 1.706825530159866e-05, + "loss": 0.961, + "step": 4441 + }, + { + "epoch": 0.2726909972681789, + "grad_norm": 0.6174537483808765, + "learning_rate": 1.706684862726854e-05, + "loss": 0.9225, + "step": 4442 + }, + { + "epoch": 0.2727523865066454, + "grad_norm": 0.65980059513469, + "learning_rate": 1.70654416735481e-05, + "loss": 0.9708, + "step": 4443 + }, + { + "epoch": 0.2728137757451119, + "grad_norm": 0.6297996162940226, + "learning_rate": 1.7064034440492966e-05, + "loss": 0.9437, + "step": 4444 + }, + { + "epoch": 0.2728751649835784, + "grad_norm": 0.590599868588795, + "learning_rate": 1.7062626928158767e-05, + "loss": 0.9198, + "step": 4445 + }, + { + "epoch": 0.2729365542220449, + "grad_norm": 0.6805007775636454, + "learning_rate": 1.7061219136601153e-05, + "loss": 0.9367, + "step": 4446 + }, + { + "epoch": 0.27299794346051137, + "grad_norm": 0.6799123453383856, + "learning_rate": 1.705981106587578e-05, + "loss": 1.0154, + "step": 4447 + }, + { + "epoch": 0.27305933269897786, + "grad_norm": 0.7083474109399462, + "learning_rate": 1.7058402716038317e-05, + "loss": 0.9744, + "step": 4448 + }, + { + "epoch": 0.27312072193744436, + "grad_norm": 0.5987632530598679, + "learning_rate": 1.7056994087144443e-05, + "loss": 0.9821, + "step": 4449 + }, + { + "epoch": 0.27318211117591085, + "grad_norm": 0.6512173989689034, + "learning_rate": 1.7055585179249853e-05, + "loss": 0.9575, + "step": 4450 + }, + { + "epoch": 0.27324350041437734, + "grad_norm": 0.689853267788838, + "learning_rate": 1.705417599241024e-05, + "loss": 1.0078, + "step": 4451 + }, + { + "epoch": 0.27330488965284383, + "grad_norm": 0.6181030616689633, + "learning_rate": 1.7052766526681323e-05, + "loss": 0.919, + "step": 4452 + }, + { + "epoch": 0.2733662788913104, + "grad_norm": 0.6818880471621439, + "learning_rate": 1.7051356782118826e-05, + "loss": 0.9353, + "step": 4453 + }, + { + "epoch": 0.27342766812977687, + "grad_norm": 0.6481507423103833, + "learning_rate": 1.704994675877848e-05, + "loss": 0.9211, + "step": 4454 + }, + { + "epoch": 0.27348905736824336, + "grad_norm": 0.7072276375356142, + "learning_rate": 1.7048536456716035e-05, + "loss": 0.9393, + "step": 4455 + }, + { + "epoch": 0.27355044660670985, + "grad_norm": 0.6671340521559006, + "learning_rate": 1.7047125875987244e-05, + "loss": 0.9558, + "step": 4456 + }, + { + "epoch": 0.27361183584517634, + "grad_norm": 0.621023800850385, + "learning_rate": 1.7045715016647876e-05, + "loss": 0.8807, + "step": 4457 + }, + { + "epoch": 0.27367322508364283, + "grad_norm": 0.6745926749587541, + "learning_rate": 1.704430387875371e-05, + "loss": 0.9351, + "step": 4458 + }, + { + "epoch": 0.2737346143221093, + "grad_norm": 0.6397713580661819, + "learning_rate": 1.704289246236054e-05, + "loss": 0.964, + "step": 4459 + }, + { + "epoch": 0.2737960035605758, + "grad_norm": 0.6456572977714016, + "learning_rate": 1.704148076752416e-05, + "loss": 0.9447, + "step": 4460 + }, + { + "epoch": 0.2738573927990423, + "grad_norm": 0.6264787402285668, + "learning_rate": 1.7040068794300385e-05, + "loss": 1.0154, + "step": 4461 + }, + { + "epoch": 0.2739187820375088, + "grad_norm": 0.6341264269509459, + "learning_rate": 1.7038656542745034e-05, + "loss": 0.9684, + "step": 4462 + }, + { + "epoch": 0.27398017127597535, + "grad_norm": 0.6482308887172002, + "learning_rate": 1.7037244012913953e-05, + "loss": 0.9625, + "step": 4463 + }, + { + "epoch": 0.27404156051444184, + "grad_norm": 0.6619268236880097, + "learning_rate": 1.703583120486297e-05, + "loss": 0.7529, + "step": 4464 + }, + { + "epoch": 0.27410294975290833, + "grad_norm": 0.6546432474654293, + "learning_rate": 1.7034418118647954e-05, + "loss": 0.9593, + "step": 4465 + }, + { + "epoch": 0.2741643389913748, + "grad_norm": 0.627785186287015, + "learning_rate": 1.7033004754324766e-05, + "loss": 0.9381, + "step": 4466 + }, + { + "epoch": 0.2742257282298413, + "grad_norm": 0.7077638207141428, + "learning_rate": 1.7031591111949285e-05, + "loss": 1.0097, + "step": 4467 + }, + { + "epoch": 0.2742871174683078, + "grad_norm": 0.7571731870847512, + "learning_rate": 1.7030177191577398e-05, + "loss": 1.043, + "step": 4468 + }, + { + "epoch": 0.2743485067067743, + "grad_norm": 0.8209154295493443, + "learning_rate": 1.7028762993265008e-05, + "loss": 1.0173, + "step": 4469 + }, + { + "epoch": 0.2744098959452408, + "grad_norm": 0.6704919429452393, + "learning_rate": 1.7027348517068024e-05, + "loss": 0.9852, + "step": 4470 + }, + { + "epoch": 0.2744712851837073, + "grad_norm": 0.6805168125351913, + "learning_rate": 1.702593376304237e-05, + "loss": 0.9883, + "step": 4471 + }, + { + "epoch": 0.2745326744221738, + "grad_norm": 0.6396913487530713, + "learning_rate": 1.7024518731243976e-05, + "loss": 0.9694, + "step": 4472 + }, + { + "epoch": 0.27459406366064026, + "grad_norm": 0.5942990053170724, + "learning_rate": 1.7023103421728788e-05, + "loss": 0.9342, + "step": 4473 + }, + { + "epoch": 0.2746554528991068, + "grad_norm": 0.5968180766704319, + "learning_rate": 1.7021687834552755e-05, + "loss": 0.9297, + "step": 4474 + }, + { + "epoch": 0.2747168421375733, + "grad_norm": 0.6658991684148168, + "learning_rate": 1.702027196977185e-05, + "loss": 0.9268, + "step": 4475 + }, + { + "epoch": 0.2747782313760398, + "grad_norm": 0.614721732635249, + "learning_rate": 1.701885582744205e-05, + "loss": 0.9367, + "step": 4476 + }, + { + "epoch": 0.2748396206145063, + "grad_norm": 0.6679344437617222, + "learning_rate": 1.7017439407619333e-05, + "loss": 0.9645, + "step": 4477 + }, + { + "epoch": 0.2749010098529728, + "grad_norm": 0.6508552084534246, + "learning_rate": 1.701602271035971e-05, + "loss": 0.9643, + "step": 4478 + }, + { + "epoch": 0.27496239909143927, + "grad_norm": 0.7271689254266548, + "learning_rate": 1.7014605735719182e-05, + "loss": 1.0191, + "step": 4479 + }, + { + "epoch": 0.27502378832990576, + "grad_norm": 0.646132802760918, + "learning_rate": 1.7013188483753776e-05, + "loss": 0.9839, + "step": 4480 + }, + { + "epoch": 0.27508517756837225, + "grad_norm": 0.6634647157466046, + "learning_rate": 1.7011770954519517e-05, + "loss": 0.961, + "step": 4481 + }, + { + "epoch": 0.27514656680683874, + "grad_norm": 0.7195539555089059, + "learning_rate": 1.701035314807245e-05, + "loss": 0.9805, + "step": 4482 + }, + { + "epoch": 0.27520795604530524, + "grad_norm": 0.678252045999876, + "learning_rate": 1.700893506446863e-05, + "loss": 0.9777, + "step": 4483 + }, + { + "epoch": 0.2752693452837718, + "grad_norm": 0.6725652845817244, + "learning_rate": 1.700751670376412e-05, + "loss": 0.935, + "step": 4484 + }, + { + "epoch": 0.2753307345222383, + "grad_norm": 0.6687039959167048, + "learning_rate": 1.7006098066015e-05, + "loss": 0.9723, + "step": 4485 + }, + { + "epoch": 0.27539212376070477, + "grad_norm": 0.6093935203812034, + "learning_rate": 1.700467915127735e-05, + "loss": 0.9717, + "step": 4486 + }, + { + "epoch": 0.27545351299917126, + "grad_norm": 0.6866938398149973, + "learning_rate": 1.7003259959607266e-05, + "loss": 0.9632, + "step": 4487 + }, + { + "epoch": 0.27551490223763775, + "grad_norm": 0.6460992170040064, + "learning_rate": 1.7001840491060863e-05, + "loss": 0.9671, + "step": 4488 + }, + { + "epoch": 0.27557629147610424, + "grad_norm": 0.6957474615972697, + "learning_rate": 1.7000420745694256e-05, + "loss": 1.0112, + "step": 4489 + }, + { + "epoch": 0.27563768071457073, + "grad_norm": 0.7008221413688842, + "learning_rate": 1.6999000723563575e-05, + "loss": 0.9437, + "step": 4490 + }, + { + "epoch": 0.2756990699530372, + "grad_norm": 0.6873178576331589, + "learning_rate": 1.6997580424724963e-05, + "loss": 0.9782, + "step": 4491 + }, + { + "epoch": 0.2757604591915037, + "grad_norm": 0.6515688745088741, + "learning_rate": 1.6996159849234572e-05, + "loss": 0.9297, + "step": 4492 + }, + { + "epoch": 0.2758218484299702, + "grad_norm": 0.6798535744647057, + "learning_rate": 1.6994738997148564e-05, + "loss": 0.9315, + "step": 4493 + }, + { + "epoch": 0.2758832376684367, + "grad_norm": 0.6925597299117583, + "learning_rate": 1.699331786852311e-05, + "loss": 0.9537, + "step": 4494 + }, + { + "epoch": 0.27594462690690325, + "grad_norm": 0.6711074476083578, + "learning_rate": 1.69918964634144e-05, + "loss": 0.9563, + "step": 4495 + }, + { + "epoch": 0.27600601614536974, + "grad_norm": 0.6443186705647546, + "learning_rate": 1.699047478187863e-05, + "loss": 0.8981, + "step": 4496 + }, + { + "epoch": 0.27606740538383623, + "grad_norm": 0.7703347275141785, + "learning_rate": 1.6989052823972e-05, + "loss": 1.0432, + "step": 4497 + }, + { + "epoch": 0.2761287946223027, + "grad_norm": 0.7194008172290656, + "learning_rate": 1.6987630589750733e-05, + "loss": 1.0199, + "step": 4498 + }, + { + "epoch": 0.2761901838607692, + "grad_norm": 0.7179976684345275, + "learning_rate": 1.6986208079271058e-05, + "loss": 0.9687, + "step": 4499 + }, + { + "epoch": 0.2762515730992357, + "grad_norm": 0.7038396273330799, + "learning_rate": 1.698478529258921e-05, + "loss": 0.9408, + "step": 4500 + }, + { + "epoch": 0.2763129623377022, + "grad_norm": 0.6161200852249745, + "learning_rate": 1.6983362229761448e-05, + "loss": 0.9694, + "step": 4501 + }, + { + "epoch": 0.2763743515761687, + "grad_norm": 0.6101434709274498, + "learning_rate": 1.698193889084402e-05, + "loss": 0.9436, + "step": 4502 + }, + { + "epoch": 0.2764357408146352, + "grad_norm": 0.6652685808793194, + "learning_rate": 1.698051527589321e-05, + "loss": 0.9704, + "step": 4503 + }, + { + "epoch": 0.27649713005310167, + "grad_norm": 0.6736633603718165, + "learning_rate": 1.6979091384965294e-05, + "loss": 0.936, + "step": 4504 + }, + { + "epoch": 0.27655851929156816, + "grad_norm": 0.6386475616553945, + "learning_rate": 1.6977667218116572e-05, + "loss": 0.9171, + "step": 4505 + }, + { + "epoch": 0.2766199085300347, + "grad_norm": 0.7372343435239984, + "learning_rate": 1.6976242775403342e-05, + "loss": 1.02, + "step": 4506 + }, + { + "epoch": 0.2766812977685012, + "grad_norm": 0.7306001032591337, + "learning_rate": 1.6974818056881926e-05, + "loss": 0.9751, + "step": 4507 + }, + { + "epoch": 0.2767426870069677, + "grad_norm": 0.6875321426850981, + "learning_rate": 1.6973393062608647e-05, + "loss": 0.9559, + "step": 4508 + }, + { + "epoch": 0.2768040762454342, + "grad_norm": 0.724926260536874, + "learning_rate": 1.6971967792639845e-05, + "loss": 0.9679, + "step": 4509 + }, + { + "epoch": 0.2768654654839007, + "grad_norm": 0.6344809286239261, + "learning_rate": 1.6970542247031868e-05, + "loss": 0.8946, + "step": 4510 + }, + { + "epoch": 0.27692685472236717, + "grad_norm": 0.7285760200741589, + "learning_rate": 1.6969116425841075e-05, + "loss": 1.0038, + "step": 4511 + }, + { + "epoch": 0.27698824396083366, + "grad_norm": 0.6505181070186832, + "learning_rate": 1.6967690329123833e-05, + "loss": 0.9295, + "step": 4512 + }, + { + "epoch": 0.27704963319930015, + "grad_norm": 0.7158383595995466, + "learning_rate": 1.696626395693653e-05, + "loss": 0.9881, + "step": 4513 + }, + { + "epoch": 0.27711102243776664, + "grad_norm": 0.6734171365972442, + "learning_rate": 1.6964837309335553e-05, + "loss": 0.6797, + "step": 4514 + }, + { + "epoch": 0.27717241167623313, + "grad_norm": 0.6425378480867101, + "learning_rate": 1.6963410386377306e-05, + "loss": 0.9512, + "step": 4515 + }, + { + "epoch": 0.2772338009146997, + "grad_norm": 0.6694756991579005, + "learning_rate": 1.6961983188118206e-05, + "loss": 1.004, + "step": 4516 + }, + { + "epoch": 0.27729519015316617, + "grad_norm": 0.6876537978316406, + "learning_rate": 1.6960555714614672e-05, + "loss": 0.9731, + "step": 4517 + }, + { + "epoch": 0.27735657939163266, + "grad_norm": 0.6093279681209794, + "learning_rate": 1.6959127965923144e-05, + "loss": 0.9581, + "step": 4518 + }, + { + "epoch": 0.27741796863009915, + "grad_norm": 0.6649552160496712, + "learning_rate": 1.695769994210007e-05, + "loss": 0.9675, + "step": 4519 + }, + { + "epoch": 0.27747935786856565, + "grad_norm": 0.6586352433676173, + "learning_rate": 1.69562716432019e-05, + "loss": 0.9342, + "step": 4520 + }, + { + "epoch": 0.27754074710703214, + "grad_norm": 0.683229447784096, + "learning_rate": 1.6954843069285113e-05, + "loss": 0.9898, + "step": 4521 + }, + { + "epoch": 0.27760213634549863, + "grad_norm": 0.6593254423911192, + "learning_rate": 1.6953414220406177e-05, + "loss": 0.9404, + "step": 4522 + }, + { + "epoch": 0.2776635255839651, + "grad_norm": 0.7006611330922917, + "learning_rate": 1.695198509662159e-05, + "loss": 1.0127, + "step": 4523 + }, + { + "epoch": 0.2777249148224316, + "grad_norm": 0.6637120805532344, + "learning_rate": 1.695055569798785e-05, + "loss": 0.9593, + "step": 4524 + }, + { + "epoch": 0.2777863040608981, + "grad_norm": 0.6615237935255899, + "learning_rate": 1.694912602456147e-05, + "loss": 0.9199, + "step": 4525 + }, + { + "epoch": 0.2778476932993646, + "grad_norm": 0.6866856691251163, + "learning_rate": 1.6947696076398973e-05, + "loss": 0.9386, + "step": 4526 + }, + { + "epoch": 0.27790908253783114, + "grad_norm": 0.7298921667863837, + "learning_rate": 1.6946265853556888e-05, + "loss": 0.9846, + "step": 4527 + }, + { + "epoch": 0.27797047177629763, + "grad_norm": 0.6322291980534058, + "learning_rate": 1.6944835356091763e-05, + "loss": 0.9337, + "step": 4528 + }, + { + "epoch": 0.2780318610147641, + "grad_norm": 0.6822942316839694, + "learning_rate": 1.6943404584060156e-05, + "loss": 0.979, + "step": 4529 + }, + { + "epoch": 0.2780932502532306, + "grad_norm": 0.6671319349126549, + "learning_rate": 1.6941973537518625e-05, + "loss": 0.9453, + "step": 4530 + }, + { + "epoch": 0.2781546394916971, + "grad_norm": 0.7105209138647853, + "learning_rate": 1.6940542216523752e-05, + "loss": 0.9673, + "step": 4531 + }, + { + "epoch": 0.2782160287301636, + "grad_norm": 0.6426928020072529, + "learning_rate": 1.693911062113213e-05, + "loss": 0.9375, + "step": 4532 + }, + { + "epoch": 0.2782774179686301, + "grad_norm": 0.5968720404582769, + "learning_rate": 1.6937678751400344e-05, + "loss": 0.9262, + "step": 4533 + }, + { + "epoch": 0.2783388072070966, + "grad_norm": 0.6385141633751688, + "learning_rate": 1.693624660738502e-05, + "loss": 0.9184, + "step": 4534 + }, + { + "epoch": 0.2784001964455631, + "grad_norm": 0.6606205418679376, + "learning_rate": 1.6934814189142766e-05, + "loss": 0.9379, + "step": 4535 + }, + { + "epoch": 0.27846158568402957, + "grad_norm": 0.6606664174335526, + "learning_rate": 1.6933381496730218e-05, + "loss": 0.9345, + "step": 4536 + }, + { + "epoch": 0.2785229749224961, + "grad_norm": 0.647561266641813, + "learning_rate": 1.6931948530204018e-05, + "loss": 0.9564, + "step": 4537 + }, + { + "epoch": 0.2785843641609626, + "grad_norm": 0.700878667291816, + "learning_rate": 1.6930515289620813e-05, + "loss": 0.9935, + "step": 4538 + }, + { + "epoch": 0.2786457533994291, + "grad_norm": 0.6870096418424689, + "learning_rate": 1.6929081775037276e-05, + "loss": 1.0083, + "step": 4539 + }, + { + "epoch": 0.2787071426378956, + "grad_norm": 0.7337048896816241, + "learning_rate": 1.6927647986510077e-05, + "loss": 0.9878, + "step": 4540 + }, + { + "epoch": 0.2787685318763621, + "grad_norm": 0.6088577913403892, + "learning_rate": 1.69262139240959e-05, + "loss": 0.9002, + "step": 4541 + }, + { + "epoch": 0.27882992111482857, + "grad_norm": 0.6855171760551626, + "learning_rate": 1.6924779587851447e-05, + "loss": 0.9782, + "step": 4542 + }, + { + "epoch": 0.27889131035329506, + "grad_norm": 0.6619068415302214, + "learning_rate": 1.6923344977833413e-05, + "loss": 0.933, + "step": 4543 + }, + { + "epoch": 0.27895269959176155, + "grad_norm": 0.6519218608972172, + "learning_rate": 1.692191009409853e-05, + "loss": 0.9346, + "step": 4544 + }, + { + "epoch": 0.27901408883022805, + "grad_norm": 0.6567408490098167, + "learning_rate": 1.6920474936703515e-05, + "loss": 0.959, + "step": 4545 + }, + { + "epoch": 0.27907547806869454, + "grad_norm": 0.7522063461036314, + "learning_rate": 1.6919039505705116e-05, + "loss": 1.0459, + "step": 4546 + }, + { + "epoch": 0.27913686730716103, + "grad_norm": 0.6465071443383896, + "learning_rate": 1.6917603801160076e-05, + "loss": 0.9058, + "step": 4547 + }, + { + "epoch": 0.2791982565456276, + "grad_norm": 0.71509531972908, + "learning_rate": 1.6916167823125163e-05, + "loss": 0.7913, + "step": 4548 + }, + { + "epoch": 0.27925964578409407, + "grad_norm": 0.6270368224434125, + "learning_rate": 1.6914731571657146e-05, + "loss": 0.8914, + "step": 4549 + }, + { + "epoch": 0.27932103502256056, + "grad_norm": 0.665811911101085, + "learning_rate": 1.6913295046812806e-05, + "loss": 1.0578, + "step": 4550 + }, + { + "epoch": 0.27938242426102705, + "grad_norm": 0.665907228776672, + "learning_rate": 1.691185824864894e-05, + "loss": 0.9714, + "step": 4551 + }, + { + "epoch": 0.27944381349949354, + "grad_norm": 0.6340840130408075, + "learning_rate": 1.6910421177222346e-05, + "loss": 0.9181, + "step": 4552 + }, + { + "epoch": 0.27950520273796003, + "grad_norm": 0.6680263643757539, + "learning_rate": 1.6908983832589843e-05, + "loss": 0.9258, + "step": 4553 + }, + { + "epoch": 0.2795665919764265, + "grad_norm": 0.7438692467327364, + "learning_rate": 1.6907546214808263e-05, + "loss": 0.9785, + "step": 4554 + }, + { + "epoch": 0.279627981214893, + "grad_norm": 0.6156360454350248, + "learning_rate": 1.6906108323934434e-05, + "loss": 0.9096, + "step": 4555 + }, + { + "epoch": 0.2796893704533595, + "grad_norm": 0.653263312255218, + "learning_rate": 1.6904670160025207e-05, + "loss": 0.9784, + "step": 4556 + }, + { + "epoch": 0.279750759691826, + "grad_norm": 0.6602893325449041, + "learning_rate": 1.6903231723137437e-05, + "loss": 0.9908, + "step": 4557 + }, + { + "epoch": 0.2798121489302925, + "grad_norm": 0.6490193538587756, + "learning_rate": 1.6901793013327998e-05, + "loss": 0.9909, + "step": 4558 + }, + { + "epoch": 0.27987353816875904, + "grad_norm": 0.6412186705245008, + "learning_rate": 1.690035403065377e-05, + "loss": 0.9599, + "step": 4559 + }, + { + "epoch": 0.27993492740722553, + "grad_norm": 0.7042196638116704, + "learning_rate": 1.689891477517164e-05, + "loss": 0.9809, + "step": 4560 + }, + { + "epoch": 0.279996316645692, + "grad_norm": 0.680561092352415, + "learning_rate": 1.6897475246938507e-05, + "loss": 0.9658, + "step": 4561 + }, + { + "epoch": 0.2800577058841585, + "grad_norm": 0.6839552883600424, + "learning_rate": 1.689603544601129e-05, + "loss": 1.0181, + "step": 4562 + }, + { + "epoch": 0.280119095122625, + "grad_norm": 0.6418486673532151, + "learning_rate": 1.6894595372446915e-05, + "loss": 0.967, + "step": 4563 + }, + { + "epoch": 0.2801804843610915, + "grad_norm": 0.6676748526109084, + "learning_rate": 1.68931550263023e-05, + "loss": 0.9489, + "step": 4564 + }, + { + "epoch": 0.280241873599558, + "grad_norm": 0.6405390794269914, + "learning_rate": 1.6891714407634404e-05, + "loss": 0.941, + "step": 4565 + }, + { + "epoch": 0.2803032628380245, + "grad_norm": 0.66768896054529, + "learning_rate": 1.6890273516500182e-05, + "loss": 0.9446, + "step": 4566 + }, + { + "epoch": 0.28036465207649097, + "grad_norm": 0.6433931526705575, + "learning_rate": 1.6888832352956594e-05, + "loss": 0.9633, + "step": 4567 + }, + { + "epoch": 0.28042604131495746, + "grad_norm": 0.6610971689107358, + "learning_rate": 1.6887390917060616e-05, + "loss": 0.9743, + "step": 4568 + }, + { + "epoch": 0.280487430553424, + "grad_norm": 0.693950344816416, + "learning_rate": 1.688594920886924e-05, + "loss": 0.9748, + "step": 4569 + }, + { + "epoch": 0.2805488197918905, + "grad_norm": 0.7026790708034829, + "learning_rate": 1.6884507228439463e-05, + "loss": 0.968, + "step": 4570 + }, + { + "epoch": 0.280610209030357, + "grad_norm": 0.655716577206835, + "learning_rate": 1.6883064975828297e-05, + "loss": 0.994, + "step": 4571 + }, + { + "epoch": 0.2806715982688235, + "grad_norm": 0.6757882617292246, + "learning_rate": 1.6881622451092754e-05, + "loss": 0.9083, + "step": 4572 + }, + { + "epoch": 0.28073298750729, + "grad_norm": 0.676127098711851, + "learning_rate": 1.6880179654289876e-05, + "loss": 0.9801, + "step": 4573 + }, + { + "epoch": 0.28079437674575647, + "grad_norm": 0.5941627337435764, + "learning_rate": 1.6878736585476695e-05, + "loss": 0.9423, + "step": 4574 + }, + { + "epoch": 0.28085576598422296, + "grad_norm": 0.6702469178118574, + "learning_rate": 1.6877293244710267e-05, + "loss": 0.935, + "step": 4575 + }, + { + "epoch": 0.28091715522268945, + "grad_norm": 0.6756013003134557, + "learning_rate": 1.6875849632047653e-05, + "loss": 1.016, + "step": 4576 + }, + { + "epoch": 0.28097854446115594, + "grad_norm": 0.669147641985828, + "learning_rate": 1.687440574754593e-05, + "loss": 0.9585, + "step": 4577 + }, + { + "epoch": 0.28103993369962244, + "grad_norm": 0.6932307311484303, + "learning_rate": 1.687296159126218e-05, + "loss": 0.955, + "step": 4578 + }, + { + "epoch": 0.2811013229380889, + "grad_norm": 0.6730108162130504, + "learning_rate": 1.6871517163253504e-05, + "loss": 0.942, + "step": 4579 + }, + { + "epoch": 0.2811627121765555, + "grad_norm": 0.684388012956444, + "learning_rate": 1.6870072463576995e-05, + "loss": 0.9875, + "step": 4580 + }, + { + "epoch": 0.28122410141502197, + "grad_norm": 0.712783308898785, + "learning_rate": 1.6868627492289786e-05, + "loss": 0.9627, + "step": 4581 + }, + { + "epoch": 0.28128549065348846, + "grad_norm": 0.7120817641227035, + "learning_rate": 1.686718224944899e-05, + "loss": 0.9977, + "step": 4582 + }, + { + "epoch": 0.28134687989195495, + "grad_norm": 0.7004602571382065, + "learning_rate": 1.6865736735111755e-05, + "loss": 1.0349, + "step": 4583 + }, + { + "epoch": 0.28140826913042144, + "grad_norm": 0.6180105148510918, + "learning_rate": 1.6864290949335225e-05, + "loss": 0.9779, + "step": 4584 + }, + { + "epoch": 0.28146965836888793, + "grad_norm": 0.6372846046630467, + "learning_rate": 1.686284489217656e-05, + "loss": 0.9644, + "step": 4585 + }, + { + "epoch": 0.2815310476073544, + "grad_norm": 0.6230645904217134, + "learning_rate": 1.6861398563692934e-05, + "loss": 0.9466, + "step": 4586 + }, + { + "epoch": 0.2815924368458209, + "grad_norm": 0.728616273980487, + "learning_rate": 1.6859951963941523e-05, + "loss": 1.0248, + "step": 4587 + }, + { + "epoch": 0.2816538260842874, + "grad_norm": 0.6864741177013073, + "learning_rate": 1.6858505092979523e-05, + "loss": 1.004, + "step": 4588 + }, + { + "epoch": 0.2817152153227539, + "grad_norm": 0.6890869632212003, + "learning_rate": 1.6857057950864134e-05, + "loss": 0.9285, + "step": 4589 + }, + { + "epoch": 0.28177660456122045, + "grad_norm": 0.6469880784502678, + "learning_rate": 1.685561053765257e-05, + "loss": 0.9774, + "step": 4590 + }, + { + "epoch": 0.28183799379968694, + "grad_norm": 0.621827517048206, + "learning_rate": 1.6854162853402054e-05, + "loss": 0.9656, + "step": 4591 + }, + { + "epoch": 0.28189938303815343, + "grad_norm": 0.6342995056011751, + "learning_rate": 1.6852714898169824e-05, + "loss": 0.906, + "step": 4592 + }, + { + "epoch": 0.2819607722766199, + "grad_norm": 0.679423246223174, + "learning_rate": 1.685126667201312e-05, + "loss": 0.9367, + "step": 4593 + }, + { + "epoch": 0.2820221615150864, + "grad_norm": 0.6577675154558252, + "learning_rate": 1.6849818174989202e-05, + "loss": 0.947, + "step": 4594 + }, + { + "epoch": 0.2820835507535529, + "grad_norm": 0.6295201430930942, + "learning_rate": 1.684836940715534e-05, + "loss": 0.9735, + "step": 4595 + }, + { + "epoch": 0.2821449399920194, + "grad_norm": 0.6177979094456378, + "learning_rate": 1.6846920368568804e-05, + "loss": 0.9288, + "step": 4596 + }, + { + "epoch": 0.2822063292304859, + "grad_norm": 0.6109877962308738, + "learning_rate": 1.684547105928689e-05, + "loss": 0.7412, + "step": 4597 + }, + { + "epoch": 0.2822677184689524, + "grad_norm": 0.6868758541222126, + "learning_rate": 1.6844021479366886e-05, + "loss": 1.012, + "step": 4598 + }, + { + "epoch": 0.28232910770741887, + "grad_norm": 0.6940515219219535, + "learning_rate": 1.6842571628866114e-05, + "loss": 0.9806, + "step": 4599 + }, + { + "epoch": 0.28239049694588536, + "grad_norm": 0.684102384560728, + "learning_rate": 1.6841121507841888e-05, + "loss": 0.9853, + "step": 4600 + }, + { + "epoch": 0.2824518861843519, + "grad_norm": 0.6770694850571932, + "learning_rate": 1.683967111635154e-05, + "loss": 0.9712, + "step": 4601 + }, + { + "epoch": 0.2825132754228184, + "grad_norm": 0.6303751593261794, + "learning_rate": 1.6838220454452413e-05, + "loss": 0.9391, + "step": 4602 + }, + { + "epoch": 0.2825746646612849, + "grad_norm": 0.6185959938694391, + "learning_rate": 1.6836769522201853e-05, + "loss": 0.9291, + "step": 4603 + }, + { + "epoch": 0.2826360538997514, + "grad_norm": 0.6917176583530554, + "learning_rate": 1.683531831965723e-05, + "loss": 0.9957, + "step": 4604 + }, + { + "epoch": 0.2826974431382179, + "grad_norm": 0.6349676579098963, + "learning_rate": 1.6833866846875916e-05, + "loss": 0.9399, + "step": 4605 + }, + { + "epoch": 0.28275883237668437, + "grad_norm": 0.6050222978760997, + "learning_rate": 1.68324151039153e-05, + "loss": 0.7653, + "step": 4606 + }, + { + "epoch": 0.28282022161515086, + "grad_norm": 0.6412262467590597, + "learning_rate": 1.6830963090832768e-05, + "loss": 0.977, + "step": 4607 + }, + { + "epoch": 0.28288161085361735, + "grad_norm": 0.6879659203976964, + "learning_rate": 1.6829510807685735e-05, + "loss": 0.9769, + "step": 4608 + }, + { + "epoch": 0.28294300009208384, + "grad_norm": 0.6674897691737893, + "learning_rate": 1.6828058254531606e-05, + "loss": 0.9324, + "step": 4609 + }, + { + "epoch": 0.28300438933055033, + "grad_norm": 0.5896856992864199, + "learning_rate": 1.682660543142782e-05, + "loss": 0.9514, + "step": 4610 + }, + { + "epoch": 0.2830657785690168, + "grad_norm": 0.579396910255958, + "learning_rate": 1.682515233843181e-05, + "loss": 0.8761, + "step": 4611 + }, + { + "epoch": 0.28312716780748337, + "grad_norm": 0.6885942461925649, + "learning_rate": 1.682369897560102e-05, + "loss": 0.9524, + "step": 4612 + }, + { + "epoch": 0.28318855704594986, + "grad_norm": 0.655871339635009, + "learning_rate": 1.6822245342992917e-05, + "loss": 0.9288, + "step": 4613 + }, + { + "epoch": 0.28324994628441635, + "grad_norm": 0.6725623929613189, + "learning_rate": 1.682079144066497e-05, + "loss": 0.9698, + "step": 4614 + }, + { + "epoch": 0.28331133552288285, + "grad_norm": 0.6848159937233622, + "learning_rate": 1.6819337268674654e-05, + "loss": 0.9987, + "step": 4615 + }, + { + "epoch": 0.28337272476134934, + "grad_norm": 0.6531436329840812, + "learning_rate": 1.6817882827079464e-05, + "loss": 0.9125, + "step": 4616 + }, + { + "epoch": 0.28343411399981583, + "grad_norm": 0.6323478473387094, + "learning_rate": 1.6816428115936903e-05, + "loss": 0.8831, + "step": 4617 + }, + { + "epoch": 0.2834955032382823, + "grad_norm": 0.695245019348433, + "learning_rate": 1.681497313530448e-05, + "loss": 0.9883, + "step": 4618 + }, + { + "epoch": 0.2835568924767488, + "grad_norm": 0.7225173983491484, + "learning_rate": 1.6813517885239718e-05, + "loss": 0.9787, + "step": 4619 + }, + { + "epoch": 0.2836182817152153, + "grad_norm": 0.6314116394164522, + "learning_rate": 1.6812062365800157e-05, + "loss": 0.9134, + "step": 4620 + }, + { + "epoch": 0.2836796709536818, + "grad_norm": 0.6665080137425331, + "learning_rate": 1.6810606577043334e-05, + "loss": 0.9264, + "step": 4621 + }, + { + "epoch": 0.28374106019214834, + "grad_norm": 0.6420706266434724, + "learning_rate": 1.6809150519026813e-05, + "loss": 0.9564, + "step": 4622 + }, + { + "epoch": 0.28380244943061483, + "grad_norm": 0.5834386057685501, + "learning_rate": 1.680769419180815e-05, + "loss": 0.7426, + "step": 4623 + }, + { + "epoch": 0.2838638386690813, + "grad_norm": 0.7063320780962029, + "learning_rate": 1.680623759544492e-05, + "loss": 0.9719, + "step": 4624 + }, + { + "epoch": 0.2839252279075478, + "grad_norm": 0.7024695329551603, + "learning_rate": 1.6804780729994723e-05, + "loss": 0.9514, + "step": 4625 + }, + { + "epoch": 0.2839866171460143, + "grad_norm": 0.6642265662644817, + "learning_rate": 1.6803323595515145e-05, + "loss": 0.9495, + "step": 4626 + }, + { + "epoch": 0.2840480063844808, + "grad_norm": 0.6392505767570064, + "learning_rate": 1.6801866192063802e-05, + "loss": 0.9389, + "step": 4627 + }, + { + "epoch": 0.2841093956229473, + "grad_norm": 0.6177340936279732, + "learning_rate": 1.680040851969831e-05, + "loss": 0.8775, + "step": 4628 + }, + { + "epoch": 0.2841707848614138, + "grad_norm": 0.5924144611894047, + "learning_rate": 1.6798950578476296e-05, + "loss": 0.9429, + "step": 4629 + }, + { + "epoch": 0.2842321740998803, + "grad_norm": 0.6354092632419276, + "learning_rate": 1.6797492368455403e-05, + "loss": 0.9459, + "step": 4630 + }, + { + "epoch": 0.28429356333834677, + "grad_norm": 0.6947491324724244, + "learning_rate": 1.6796033889693277e-05, + "loss": 0.9455, + "step": 4631 + }, + { + "epoch": 0.28435495257681326, + "grad_norm": 0.6494891463173192, + "learning_rate": 1.6794575142247588e-05, + "loss": 0.9619, + "step": 4632 + }, + { + "epoch": 0.2844163418152798, + "grad_norm": 0.7004518958826892, + "learning_rate": 1.6793116126176004e-05, + "loss": 0.937, + "step": 4633 + }, + { + "epoch": 0.2844777310537463, + "grad_norm": 0.6411774549068057, + "learning_rate": 1.6791656841536205e-05, + "loss": 0.956, + "step": 4634 + }, + { + "epoch": 0.2845391202922128, + "grad_norm": 0.6218971279759318, + "learning_rate": 1.679019728838589e-05, + "loss": 0.9299, + "step": 4635 + }, + { + "epoch": 0.2846005095306793, + "grad_norm": 0.6410956243212123, + "learning_rate": 1.6788737466782756e-05, + "loss": 0.9146, + "step": 4636 + }, + { + "epoch": 0.28466189876914577, + "grad_norm": 0.6948313621783305, + "learning_rate": 1.6787277376784522e-05, + "loss": 0.9364, + "step": 4637 + }, + { + "epoch": 0.28472328800761226, + "grad_norm": 0.7173662680927693, + "learning_rate": 1.6785817018448914e-05, + "loss": 1.0122, + "step": 4638 + }, + { + "epoch": 0.28478467724607875, + "grad_norm": 0.6916156218324728, + "learning_rate": 1.6784356391833665e-05, + "loss": 1.0089, + "step": 4639 + }, + { + "epoch": 0.28484606648454525, + "grad_norm": 0.6695395580842463, + "learning_rate": 1.6782895496996522e-05, + "loss": 0.9803, + "step": 4640 + }, + { + "epoch": 0.28490745572301174, + "grad_norm": 0.6744096269342781, + "learning_rate": 1.6781434333995243e-05, + "loss": 0.968, + "step": 4641 + }, + { + "epoch": 0.28496884496147823, + "grad_norm": 0.5786462266403395, + "learning_rate": 1.6779972902887596e-05, + "loss": 0.9307, + "step": 4642 + }, + { + "epoch": 0.2850302341999448, + "grad_norm": 0.6622627028253119, + "learning_rate": 1.677851120373136e-05, + "loss": 0.9379, + "step": 4643 + }, + { + "epoch": 0.28509162343841127, + "grad_norm": 0.6017421074195549, + "learning_rate": 1.6777049236584318e-05, + "loss": 0.8892, + "step": 4644 + }, + { + "epoch": 0.28515301267687776, + "grad_norm": 0.6648076045252168, + "learning_rate": 1.6775587001504277e-05, + "loss": 0.944, + "step": 4645 + }, + { + "epoch": 0.28521440191534425, + "grad_norm": 0.7458459394267923, + "learning_rate": 1.677412449854904e-05, + "loss": 0.9649, + "step": 4646 + }, + { + "epoch": 0.28527579115381074, + "grad_norm": 0.6442542483554597, + "learning_rate": 1.6772661727776434e-05, + "loss": 0.9757, + "step": 4647 + }, + { + "epoch": 0.28533718039227723, + "grad_norm": 0.6897287382625648, + "learning_rate": 1.6771198689244286e-05, + "loss": 1.0182, + "step": 4648 + }, + { + "epoch": 0.2853985696307437, + "grad_norm": 0.63014641367353, + "learning_rate": 1.676973538301044e-05, + "loss": 0.9171, + "step": 4649 + }, + { + "epoch": 0.2854599588692102, + "grad_norm": 0.6769699114016752, + "learning_rate": 1.6768271809132747e-05, + "loss": 0.9794, + "step": 4650 + }, + { + "epoch": 0.2855213481076767, + "grad_norm": 0.6586983366369661, + "learning_rate": 1.6766807967669066e-05, + "loss": 0.9646, + "step": 4651 + }, + { + "epoch": 0.2855827373461432, + "grad_norm": 0.7065641443207098, + "learning_rate": 1.676534385867728e-05, + "loss": 0.9485, + "step": 4652 + }, + { + "epoch": 0.2856441265846097, + "grad_norm": 0.6863802814079015, + "learning_rate": 1.6763879482215264e-05, + "loss": 0.9763, + "step": 4653 + }, + { + "epoch": 0.28570551582307624, + "grad_norm": 0.6272146843753157, + "learning_rate": 1.6762414838340918e-05, + "loss": 0.9285, + "step": 4654 + }, + { + "epoch": 0.28576690506154273, + "grad_norm": 0.6690954185574155, + "learning_rate": 1.6760949927112148e-05, + "loss": 0.9568, + "step": 4655 + }, + { + "epoch": 0.2858282943000092, + "grad_norm": 0.6299902161136118, + "learning_rate": 1.6759484748586862e-05, + "loss": 0.8932, + "step": 4656 + }, + { + "epoch": 0.2858896835384757, + "grad_norm": 0.6778831364065719, + "learning_rate": 1.6758019302822993e-05, + "loss": 1.0208, + "step": 4657 + }, + { + "epoch": 0.2859510727769422, + "grad_norm": 0.6282316050620831, + "learning_rate": 1.675655358987848e-05, + "loss": 0.9196, + "step": 4658 + }, + { + "epoch": 0.2860124620154087, + "grad_norm": 0.6648143236704891, + "learning_rate": 1.675508760981126e-05, + "loss": 0.9481, + "step": 4659 + }, + { + "epoch": 0.2860738512538752, + "grad_norm": 0.6646646507216873, + "learning_rate": 1.6753621362679307e-05, + "loss": 0.9557, + "step": 4660 + }, + { + "epoch": 0.2861352404923417, + "grad_norm": 0.6749344092953836, + "learning_rate": 1.6752154848540577e-05, + "loss": 1.0119, + "step": 4661 + }, + { + "epoch": 0.28619662973080817, + "grad_norm": 0.6656472594723587, + "learning_rate": 1.6750688067453048e-05, + "loss": 0.9251, + "step": 4662 + }, + { + "epoch": 0.28625801896927466, + "grad_norm": 0.6511142981675468, + "learning_rate": 1.674922101947472e-05, + "loss": 0.9282, + "step": 4663 + }, + { + "epoch": 0.2863194082077412, + "grad_norm": 0.6828385141976154, + "learning_rate": 1.6747753704663586e-05, + "loss": 0.9663, + "step": 4664 + }, + { + "epoch": 0.2863807974462077, + "grad_norm": 0.6859040577994864, + "learning_rate": 1.674628612307766e-05, + "loss": 0.9501, + "step": 4665 + }, + { + "epoch": 0.2864421866846742, + "grad_norm": 0.6883559530420434, + "learning_rate": 1.6744818274774962e-05, + "loss": 0.9345, + "step": 4666 + }, + { + "epoch": 0.2865035759231407, + "grad_norm": 0.6391862036220894, + "learning_rate": 1.674335015981352e-05, + "loss": 0.9144, + "step": 4667 + }, + { + "epoch": 0.2865649651616072, + "grad_norm": 0.7189354405249838, + "learning_rate": 1.6741881778251383e-05, + "loss": 1.0059, + "step": 4668 + }, + { + "epoch": 0.28662635440007367, + "grad_norm": 0.6084689769507252, + "learning_rate": 1.67404131301466e-05, + "loss": 0.8941, + "step": 4669 + }, + { + "epoch": 0.28668774363854016, + "grad_norm": 0.6383760006096348, + "learning_rate": 1.673894421555724e-05, + "loss": 0.9775, + "step": 4670 + }, + { + "epoch": 0.28674913287700665, + "grad_norm": 0.5796383771503942, + "learning_rate": 1.673747503454137e-05, + "loss": 0.9594, + "step": 4671 + }, + { + "epoch": 0.28681052211547314, + "grad_norm": 0.7238957780907447, + "learning_rate": 1.6736005587157077e-05, + "loss": 1.0293, + "step": 4672 + }, + { + "epoch": 0.28687191135393963, + "grad_norm": 0.6909194356186033, + "learning_rate": 1.6734535873462455e-05, + "loss": 0.9803, + "step": 4673 + }, + { + "epoch": 0.2869333005924061, + "grad_norm": 0.599728094563081, + "learning_rate": 1.6733065893515613e-05, + "loss": 0.8949, + "step": 4674 + }, + { + "epoch": 0.2869946898308727, + "grad_norm": 0.6523427996050893, + "learning_rate": 1.6731595647374665e-05, + "loss": 0.9502, + "step": 4675 + }, + { + "epoch": 0.28705607906933917, + "grad_norm": 0.6715955085180849, + "learning_rate": 1.6730125135097736e-05, + "loss": 0.9613, + "step": 4676 + }, + { + "epoch": 0.28711746830780566, + "grad_norm": 0.6404264942197735, + "learning_rate": 1.6728654356742964e-05, + "loss": 0.9352, + "step": 4677 + }, + { + "epoch": 0.28717885754627215, + "grad_norm": 0.6611724204784742, + "learning_rate": 1.6727183312368504e-05, + "loss": 0.9323, + "step": 4678 + }, + { + "epoch": 0.28724024678473864, + "grad_norm": 0.6801094164052799, + "learning_rate": 1.67257120020325e-05, + "loss": 0.9523, + "step": 4679 + }, + { + "epoch": 0.28730163602320513, + "grad_norm": 0.6993765934065136, + "learning_rate": 1.6724240425793137e-05, + "loss": 0.9437, + "step": 4680 + }, + { + "epoch": 0.2873630252616716, + "grad_norm": 0.748019333114987, + "learning_rate": 1.6722768583708582e-05, + "loss": 0.9775, + "step": 4681 + }, + { + "epoch": 0.2874244145001381, + "grad_norm": 0.7267329209336784, + "learning_rate": 1.672129647583703e-05, + "loss": 0.9625, + "step": 4682 + }, + { + "epoch": 0.2874858037386046, + "grad_norm": 0.6407897528955795, + "learning_rate": 1.6719824102236678e-05, + "loss": 0.9233, + "step": 4683 + }, + { + "epoch": 0.2875471929770711, + "grad_norm": 0.6336458916178955, + "learning_rate": 1.6718351462965744e-05, + "loss": 0.9386, + "step": 4684 + }, + { + "epoch": 0.2876085822155376, + "grad_norm": 0.709538861219344, + "learning_rate": 1.6716878558082442e-05, + "loss": 0.9702, + "step": 4685 + }, + { + "epoch": 0.28766997145400414, + "grad_norm": 0.6701155290273655, + "learning_rate": 1.6715405387645004e-05, + "loss": 0.9531, + "step": 4686 + }, + { + "epoch": 0.28773136069247063, + "grad_norm": 0.6206514307789263, + "learning_rate": 1.671393195171168e-05, + "loss": 0.8967, + "step": 4687 + }, + { + "epoch": 0.2877927499309371, + "grad_norm": 0.647783600162223, + "learning_rate": 1.671245825034071e-05, + "loss": 0.9423, + "step": 4688 + }, + { + "epoch": 0.2878541391694036, + "grad_norm": 0.7514140830860117, + "learning_rate": 1.671098428359037e-05, + "loss": 0.9894, + "step": 4689 + }, + { + "epoch": 0.2879155284078701, + "grad_norm": 0.6712961772468916, + "learning_rate": 1.6709510051518926e-05, + "loss": 0.9288, + "step": 4690 + }, + { + "epoch": 0.2879769176463366, + "grad_norm": 0.5925300078699425, + "learning_rate": 1.6708035554184664e-05, + "loss": 0.918, + "step": 4691 + }, + { + "epoch": 0.2880383068848031, + "grad_norm": 0.6245789747869578, + "learning_rate": 1.6706560791645884e-05, + "loss": 0.9785, + "step": 4692 + }, + { + "epoch": 0.2880996961232696, + "grad_norm": 0.6085884138062556, + "learning_rate": 1.670508576396088e-05, + "loss": 0.9581, + "step": 4693 + }, + { + "epoch": 0.28816108536173607, + "grad_norm": 0.7220848490648574, + "learning_rate": 1.670361047118798e-05, + "loss": 0.9679, + "step": 4694 + }, + { + "epoch": 0.28822247460020256, + "grad_norm": 0.6145067773707216, + "learning_rate": 1.6702134913385504e-05, + "loss": 0.9448, + "step": 4695 + }, + { + "epoch": 0.2882838638386691, + "grad_norm": 0.6494751570268121, + "learning_rate": 1.6700659090611785e-05, + "loss": 0.9773, + "step": 4696 + }, + { + "epoch": 0.2883452530771356, + "grad_norm": 0.633785083241263, + "learning_rate": 1.669918300292518e-05, + "loss": 0.9923, + "step": 4697 + }, + { + "epoch": 0.2884066423156021, + "grad_norm": 0.6699898709718263, + "learning_rate": 1.6697706650384038e-05, + "loss": 1.0007, + "step": 4698 + }, + { + "epoch": 0.2884680315540686, + "grad_norm": 0.7217880960023133, + "learning_rate": 1.669623003304673e-05, + "loss": 0.9722, + "step": 4699 + }, + { + "epoch": 0.2885294207925351, + "grad_norm": 0.7589168723782828, + "learning_rate": 1.6694753150971635e-05, + "loss": 0.9976, + "step": 4700 + }, + { + "epoch": 0.28859081003100157, + "grad_norm": 0.6738544443494294, + "learning_rate": 1.6693276004217143e-05, + "loss": 0.9408, + "step": 4701 + }, + { + "epoch": 0.28865219926946806, + "grad_norm": 0.6437004962152987, + "learning_rate": 1.6691798592841653e-05, + "loss": 0.9467, + "step": 4702 + }, + { + "epoch": 0.28871358850793455, + "grad_norm": 0.6258261300190981, + "learning_rate": 1.6690320916903573e-05, + "loss": 0.9505, + "step": 4703 + }, + { + "epoch": 0.28877497774640104, + "grad_norm": 0.6798775525932875, + "learning_rate": 1.6688842976461327e-05, + "loss": 0.9505, + "step": 4704 + }, + { + "epoch": 0.28883636698486753, + "grad_norm": 0.6119964266317204, + "learning_rate": 1.6687364771573337e-05, + "loss": 0.9248, + "step": 4705 + }, + { + "epoch": 0.288897756223334, + "grad_norm": 0.5827811996209852, + "learning_rate": 1.6685886302298057e-05, + "loss": 0.8989, + "step": 4706 + }, + { + "epoch": 0.28895914546180057, + "grad_norm": 0.6730002706074878, + "learning_rate": 1.668440756869393e-05, + "loss": 0.9682, + "step": 4707 + }, + { + "epoch": 0.28902053470026706, + "grad_norm": 0.624153288941474, + "learning_rate": 1.6682928570819426e-05, + "loss": 0.7849, + "step": 4708 + }, + { + "epoch": 0.28908192393873355, + "grad_norm": 0.5726172616132952, + "learning_rate": 1.668144930873301e-05, + "loss": 0.7665, + "step": 4709 + }, + { + "epoch": 0.28914331317720005, + "grad_norm": 0.6693481263279445, + "learning_rate": 1.6679969782493165e-05, + "loss": 0.9774, + "step": 4710 + }, + { + "epoch": 0.28920470241566654, + "grad_norm": 0.7201848529939787, + "learning_rate": 1.667848999215839e-05, + "loss": 1.0075, + "step": 4711 + }, + { + "epoch": 0.28926609165413303, + "grad_norm": 0.7174754421448545, + "learning_rate": 1.667700993778719e-05, + "loss": 0.9304, + "step": 4712 + }, + { + "epoch": 0.2893274808925995, + "grad_norm": 0.6322711134409366, + "learning_rate": 1.667552961943807e-05, + "loss": 0.9123, + "step": 4713 + }, + { + "epoch": 0.289388870131066, + "grad_norm": 0.7082126063154058, + "learning_rate": 1.6674049037169565e-05, + "loss": 0.9712, + "step": 4714 + }, + { + "epoch": 0.2894502593695325, + "grad_norm": 0.6290474327100911, + "learning_rate": 1.6672568191040203e-05, + "loss": 0.9094, + "step": 4715 + }, + { + "epoch": 0.289511648607999, + "grad_norm": 0.6393441624519501, + "learning_rate": 1.6671087081108536e-05, + "loss": 1.0018, + "step": 4716 + }, + { + "epoch": 0.28957303784646554, + "grad_norm": 0.7286313285971944, + "learning_rate": 1.6669605707433113e-05, + "loss": 1.0266, + "step": 4717 + }, + { + "epoch": 0.28963442708493203, + "grad_norm": 0.6374849423782477, + "learning_rate": 1.6668124070072508e-05, + "loss": 0.9734, + "step": 4718 + }, + { + "epoch": 0.2896958163233985, + "grad_norm": 0.6210001438066738, + "learning_rate": 1.6666642169085295e-05, + "loss": 0.9273, + "step": 4719 + }, + { + "epoch": 0.289757205561865, + "grad_norm": 0.6849024791245967, + "learning_rate": 1.6665160004530063e-05, + "loss": 0.9681, + "step": 4720 + }, + { + "epoch": 0.2898185948003315, + "grad_norm": 0.6475127817745033, + "learning_rate": 1.6663677576465404e-05, + "loss": 0.9327, + "step": 4721 + }, + { + "epoch": 0.289879984038798, + "grad_norm": 0.6500191474950678, + "learning_rate": 1.6662194884949935e-05, + "loss": 0.9405, + "step": 4722 + }, + { + "epoch": 0.2899413732772645, + "grad_norm": 0.8008314422457179, + "learning_rate": 1.6660711930042266e-05, + "loss": 0.9687, + "step": 4723 + }, + { + "epoch": 0.290002762515731, + "grad_norm": 0.7007451921721255, + "learning_rate": 1.6659228711801035e-05, + "loss": 0.9748, + "step": 4724 + }, + { + "epoch": 0.2900641517541975, + "grad_norm": 0.6595817132195118, + "learning_rate": 1.665774523028487e-05, + "loss": 0.977, + "step": 4725 + }, + { + "epoch": 0.29012554099266397, + "grad_norm": 0.6748950790848977, + "learning_rate": 1.6656261485552437e-05, + "loss": 0.9171, + "step": 4726 + }, + { + "epoch": 0.29018693023113046, + "grad_norm": 0.6767134802967196, + "learning_rate": 1.665477747766238e-05, + "loss": 0.9862, + "step": 4727 + }, + { + "epoch": 0.290248319469597, + "grad_norm": 0.6741116789500003, + "learning_rate": 1.665329320667338e-05, + "loss": 0.9393, + "step": 4728 + }, + { + "epoch": 0.2903097087080635, + "grad_norm": 0.6411544022124763, + "learning_rate": 1.6651808672644114e-05, + "loss": 0.9322, + "step": 4729 + }, + { + "epoch": 0.29037109794653, + "grad_norm": 0.6699198424206887, + "learning_rate": 1.6650323875633277e-05, + "loss": 0.9524, + "step": 4730 + }, + { + "epoch": 0.2904324871849965, + "grad_norm": 0.670543326522989, + "learning_rate": 1.664883881569957e-05, + "loss": 0.8789, + "step": 4731 + }, + { + "epoch": 0.29049387642346297, + "grad_norm": 0.6773480573898768, + "learning_rate": 1.66473534929017e-05, + "loss": 0.9516, + "step": 4732 + }, + { + "epoch": 0.29055526566192946, + "grad_norm": 0.6470002471174493, + "learning_rate": 1.6645867907298395e-05, + "loss": 0.9482, + "step": 4733 + }, + { + "epoch": 0.29061665490039595, + "grad_norm": 0.6797824340794929, + "learning_rate": 1.6644382058948387e-05, + "loss": 0.9957, + "step": 4734 + }, + { + "epoch": 0.29067804413886245, + "grad_norm": 0.6796169835006433, + "learning_rate": 1.664289594791042e-05, + "loss": 0.9403, + "step": 4735 + }, + { + "epoch": 0.29073943337732894, + "grad_norm": 0.6077913025086973, + "learning_rate": 1.6641409574243247e-05, + "loss": 0.9725, + "step": 4736 + }, + { + "epoch": 0.29080082261579543, + "grad_norm": 0.6838493950920297, + "learning_rate": 1.6639922938005634e-05, + "loss": 0.9382, + "step": 4737 + }, + { + "epoch": 0.2908622118542619, + "grad_norm": 0.6133114112736959, + "learning_rate": 1.663843603925635e-05, + "loss": 0.9377, + "step": 4738 + }, + { + "epoch": 0.29092360109272847, + "grad_norm": 0.6766798114573537, + "learning_rate": 1.6636948878054192e-05, + "loss": 0.9816, + "step": 4739 + }, + { + "epoch": 0.29098499033119496, + "grad_norm": 0.6653621581656567, + "learning_rate": 1.6635461454457944e-05, + "loss": 0.9586, + "step": 4740 + }, + { + "epoch": 0.29104637956966145, + "grad_norm": 0.6645261870412199, + "learning_rate": 1.6633973768526413e-05, + "loss": 0.9501, + "step": 4741 + }, + { + "epoch": 0.29110776880812794, + "grad_norm": 0.6183803071054618, + "learning_rate": 1.6632485820318422e-05, + "loss": 0.9043, + "step": 4742 + }, + { + "epoch": 0.29116915804659443, + "grad_norm": 0.6313039091649952, + "learning_rate": 1.663099760989279e-05, + "loss": 0.9561, + "step": 4743 + }, + { + "epoch": 0.2912305472850609, + "grad_norm": 0.6300738566856107, + "learning_rate": 1.6629509137308363e-05, + "loss": 0.9465, + "step": 4744 + }, + { + "epoch": 0.2912919365235274, + "grad_norm": 0.6493031702598537, + "learning_rate": 1.662802040262398e-05, + "loss": 0.9623, + "step": 4745 + }, + { + "epoch": 0.2913533257619939, + "grad_norm": 0.6882861284178736, + "learning_rate": 1.66265314058985e-05, + "loss": 0.9767, + "step": 4746 + }, + { + "epoch": 0.2914147150004604, + "grad_norm": 0.694536399430722, + "learning_rate": 1.662504214719079e-05, + "loss": 0.9261, + "step": 4747 + }, + { + "epoch": 0.2914761042389269, + "grad_norm": 0.6674102515853291, + "learning_rate": 1.6623552626559737e-05, + "loss": 0.951, + "step": 4748 + }, + { + "epoch": 0.29153749347739344, + "grad_norm": 0.6344389583520574, + "learning_rate": 1.662206284406422e-05, + "loss": 0.9279, + "step": 4749 + }, + { + "epoch": 0.29159888271585993, + "grad_norm": 0.735178430289922, + "learning_rate": 1.662057279976314e-05, + "loss": 0.9556, + "step": 4750 + }, + { + "epoch": 0.2916602719543264, + "grad_norm": 0.6625805646039629, + "learning_rate": 1.6619082493715412e-05, + "loss": 0.9296, + "step": 4751 + }, + { + "epoch": 0.2917216611927929, + "grad_norm": 0.6375917743762227, + "learning_rate": 1.661759192597995e-05, + "loss": 0.9077, + "step": 4752 + }, + { + "epoch": 0.2917830504312594, + "grad_norm": 0.6211316952282784, + "learning_rate": 1.6616101096615686e-05, + "loss": 0.9175, + "step": 4753 + }, + { + "epoch": 0.2918444396697259, + "grad_norm": 0.630893294689961, + "learning_rate": 1.6614610005681557e-05, + "loss": 0.9382, + "step": 4754 + }, + { + "epoch": 0.2919058289081924, + "grad_norm": 0.6995409717050872, + "learning_rate": 1.661311865323652e-05, + "loss": 0.9285, + "step": 4755 + }, + { + "epoch": 0.2919672181466589, + "grad_norm": 0.6361132320319837, + "learning_rate": 1.6611627039339533e-05, + "loss": 0.9336, + "step": 4756 + }, + { + "epoch": 0.29202860738512537, + "grad_norm": 0.7421829307957434, + "learning_rate": 1.6610135164049568e-05, + "loss": 0.9814, + "step": 4757 + }, + { + "epoch": 0.29208999662359186, + "grad_norm": 0.698052912269993, + "learning_rate": 1.6608643027425605e-05, + "loss": 0.9418, + "step": 4758 + }, + { + "epoch": 0.29215138586205835, + "grad_norm": 0.6939213710039014, + "learning_rate": 1.660715062952664e-05, + "loss": 0.9408, + "step": 4759 + }, + { + "epoch": 0.2922127751005249, + "grad_norm": 0.6451352185651225, + "learning_rate": 1.660565797041167e-05, + "loss": 0.9273, + "step": 4760 + }, + { + "epoch": 0.2922741643389914, + "grad_norm": 0.6477479894018726, + "learning_rate": 1.6604165050139712e-05, + "loss": 0.9074, + "step": 4761 + }, + { + "epoch": 0.2923355535774579, + "grad_norm": 0.6725546754205658, + "learning_rate": 1.6602671868769788e-05, + "loss": 0.9306, + "step": 4762 + }, + { + "epoch": 0.2923969428159244, + "grad_norm": 0.7030198582210345, + "learning_rate": 1.660117842636093e-05, + "loss": 0.9901, + "step": 4763 + }, + { + "epoch": 0.29245833205439087, + "grad_norm": 0.7187738578846721, + "learning_rate": 1.6599684722972188e-05, + "loss": 0.977, + "step": 4764 + }, + { + "epoch": 0.29251972129285736, + "grad_norm": 0.7050510739915, + "learning_rate": 1.6598190758662605e-05, + "loss": 0.9347, + "step": 4765 + }, + { + "epoch": 0.29258111053132385, + "grad_norm": 0.6843957295381976, + "learning_rate": 1.659669653349126e-05, + "loss": 0.9857, + "step": 4766 + }, + { + "epoch": 0.29264249976979034, + "grad_norm": 0.7081867828772627, + "learning_rate": 1.6595202047517212e-05, + "loss": 0.9651, + "step": 4767 + }, + { + "epoch": 0.29270388900825683, + "grad_norm": 0.7161318409166679, + "learning_rate": 1.659370730079956e-05, + "loss": 0.9694, + "step": 4768 + }, + { + "epoch": 0.2927652782467233, + "grad_norm": 0.7216333570949831, + "learning_rate": 1.6592212293397386e-05, + "loss": 0.9999, + "step": 4769 + }, + { + "epoch": 0.2928266674851899, + "grad_norm": 0.6339077125167631, + "learning_rate": 1.6590717025369802e-05, + "loss": 0.9134, + "step": 4770 + }, + { + "epoch": 0.29288805672365636, + "grad_norm": 0.6533072756121949, + "learning_rate": 1.658922149677593e-05, + "loss": 0.9636, + "step": 4771 + }, + { + "epoch": 0.29294944596212286, + "grad_norm": 0.6314885479120198, + "learning_rate": 1.6587725707674888e-05, + "loss": 0.9165, + "step": 4772 + }, + { + "epoch": 0.29301083520058935, + "grad_norm": 0.6533854328748896, + "learning_rate": 1.6586229658125816e-05, + "loss": 0.9457, + "step": 4773 + }, + { + "epoch": 0.29307222443905584, + "grad_norm": 0.8919193047916821, + "learning_rate": 1.658473334818786e-05, + "loss": 0.7336, + "step": 4774 + }, + { + "epoch": 0.29313361367752233, + "grad_norm": 0.6232289477656172, + "learning_rate": 1.6583236777920174e-05, + "loss": 0.8944, + "step": 4775 + }, + { + "epoch": 0.2931950029159888, + "grad_norm": 0.6530904164680518, + "learning_rate": 1.658173994738193e-05, + "loss": 0.9347, + "step": 4776 + }, + { + "epoch": 0.2932563921544553, + "grad_norm": 0.674784633634674, + "learning_rate": 1.6580242856632306e-05, + "loss": 0.911, + "step": 4777 + }, + { + "epoch": 0.2933177813929218, + "grad_norm": 0.6797283262631173, + "learning_rate": 1.657874550573049e-05, + "loss": 0.9103, + "step": 4778 + }, + { + "epoch": 0.2933791706313883, + "grad_norm": 0.679612918312619, + "learning_rate": 1.6577247894735674e-05, + "loss": 0.9558, + "step": 4779 + }, + { + "epoch": 0.2934405598698548, + "grad_norm": 0.6685079751968006, + "learning_rate": 1.6575750023707075e-05, + "loss": 0.989, + "step": 4780 + }, + { + "epoch": 0.29350194910832134, + "grad_norm": 0.7013191342955464, + "learning_rate": 1.6574251892703904e-05, + "loss": 0.95, + "step": 4781 + }, + { + "epoch": 0.2935633383467878, + "grad_norm": 0.7864613398438146, + "learning_rate": 1.6572753501785397e-05, + "loss": 0.7334, + "step": 4782 + }, + { + "epoch": 0.2936247275852543, + "grad_norm": 0.7138852069492438, + "learning_rate": 1.657125485101079e-05, + "loss": 0.9353, + "step": 4783 + }, + { + "epoch": 0.2936861168237208, + "grad_norm": 0.7789806928703494, + "learning_rate": 1.6569755940439335e-05, + "loss": 0.9565, + "step": 4784 + }, + { + "epoch": 0.2937475060621873, + "grad_norm": 0.6752811664648835, + "learning_rate": 1.6568256770130285e-05, + "loss": 0.9408, + "step": 4785 + }, + { + "epoch": 0.2938088953006538, + "grad_norm": 0.6855092453793953, + "learning_rate": 1.656675734014292e-05, + "loss": 0.9463, + "step": 4786 + }, + { + "epoch": 0.2938702845391203, + "grad_norm": 0.6713852438712088, + "learning_rate": 1.6565257650536514e-05, + "loss": 0.9487, + "step": 4787 + }, + { + "epoch": 0.2939316737775868, + "grad_norm": 0.6815271956101036, + "learning_rate": 1.656375770137036e-05, + "loss": 0.9775, + "step": 4788 + }, + { + "epoch": 0.29399306301605327, + "grad_norm": 0.625155853617614, + "learning_rate": 1.6562257492703756e-05, + "loss": 0.8672, + "step": 4789 + }, + { + "epoch": 0.29405445225451976, + "grad_norm": 0.6570856224834871, + "learning_rate": 1.6560757024596022e-05, + "loss": 0.9407, + "step": 4790 + }, + { + "epoch": 0.29411584149298625, + "grad_norm": 0.6735585634928238, + "learning_rate": 1.6559256297106468e-05, + "loss": 0.897, + "step": 4791 + }, + { + "epoch": 0.2941772307314528, + "grad_norm": 0.6042100815763854, + "learning_rate": 1.6557755310294433e-05, + "loss": 0.9266, + "step": 4792 + }, + { + "epoch": 0.2942386199699193, + "grad_norm": 0.6947977559193566, + "learning_rate": 1.6556254064219257e-05, + "loss": 1.0113, + "step": 4793 + }, + { + "epoch": 0.2943000092083858, + "grad_norm": 0.716045100467387, + "learning_rate": 1.6554752558940292e-05, + "loss": 0.9582, + "step": 4794 + }, + { + "epoch": 0.2943613984468523, + "grad_norm": 0.601418900122419, + "learning_rate": 1.6553250794516904e-05, + "loss": 0.9389, + "step": 4795 + }, + { + "epoch": 0.29442278768531877, + "grad_norm": 0.6858879321963159, + "learning_rate": 1.655174877100846e-05, + "loss": 0.9691, + "step": 4796 + }, + { + "epoch": 0.29448417692378526, + "grad_norm": 0.6369769504377527, + "learning_rate": 1.6550246488474345e-05, + "loss": 0.9318, + "step": 4797 + }, + { + "epoch": 0.29454556616225175, + "grad_norm": 0.6241958975959199, + "learning_rate": 1.654874394697396e-05, + "loss": 0.9369, + "step": 4798 + }, + { + "epoch": 0.29460695540071824, + "grad_norm": 0.663387421581193, + "learning_rate": 1.6547241146566694e-05, + "loss": 0.9625, + "step": 4799 + }, + { + "epoch": 0.29466834463918473, + "grad_norm": 0.6643044735396753, + "learning_rate": 1.654573808731197e-05, + "loss": 0.9691, + "step": 4800 + }, + { + "epoch": 0.2947297338776512, + "grad_norm": 0.6560509517713466, + "learning_rate": 1.654423476926921e-05, + "loss": 0.9268, + "step": 4801 + }, + { + "epoch": 0.29479112311611777, + "grad_norm": 0.7402799103857856, + "learning_rate": 1.6542731192497848e-05, + "loss": 0.9595, + "step": 4802 + }, + { + "epoch": 0.29485251235458426, + "grad_norm": 0.6622779870308171, + "learning_rate": 1.654122735705733e-05, + "loss": 0.9389, + "step": 4803 + }, + { + "epoch": 0.29491390159305075, + "grad_norm": 0.5898138831530406, + "learning_rate": 1.653972326300711e-05, + "loss": 0.9373, + "step": 4804 + }, + { + "epoch": 0.29497529083151725, + "grad_norm": 0.6697561879637225, + "learning_rate": 1.6538218910406654e-05, + "loss": 0.9528, + "step": 4805 + }, + { + "epoch": 0.29503668006998374, + "grad_norm": 0.7015065709689703, + "learning_rate": 1.6536714299315435e-05, + "loss": 0.9912, + "step": 4806 + }, + { + "epoch": 0.29509806930845023, + "grad_norm": 0.6938961140195453, + "learning_rate": 1.653520942979294e-05, + "loss": 0.9749, + "step": 4807 + }, + { + "epoch": 0.2951594585469167, + "grad_norm": 0.6996053243924718, + "learning_rate": 1.6533704301898658e-05, + "loss": 1.0121, + "step": 4808 + }, + { + "epoch": 0.2952208477853832, + "grad_norm": 0.5479230548076985, + "learning_rate": 1.6532198915692105e-05, + "loss": 0.9145, + "step": 4809 + }, + { + "epoch": 0.2952822370238497, + "grad_norm": 0.6961084366193291, + "learning_rate": 1.6530693271232792e-05, + "loss": 0.9467, + "step": 4810 + }, + { + "epoch": 0.2953436262623162, + "grad_norm": 0.6903545769265692, + "learning_rate": 1.6529187368580246e-05, + "loss": 0.9762, + "step": 4811 + }, + { + "epoch": 0.2954050155007827, + "grad_norm": 0.6611935725630346, + "learning_rate": 1.6527681207794e-05, + "loss": 0.9433, + "step": 4812 + }, + { + "epoch": 0.29546640473924923, + "grad_norm": 0.6742161951016546, + "learning_rate": 1.6526174788933606e-05, + "loss": 0.9829, + "step": 4813 + }, + { + "epoch": 0.2955277939777157, + "grad_norm": 0.6528039327029278, + "learning_rate": 1.6524668112058617e-05, + "loss": 0.9303, + "step": 4814 + }, + { + "epoch": 0.2955891832161822, + "grad_norm": 0.6953799802953926, + "learning_rate": 1.6523161177228598e-05, + "loss": 0.9361, + "step": 4815 + }, + { + "epoch": 0.2956505724546487, + "grad_norm": 0.6282172404692632, + "learning_rate": 1.6521653984503135e-05, + "loss": 0.9244, + "step": 4816 + }, + { + "epoch": 0.2957119616931152, + "grad_norm": 0.7534504855794563, + "learning_rate": 1.6520146533941805e-05, + "loss": 0.9533, + "step": 4817 + }, + { + "epoch": 0.2957733509315817, + "grad_norm": 0.6555394337368678, + "learning_rate": 1.6518638825604215e-05, + "loss": 0.9479, + "step": 4818 + }, + { + "epoch": 0.2958347401700482, + "grad_norm": 0.6697189275024056, + "learning_rate": 1.6517130859549967e-05, + "loss": 0.9383, + "step": 4819 + }, + { + "epoch": 0.2958961294085147, + "grad_norm": 0.7131985338992254, + "learning_rate": 1.6515622635838677e-05, + "loss": 0.997, + "step": 4820 + }, + { + "epoch": 0.29595751864698117, + "grad_norm": 0.6366652740690397, + "learning_rate": 1.6514114154529977e-05, + "loss": 0.9051, + "step": 4821 + }, + { + "epoch": 0.29601890788544766, + "grad_norm": 0.6512051882939764, + "learning_rate": 1.6512605415683508e-05, + "loss": 0.9606, + "step": 4822 + }, + { + "epoch": 0.2960802971239142, + "grad_norm": 0.6525918439946969, + "learning_rate": 1.651109641935891e-05, + "loss": 0.9346, + "step": 4823 + }, + { + "epoch": 0.2961416863623807, + "grad_norm": 0.7189349956829671, + "learning_rate": 1.650958716561585e-05, + "loss": 0.9441, + "step": 4824 + }, + { + "epoch": 0.2962030756008472, + "grad_norm": 0.7311139374844257, + "learning_rate": 1.6508077654513992e-05, + "loss": 1.0381, + "step": 4825 + }, + { + "epoch": 0.2962644648393137, + "grad_norm": 0.6561811270804863, + "learning_rate": 1.6506567886113016e-05, + "loss": 0.9726, + "step": 4826 + }, + { + "epoch": 0.29632585407778017, + "grad_norm": 0.6343715598482855, + "learning_rate": 1.6505057860472614e-05, + "loss": 0.9494, + "step": 4827 + }, + { + "epoch": 0.29638724331624666, + "grad_norm": 0.6190868604634101, + "learning_rate": 1.6503547577652483e-05, + "loss": 0.9006, + "step": 4828 + }, + { + "epoch": 0.29644863255471315, + "grad_norm": 0.69223780076931, + "learning_rate": 1.6502037037712333e-05, + "loss": 0.9312, + "step": 4829 + }, + { + "epoch": 0.29651002179317965, + "grad_norm": 0.7016890256379813, + "learning_rate": 1.6500526240711883e-05, + "loss": 0.9434, + "step": 4830 + }, + { + "epoch": 0.29657141103164614, + "grad_norm": 0.6679296665782497, + "learning_rate": 1.6499015186710863e-05, + "loss": 0.9808, + "step": 4831 + }, + { + "epoch": 0.29663280027011263, + "grad_norm": 0.6865160305526538, + "learning_rate": 1.6497503875769015e-05, + "loss": 0.9604, + "step": 4832 + }, + { + "epoch": 0.2966941895085791, + "grad_norm": 0.6654368212907187, + "learning_rate": 1.6495992307946086e-05, + "loss": 0.9357, + "step": 4833 + }, + { + "epoch": 0.29675557874704567, + "grad_norm": 0.701796110684718, + "learning_rate": 1.6494480483301836e-05, + "loss": 0.9837, + "step": 4834 + }, + { + "epoch": 0.29681696798551216, + "grad_norm": 0.6838066897955846, + "learning_rate": 1.6492968401896044e-05, + "loss": 0.9626, + "step": 4835 + }, + { + "epoch": 0.29687835722397865, + "grad_norm": 0.679300846469494, + "learning_rate": 1.6491456063788482e-05, + "loss": 0.9217, + "step": 4836 + }, + { + "epoch": 0.29693974646244514, + "grad_norm": 0.6877423470959199, + "learning_rate": 1.648994346903894e-05, + "loss": 0.9132, + "step": 4837 + }, + { + "epoch": 0.29700113570091163, + "grad_norm": 0.656465370444906, + "learning_rate": 1.648843061770722e-05, + "loss": 0.9389, + "step": 4838 + }, + { + "epoch": 0.2970625249393781, + "grad_norm": 0.6814596663167994, + "learning_rate": 1.648691750985314e-05, + "loss": 0.9572, + "step": 4839 + }, + { + "epoch": 0.2971239141778446, + "grad_norm": 0.6578820086361158, + "learning_rate": 1.6485404145536517e-05, + "loss": 0.9485, + "step": 4840 + }, + { + "epoch": 0.2971853034163111, + "grad_norm": 0.731827520799178, + "learning_rate": 1.6483890524817178e-05, + "loss": 1.0226, + "step": 4841 + }, + { + "epoch": 0.2972466926547776, + "grad_norm": 0.742758231564385, + "learning_rate": 1.648237664775497e-05, + "loss": 0.9914, + "step": 4842 + }, + { + "epoch": 0.2973080818932441, + "grad_norm": 0.6800731401623535, + "learning_rate": 1.6480862514409742e-05, + "loss": 0.9548, + "step": 4843 + }, + { + "epoch": 0.29736947113171064, + "grad_norm": 0.6704137864836499, + "learning_rate": 1.6479348124841358e-05, + "loss": 0.9563, + "step": 4844 + }, + { + "epoch": 0.29743086037017713, + "grad_norm": 0.6434701694960067, + "learning_rate": 1.647783347910969e-05, + "loss": 0.9514, + "step": 4845 + }, + { + "epoch": 0.2974922496086436, + "grad_norm": 0.6553259903523467, + "learning_rate": 1.6476318577274617e-05, + "loss": 0.927, + "step": 4846 + }, + { + "epoch": 0.2975536388471101, + "grad_norm": 0.6987584178536962, + "learning_rate": 1.6474803419396033e-05, + "loss": 0.9609, + "step": 4847 + }, + { + "epoch": 0.2976150280855766, + "grad_norm": 0.6310029409745952, + "learning_rate": 1.647328800553384e-05, + "loss": 0.9364, + "step": 4848 + }, + { + "epoch": 0.2976764173240431, + "grad_norm": 0.570218043953627, + "learning_rate": 1.647177233574795e-05, + "loss": 0.8806, + "step": 4849 + }, + { + "epoch": 0.2977378065625096, + "grad_norm": 0.6342376079816868, + "learning_rate": 1.6470256410098286e-05, + "loss": 0.9228, + "step": 4850 + }, + { + "epoch": 0.2977991958009761, + "grad_norm": 0.630927097724428, + "learning_rate": 1.646874022864478e-05, + "loss": 0.8927, + "step": 4851 + }, + { + "epoch": 0.29786058503944257, + "grad_norm": 0.6748879343663693, + "learning_rate": 1.646722379144738e-05, + "loss": 0.9775, + "step": 4852 + }, + { + "epoch": 0.29792197427790906, + "grad_norm": 0.695137250168839, + "learning_rate": 1.6465707098566032e-05, + "loss": 0.9874, + "step": 4853 + }, + { + "epoch": 0.29798336351637555, + "grad_norm": 0.64711703718946, + "learning_rate": 1.64641901500607e-05, + "loss": 0.9375, + "step": 4854 + }, + { + "epoch": 0.2980447527548421, + "grad_norm": 0.6906320265353662, + "learning_rate": 1.6462672945991357e-05, + "loss": 0.9486, + "step": 4855 + }, + { + "epoch": 0.2981061419933086, + "grad_norm": 0.6580391278881085, + "learning_rate": 1.6461155486417992e-05, + "loss": 0.956, + "step": 4856 + }, + { + "epoch": 0.2981675312317751, + "grad_norm": 0.7013643629079408, + "learning_rate": 1.645963777140059e-05, + "loss": 0.9275, + "step": 4857 + }, + { + "epoch": 0.2982289204702416, + "grad_norm": 0.6455559477916452, + "learning_rate": 1.6458119800999162e-05, + "loss": 0.9486, + "step": 4858 + }, + { + "epoch": 0.29829030970870807, + "grad_norm": 0.6514571061604425, + "learning_rate": 1.6456601575273716e-05, + "loss": 0.9428, + "step": 4859 + }, + { + "epoch": 0.29835169894717456, + "grad_norm": 0.6651804130487188, + "learning_rate": 1.6455083094284275e-05, + "loss": 0.9667, + "step": 4860 + }, + { + "epoch": 0.29841308818564105, + "grad_norm": 0.6367635682103715, + "learning_rate": 1.6453564358090876e-05, + "loss": 1.0022, + "step": 4861 + }, + { + "epoch": 0.29847447742410754, + "grad_norm": 0.6548497614809804, + "learning_rate": 1.6452045366753568e-05, + "loss": 1.013, + "step": 4862 + }, + { + "epoch": 0.29853586666257403, + "grad_norm": 0.7342951797941548, + "learning_rate": 1.645052612033239e-05, + "loss": 0.9768, + "step": 4863 + }, + { + "epoch": 0.2985972559010405, + "grad_norm": 0.6501018901208514, + "learning_rate": 1.644900661888742e-05, + "loss": 0.9408, + "step": 4864 + }, + { + "epoch": 0.298658645139507, + "grad_norm": 0.6458876023933356, + "learning_rate": 1.644748686247872e-05, + "loss": 0.9887, + "step": 4865 + }, + { + "epoch": 0.29872003437797356, + "grad_norm": 0.6565608753741198, + "learning_rate": 1.6445966851166392e-05, + "loss": 0.9508, + "step": 4866 + }, + { + "epoch": 0.29878142361644006, + "grad_norm": 0.634907267886848, + "learning_rate": 1.6444446585010512e-05, + "loss": 0.9268, + "step": 4867 + }, + { + "epoch": 0.29884281285490655, + "grad_norm": 0.6331308764934565, + "learning_rate": 1.644292606407119e-05, + "loss": 0.8934, + "step": 4868 + }, + { + "epoch": 0.29890420209337304, + "grad_norm": 0.6653686719901984, + "learning_rate": 1.6441405288408544e-05, + "loss": 0.9135, + "step": 4869 + }, + { + "epoch": 0.29896559133183953, + "grad_norm": 0.6625128062346586, + "learning_rate": 1.6439884258082693e-05, + "loss": 0.9197, + "step": 4870 + }, + { + "epoch": 0.299026980570306, + "grad_norm": 0.7167103760016199, + "learning_rate": 1.6438362973153783e-05, + "loss": 0.9456, + "step": 4871 + }, + { + "epoch": 0.2990883698087725, + "grad_norm": 0.6574256888319979, + "learning_rate": 1.643684143368194e-05, + "loss": 0.9745, + "step": 4872 + }, + { + "epoch": 0.299149759047239, + "grad_norm": 0.7034506495074089, + "learning_rate": 1.6435319639727333e-05, + "loss": 0.9855, + "step": 4873 + }, + { + "epoch": 0.2992111482857055, + "grad_norm": 0.6976188657129656, + "learning_rate": 1.6433797591350123e-05, + "loss": 0.9787, + "step": 4874 + }, + { + "epoch": 0.299272537524172, + "grad_norm": 1.1348854720428894, + "learning_rate": 1.6432275288610478e-05, + "loss": 0.9384, + "step": 4875 + }, + { + "epoch": 0.29933392676263854, + "grad_norm": 0.6557000420917164, + "learning_rate": 1.6430752731568595e-05, + "loss": 0.9264, + "step": 4876 + }, + { + "epoch": 0.299395316001105, + "grad_norm": 0.6161821438773726, + "learning_rate": 1.642922992028466e-05, + "loss": 0.9496, + "step": 4877 + }, + { + "epoch": 0.2994567052395715, + "grad_norm": 0.6964713511723555, + "learning_rate": 1.642770685481888e-05, + "loss": 0.9706, + "step": 4878 + }, + { + "epoch": 0.299518094478038, + "grad_norm": 0.6829973827292836, + "learning_rate": 1.6426183535231472e-05, + "loss": 0.9181, + "step": 4879 + }, + { + "epoch": 0.2995794837165045, + "grad_norm": 0.6331250212914711, + "learning_rate": 1.6424659961582654e-05, + "loss": 0.8923, + "step": 4880 + }, + { + "epoch": 0.299640872954971, + "grad_norm": 0.6191793370408321, + "learning_rate": 1.642313613393267e-05, + "loss": 0.9068, + "step": 4881 + }, + { + "epoch": 0.2997022621934375, + "grad_norm": 0.6818651617077107, + "learning_rate": 1.6421612052341762e-05, + "loss": 0.9573, + "step": 4882 + }, + { + "epoch": 0.299763651431904, + "grad_norm": 0.6387195804143804, + "learning_rate": 1.6420087716870187e-05, + "loss": 0.9198, + "step": 4883 + }, + { + "epoch": 0.29982504067037047, + "grad_norm": 0.7138705421686473, + "learning_rate": 1.6418563127578203e-05, + "loss": 1.0122, + "step": 4884 + }, + { + "epoch": 0.29988642990883696, + "grad_norm": 0.6900312048320913, + "learning_rate": 1.641703828452609e-05, + "loss": 0.9714, + "step": 4885 + }, + { + "epoch": 0.29994781914730345, + "grad_norm": 0.6899272400215066, + "learning_rate": 1.641551318777413e-05, + "loss": 0.9914, + "step": 4886 + }, + { + "epoch": 0.30000920838577, + "grad_norm": 0.6701224270131267, + "learning_rate": 1.641398783738263e-05, + "loss": 0.9165, + "step": 4887 + }, + { + "epoch": 0.3000705976242365, + "grad_norm": 0.6225000414760145, + "learning_rate": 1.641246223341188e-05, + "loss": 0.9216, + "step": 4888 + }, + { + "epoch": 0.300131986862703, + "grad_norm": 0.6831082880670999, + "learning_rate": 1.64109363759222e-05, + "loss": 0.9744, + "step": 4889 + }, + { + "epoch": 0.3001933761011695, + "grad_norm": 0.6335557831837292, + "learning_rate": 1.6409410264973922e-05, + "loss": 0.9356, + "step": 4890 + }, + { + "epoch": 0.30025476533963597, + "grad_norm": 0.6751984105781247, + "learning_rate": 1.6407883900627374e-05, + "loss": 0.9401, + "step": 4891 + }, + { + "epoch": 0.30031615457810246, + "grad_norm": 0.6366158938331916, + "learning_rate": 1.6406357282942904e-05, + "loss": 0.9337, + "step": 4892 + }, + { + "epoch": 0.30037754381656895, + "grad_norm": 0.6963219890226016, + "learning_rate": 1.6404830411980865e-05, + "loss": 0.9314, + "step": 4893 + }, + { + "epoch": 0.30043893305503544, + "grad_norm": 0.6864001887074397, + "learning_rate": 1.640330328780163e-05, + "loss": 0.9856, + "step": 4894 + }, + { + "epoch": 0.30050032229350193, + "grad_norm": 0.643279483798317, + "learning_rate": 1.6401775910465562e-05, + "loss": 0.8769, + "step": 4895 + }, + { + "epoch": 0.3005617115319684, + "grad_norm": 0.7229693917562463, + "learning_rate": 1.6400248280033057e-05, + "loss": 0.9808, + "step": 4896 + }, + { + "epoch": 0.30062310077043497, + "grad_norm": 0.7084231712176995, + "learning_rate": 1.6398720396564506e-05, + "loss": 0.9695, + "step": 4897 + }, + { + "epoch": 0.30068449000890146, + "grad_norm": 0.6561467253086344, + "learning_rate": 1.6397192260120312e-05, + "loss": 0.9117, + "step": 4898 + }, + { + "epoch": 0.30074587924736795, + "grad_norm": 0.7143525101099486, + "learning_rate": 1.63956638707609e-05, + "loss": 0.9573, + "step": 4899 + }, + { + "epoch": 0.30080726848583444, + "grad_norm": 0.6396233437318983, + "learning_rate": 1.6394135228546682e-05, + "loss": 0.8794, + "step": 4900 + }, + { + "epoch": 0.30086865772430094, + "grad_norm": 0.6620649857115037, + "learning_rate": 1.6392606333538104e-05, + "loss": 0.9542, + "step": 4901 + }, + { + "epoch": 0.30093004696276743, + "grad_norm": 0.6778574333792419, + "learning_rate": 1.6391077185795606e-05, + "loss": 0.9066, + "step": 4902 + }, + { + "epoch": 0.3009914362012339, + "grad_norm": 0.6364300592185842, + "learning_rate": 1.6389547785379643e-05, + "loss": 0.9593, + "step": 4903 + }, + { + "epoch": 0.3010528254397004, + "grad_norm": 0.6311825145478775, + "learning_rate": 1.6388018132350686e-05, + "loss": 0.9298, + "step": 4904 + }, + { + "epoch": 0.3011142146781669, + "grad_norm": 0.6524787515174456, + "learning_rate": 1.638648822676921e-05, + "loss": 0.9517, + "step": 4905 + }, + { + "epoch": 0.3011756039166334, + "grad_norm": 0.6992300596615596, + "learning_rate": 1.638495806869569e-05, + "loss": 0.9912, + "step": 4906 + }, + { + "epoch": 0.3012369931550999, + "grad_norm": 0.6195167723197558, + "learning_rate": 1.638342765819063e-05, + "loss": 0.9202, + "step": 4907 + }, + { + "epoch": 0.30129838239356643, + "grad_norm": 0.6423224136153881, + "learning_rate": 1.6381896995314534e-05, + "loss": 0.9477, + "step": 4908 + }, + { + "epoch": 0.3013597716320329, + "grad_norm": 0.6594087855870951, + "learning_rate": 1.6380366080127918e-05, + "loss": 0.916, + "step": 4909 + }, + { + "epoch": 0.3014211608704994, + "grad_norm": 0.6625735957912227, + "learning_rate": 1.637883491269131e-05, + "loss": 0.9722, + "step": 4910 + }, + { + "epoch": 0.3014825501089659, + "grad_norm": 0.6557214887021263, + "learning_rate": 1.6377303493065236e-05, + "loss": 0.9251, + "step": 4911 + }, + { + "epoch": 0.3015439393474324, + "grad_norm": 0.7038326503741632, + "learning_rate": 1.6375771821310248e-05, + "loss": 0.9624, + "step": 4912 + }, + { + "epoch": 0.3016053285858989, + "grad_norm": 0.6572762643176667, + "learning_rate": 1.63742398974869e-05, + "loss": 0.8911, + "step": 4913 + }, + { + "epoch": 0.3016667178243654, + "grad_norm": 0.5988721816926992, + "learning_rate": 1.6372707721655756e-05, + "loss": 0.755, + "step": 4914 + }, + { + "epoch": 0.3017281070628319, + "grad_norm": 0.7262686897877586, + "learning_rate": 1.637117529387739e-05, + "loss": 1.0089, + "step": 4915 + }, + { + "epoch": 0.30178949630129837, + "grad_norm": 0.6884411337284615, + "learning_rate": 1.6369642614212394e-05, + "loss": 0.882, + "step": 4916 + }, + { + "epoch": 0.30185088553976486, + "grad_norm": 0.7580932825478633, + "learning_rate": 1.6368109682721357e-05, + "loss": 1.0207, + "step": 4917 + }, + { + "epoch": 0.30191227477823135, + "grad_norm": 0.766190120624319, + "learning_rate": 1.6366576499464884e-05, + "loss": 0.949, + "step": 4918 + }, + { + "epoch": 0.3019736640166979, + "grad_norm": 0.6774941258680388, + "learning_rate": 1.6365043064503593e-05, + "loss": 0.9692, + "step": 4919 + }, + { + "epoch": 0.3020350532551644, + "grad_norm": 0.6188282832559012, + "learning_rate": 1.6363509377898106e-05, + "loss": 0.9409, + "step": 4920 + }, + { + "epoch": 0.3020964424936309, + "grad_norm": 0.6853243314162003, + "learning_rate": 1.636197543970906e-05, + "loss": 0.9571, + "step": 4921 + }, + { + "epoch": 0.30215783173209737, + "grad_norm": 0.6754290353335978, + "learning_rate": 1.6360441249997094e-05, + "loss": 0.9338, + "step": 4922 + }, + { + "epoch": 0.30221922097056386, + "grad_norm": 0.6691678952865694, + "learning_rate": 1.6358906808822874e-05, + "loss": 0.9474, + "step": 4923 + }, + { + "epoch": 0.30228061020903035, + "grad_norm": 0.5888531912709077, + "learning_rate": 1.6357372116247053e-05, + "loss": 0.9237, + "step": 4924 + }, + { + "epoch": 0.30234199944749685, + "grad_norm": 0.6483350108532373, + "learning_rate": 1.6355837172330315e-05, + "loss": 0.9085, + "step": 4925 + }, + { + "epoch": 0.30240338868596334, + "grad_norm": 0.6948547697864822, + "learning_rate": 1.6354301977133335e-05, + "loss": 0.9313, + "step": 4926 + }, + { + "epoch": 0.30246477792442983, + "grad_norm": 0.6644205497812348, + "learning_rate": 1.6352766530716815e-05, + "loss": 0.9326, + "step": 4927 + }, + { + "epoch": 0.3025261671628963, + "grad_norm": 0.6638982288193082, + "learning_rate": 1.6351230833141457e-05, + "loss": 0.9254, + "step": 4928 + }, + { + "epoch": 0.30258755640136287, + "grad_norm": 0.6425963379760672, + "learning_rate": 1.6349694884467976e-05, + "loss": 0.9093, + "step": 4929 + }, + { + "epoch": 0.30264894563982936, + "grad_norm": 0.6838297933221531, + "learning_rate": 1.6348158684757093e-05, + "loss": 0.9166, + "step": 4930 + }, + { + "epoch": 0.30271033487829585, + "grad_norm": 0.6436104272585041, + "learning_rate": 1.634662223406955e-05, + "loss": 0.7769, + "step": 4931 + }, + { + "epoch": 0.30277172411676234, + "grad_norm": 0.6358478682219909, + "learning_rate": 1.6345085532466082e-05, + "loss": 0.9498, + "step": 4932 + }, + { + "epoch": 0.30283311335522883, + "grad_norm": 0.6581815724967545, + "learning_rate": 1.634354858000745e-05, + "loss": 0.944, + "step": 4933 + }, + { + "epoch": 0.3028945025936953, + "grad_norm": 0.6598729068596672, + "learning_rate": 1.634201137675441e-05, + "loss": 0.9685, + "step": 4934 + }, + { + "epoch": 0.3029558918321618, + "grad_norm": 0.6955150684426041, + "learning_rate": 1.6340473922767745e-05, + "loss": 0.9909, + "step": 4935 + }, + { + "epoch": 0.3030172810706283, + "grad_norm": 0.7170072437523458, + "learning_rate": 1.6338936218108235e-05, + "loss": 0.999, + "step": 4936 + }, + { + "epoch": 0.3030786703090948, + "grad_norm": 0.6370083601869476, + "learning_rate": 1.633739826283667e-05, + "loss": 0.9284, + "step": 4937 + }, + { + "epoch": 0.3031400595475613, + "grad_norm": 0.6528933480918443, + "learning_rate": 1.633586005701386e-05, + "loss": 0.955, + "step": 4938 + }, + { + "epoch": 0.3032014487860278, + "grad_norm": 0.6539378665280503, + "learning_rate": 1.6334321600700612e-05, + "loss": 0.9611, + "step": 4939 + }, + { + "epoch": 0.30326283802449433, + "grad_norm": 0.6856738225693165, + "learning_rate": 1.6332782893957757e-05, + "loss": 1.032, + "step": 4940 + }, + { + "epoch": 0.3033242272629608, + "grad_norm": 0.6837399711479705, + "learning_rate": 1.6331243936846122e-05, + "loss": 0.9844, + "step": 4941 + }, + { + "epoch": 0.3033856165014273, + "grad_norm": 0.6913872788591947, + "learning_rate": 1.632970472942655e-05, + "loss": 0.9483, + "step": 4942 + }, + { + "epoch": 0.3034470057398938, + "grad_norm": 0.6641376989454167, + "learning_rate": 1.63281652717599e-05, + "loss": 0.9542, + "step": 4943 + }, + { + "epoch": 0.3035083949783603, + "grad_norm": 0.7532528736463256, + "learning_rate": 1.632662556390703e-05, + "loss": 0.9418, + "step": 4944 + }, + { + "epoch": 0.3035697842168268, + "grad_norm": 0.6147493690782807, + "learning_rate": 1.6325085605928813e-05, + "loss": 0.8789, + "step": 4945 + }, + { + "epoch": 0.3036311734552933, + "grad_norm": 0.7030569237534325, + "learning_rate": 1.6323545397886134e-05, + "loss": 0.9951, + "step": 4946 + }, + { + "epoch": 0.30369256269375977, + "grad_norm": 0.7530430809492824, + "learning_rate": 1.6322004939839886e-05, + "loss": 0.9843, + "step": 4947 + }, + { + "epoch": 0.30375395193222626, + "grad_norm": 0.66511281774812, + "learning_rate": 1.6320464231850972e-05, + "loss": 0.9338, + "step": 4948 + }, + { + "epoch": 0.30381534117069275, + "grad_norm": 0.7094147638316791, + "learning_rate": 1.6318923273980298e-05, + "loss": 1.0074, + "step": 4949 + }, + { + "epoch": 0.3038767304091593, + "grad_norm": 0.674839681519304, + "learning_rate": 1.6317382066288793e-05, + "loss": 0.924, + "step": 4950 + }, + { + "epoch": 0.3039381196476258, + "grad_norm": 0.6282149032507646, + "learning_rate": 1.631584060883739e-05, + "loss": 0.9826, + "step": 4951 + }, + { + "epoch": 0.3039995088860923, + "grad_norm": 0.6748843327018584, + "learning_rate": 1.631429890168702e-05, + "loss": 0.9653, + "step": 4952 + }, + { + "epoch": 0.3040608981245588, + "grad_norm": 0.646554868347579, + "learning_rate": 1.6312756944898653e-05, + "loss": 0.9305, + "step": 4953 + }, + { + "epoch": 0.30412228736302527, + "grad_norm": 0.6487590856665892, + "learning_rate": 1.6311214738533237e-05, + "loss": 0.9087, + "step": 4954 + }, + { + "epoch": 0.30418367660149176, + "grad_norm": 0.6912934092743358, + "learning_rate": 1.6309672282651744e-05, + "loss": 0.9729, + "step": 4955 + }, + { + "epoch": 0.30424506583995825, + "grad_norm": 0.6250105659989723, + "learning_rate": 1.6308129577315166e-05, + "loss": 0.9288, + "step": 4956 + }, + { + "epoch": 0.30430645507842474, + "grad_norm": 0.6840341265295856, + "learning_rate": 1.6306586622584482e-05, + "loss": 0.961, + "step": 4957 + }, + { + "epoch": 0.30436784431689123, + "grad_norm": 0.5923837749982773, + "learning_rate": 1.6305043418520702e-05, + "loss": 0.7673, + "step": 4958 + }, + { + "epoch": 0.3044292335553577, + "grad_norm": 0.7059898950260042, + "learning_rate": 1.6303499965184832e-05, + "loss": 0.9995, + "step": 4959 + }, + { + "epoch": 0.3044906227938242, + "grad_norm": 0.6362542488098746, + "learning_rate": 1.6301956262637894e-05, + "loss": 0.9667, + "step": 4960 + }, + { + "epoch": 0.30455201203229076, + "grad_norm": 0.6427193093047789, + "learning_rate": 1.6300412310940923e-05, + "loss": 0.9077, + "step": 4961 + }, + { + "epoch": 0.30461340127075726, + "grad_norm": 0.6291682666857615, + "learning_rate": 1.6298868110154954e-05, + "loss": 0.9203, + "step": 4962 + }, + { + "epoch": 0.30467479050922375, + "grad_norm": 0.6390105029857941, + "learning_rate": 1.629732366034104e-05, + "loss": 0.9437, + "step": 4963 + }, + { + "epoch": 0.30473617974769024, + "grad_norm": 0.7105064809145125, + "learning_rate": 1.6295778961560242e-05, + "loss": 0.9728, + "step": 4964 + }, + { + "epoch": 0.30479756898615673, + "grad_norm": 0.7088090828534074, + "learning_rate": 1.629423401387363e-05, + "loss": 0.9434, + "step": 4965 + }, + { + "epoch": 0.3048589582246232, + "grad_norm": 0.6255520920225959, + "learning_rate": 1.6292688817342282e-05, + "loss": 0.8852, + "step": 4966 + }, + { + "epoch": 0.3049203474630897, + "grad_norm": 0.6086202580591069, + "learning_rate": 1.629114337202729e-05, + "loss": 0.9838, + "step": 4967 + }, + { + "epoch": 0.3049817367015562, + "grad_norm": 0.6617944418650217, + "learning_rate": 1.6289597677989754e-05, + "loss": 0.9617, + "step": 4968 + }, + { + "epoch": 0.3050431259400227, + "grad_norm": 0.652950357929811, + "learning_rate": 1.6288051735290782e-05, + "loss": 0.9526, + "step": 4969 + }, + { + "epoch": 0.3051045151784892, + "grad_norm": 0.6775097183566792, + "learning_rate": 1.6286505543991495e-05, + "loss": 0.9505, + "step": 4970 + }, + { + "epoch": 0.3051659044169557, + "grad_norm": 0.6364877702508054, + "learning_rate": 1.628495910415302e-05, + "loss": 0.9305, + "step": 4971 + }, + { + "epoch": 0.3052272936554222, + "grad_norm": 0.665799129254414, + "learning_rate": 1.6283412415836494e-05, + "loss": 0.9053, + "step": 4972 + }, + { + "epoch": 0.3052886828938887, + "grad_norm": 0.6414441833004638, + "learning_rate": 1.6281865479103077e-05, + "loss": 0.9697, + "step": 4973 + }, + { + "epoch": 0.3053500721323552, + "grad_norm": 0.6683427200148507, + "learning_rate": 1.628031829401391e-05, + "loss": 0.9363, + "step": 4974 + }, + { + "epoch": 0.3054114613708217, + "grad_norm": 0.6666984055755992, + "learning_rate": 1.627877086063018e-05, + "loss": 0.9039, + "step": 4975 + }, + { + "epoch": 0.3054728506092882, + "grad_norm": 0.6546427168553898, + "learning_rate": 1.6277223179013055e-05, + "loss": 0.8995, + "step": 4976 + }, + { + "epoch": 0.3055342398477547, + "grad_norm": 0.6437018122967931, + "learning_rate": 1.6275675249223723e-05, + "loss": 0.882, + "step": 4977 + }, + { + "epoch": 0.3055956290862212, + "grad_norm": 0.702811914844754, + "learning_rate": 1.6274127071323384e-05, + "loss": 0.955, + "step": 4978 + }, + { + "epoch": 0.30565701832468767, + "grad_norm": 0.6510086775835322, + "learning_rate": 1.6272578645373244e-05, + "loss": 0.9406, + "step": 4979 + }, + { + "epoch": 0.30571840756315416, + "grad_norm": 0.660489551549102, + "learning_rate": 1.6271029971434528e-05, + "loss": 0.9355, + "step": 4980 + }, + { + "epoch": 0.30577979680162065, + "grad_norm": 0.65976771337993, + "learning_rate": 1.6269481049568448e-05, + "loss": 0.9561, + "step": 4981 + }, + { + "epoch": 0.3058411860400872, + "grad_norm": 0.7032359854613854, + "learning_rate": 1.6267931879836255e-05, + "loss": 0.9507, + "step": 4982 + }, + { + "epoch": 0.3059025752785537, + "grad_norm": 0.7033624706282905, + "learning_rate": 1.6266382462299197e-05, + "loss": 0.9687, + "step": 4983 + }, + { + "epoch": 0.3059639645170202, + "grad_norm": 0.6765441989463256, + "learning_rate": 1.6264832797018516e-05, + "loss": 0.9197, + "step": 4984 + }, + { + "epoch": 0.3060253537554867, + "grad_norm": 0.7313334883169442, + "learning_rate": 1.6263282884055495e-05, + "loss": 0.9278, + "step": 4985 + }, + { + "epoch": 0.30608674299395316, + "grad_norm": 0.657138160518105, + "learning_rate": 1.6261732723471397e-05, + "loss": 0.9328, + "step": 4986 + }, + { + "epoch": 0.30614813223241966, + "grad_norm": 0.7008626533176237, + "learning_rate": 1.6260182315327518e-05, + "loss": 0.941, + "step": 4987 + }, + { + "epoch": 0.30620952147088615, + "grad_norm": 0.6299807500679759, + "learning_rate": 1.6258631659685155e-05, + "loss": 0.9259, + "step": 4988 + }, + { + "epoch": 0.30627091070935264, + "grad_norm": 0.752318680369605, + "learning_rate": 1.62570807566056e-05, + "loss": 0.9918, + "step": 4989 + }, + { + "epoch": 0.30633229994781913, + "grad_norm": 0.6344337569521848, + "learning_rate": 1.6255529606150184e-05, + "loss": 0.8852, + "step": 4990 + }, + { + "epoch": 0.3063936891862856, + "grad_norm": 0.7144510748006311, + "learning_rate": 1.6253978208380222e-05, + "loss": 0.9908, + "step": 4991 + }, + { + "epoch": 0.3064550784247521, + "grad_norm": 0.7048204983383588, + "learning_rate": 1.6252426563357054e-05, + "loss": 1.0008, + "step": 4992 + }, + { + "epoch": 0.30651646766321866, + "grad_norm": 0.6792655193973108, + "learning_rate": 1.6250874671142022e-05, + "loss": 0.9578, + "step": 4993 + }, + { + "epoch": 0.30657785690168515, + "grad_norm": 0.7545062488962929, + "learning_rate": 1.6249322531796484e-05, + "loss": 1.0023, + "step": 4994 + }, + { + "epoch": 0.30663924614015164, + "grad_norm": 0.6840005897133202, + "learning_rate": 1.6247770145381806e-05, + "loss": 0.969, + "step": 4995 + }, + { + "epoch": 0.30670063537861814, + "grad_norm": 0.7176165819268661, + "learning_rate": 1.624621751195935e-05, + "loss": 0.9422, + "step": 4996 + }, + { + "epoch": 0.3067620246170846, + "grad_norm": 0.736228609967829, + "learning_rate": 1.6244664631590516e-05, + "loss": 0.9743, + "step": 4997 + }, + { + "epoch": 0.3068234138555511, + "grad_norm": 0.6839861986669714, + "learning_rate": 1.624311150433669e-05, + "loss": 0.9749, + "step": 4998 + }, + { + "epoch": 0.3068848030940176, + "grad_norm": 0.705990400223137, + "learning_rate": 1.6241558130259273e-05, + "loss": 0.93, + "step": 4999 + }, + { + "epoch": 0.3069461923324841, + "grad_norm": 0.6509760043355768, + "learning_rate": 1.624000450941968e-05, + "loss": 0.914, + "step": 5000 + }, + { + "epoch": 0.3070075815709506, + "grad_norm": 0.6429720765633171, + "learning_rate": 1.6238450641879335e-05, + "loss": 0.9408, + "step": 5001 + }, + { + "epoch": 0.3070689708094171, + "grad_norm": 0.7119757760253745, + "learning_rate": 1.6236896527699676e-05, + "loss": 0.9572, + "step": 5002 + }, + { + "epoch": 0.30713036004788363, + "grad_norm": 0.6773955223727003, + "learning_rate": 1.6235342166942135e-05, + "loss": 0.9417, + "step": 5003 + }, + { + "epoch": 0.3071917492863501, + "grad_norm": 0.7544623942281842, + "learning_rate": 1.623378755966817e-05, + "loss": 0.9863, + "step": 5004 + }, + { + "epoch": 0.3072531385248166, + "grad_norm": 0.6382261987189911, + "learning_rate": 1.623223270593924e-05, + "loss": 0.9673, + "step": 5005 + }, + { + "epoch": 0.3073145277632831, + "grad_norm": 0.6943309505145222, + "learning_rate": 1.6230677605816826e-05, + "loss": 0.9381, + "step": 5006 + }, + { + "epoch": 0.3073759170017496, + "grad_norm": 0.6965987773927587, + "learning_rate": 1.6229122259362397e-05, + "loss": 0.935, + "step": 5007 + }, + { + "epoch": 0.3074373062402161, + "grad_norm": 0.5973218410701113, + "learning_rate": 1.6227566666637448e-05, + "loss": 0.9219, + "step": 5008 + }, + { + "epoch": 0.3074986954786826, + "grad_norm": 0.6448338857931938, + "learning_rate": 1.6226010827703483e-05, + "loss": 0.9632, + "step": 5009 + }, + { + "epoch": 0.3075600847171491, + "grad_norm": 0.7361225831289311, + "learning_rate": 1.6224454742622012e-05, + "loss": 0.9505, + "step": 5010 + }, + { + "epoch": 0.30762147395561557, + "grad_norm": 0.6921903515017599, + "learning_rate": 1.622289841145455e-05, + "loss": 0.9497, + "step": 5011 + }, + { + "epoch": 0.30768286319408206, + "grad_norm": 0.710411400240141, + "learning_rate": 1.6221341834262637e-05, + "loss": 0.9814, + "step": 5012 + }, + { + "epoch": 0.30774425243254855, + "grad_norm": 0.6792715501909535, + "learning_rate": 1.6219785011107806e-05, + "loss": 0.9127, + "step": 5013 + }, + { + "epoch": 0.3078056416710151, + "grad_norm": 0.6724021335764633, + "learning_rate": 1.6218227942051606e-05, + "loss": 0.9045, + "step": 5014 + }, + { + "epoch": 0.3078670309094816, + "grad_norm": 0.6476421434112476, + "learning_rate": 1.62166706271556e-05, + "loss": 0.9197, + "step": 5015 + }, + { + "epoch": 0.3079284201479481, + "grad_norm": 0.6600463916202344, + "learning_rate": 1.621511306648135e-05, + "loss": 0.9022, + "step": 5016 + }, + { + "epoch": 0.30798980938641457, + "grad_norm": 0.6307603306935136, + "learning_rate": 1.621355526009045e-05, + "loss": 0.8746, + "step": 5017 + }, + { + "epoch": 0.30805119862488106, + "grad_norm": 0.6716904252414253, + "learning_rate": 1.6211997208044467e-05, + "loss": 0.9653, + "step": 5018 + }, + { + "epoch": 0.30811258786334755, + "grad_norm": 0.7242634646962538, + "learning_rate": 1.621043891040502e-05, + "loss": 0.7766, + "step": 5019 + }, + { + "epoch": 0.30817397710181405, + "grad_norm": 0.6896573225933121, + "learning_rate": 1.6208880367233698e-05, + "loss": 0.9562, + "step": 5020 + }, + { + "epoch": 0.30823536634028054, + "grad_norm": 0.6555215157160964, + "learning_rate": 1.6207321578592134e-05, + "loss": 0.8794, + "step": 5021 + }, + { + "epoch": 0.30829675557874703, + "grad_norm": 0.6632384908449053, + "learning_rate": 1.6205762544541946e-05, + "loss": 0.9584, + "step": 5022 + }, + { + "epoch": 0.3083581448172135, + "grad_norm": 0.6801469248014264, + "learning_rate": 1.620420326514477e-05, + "loss": 0.9528, + "step": 5023 + }, + { + "epoch": 0.30841953405568007, + "grad_norm": 0.6550432276993936, + "learning_rate": 1.6202643740462264e-05, + "loss": 0.9666, + "step": 5024 + }, + { + "epoch": 0.30848092329414656, + "grad_norm": 0.6490847295764434, + "learning_rate": 1.6201083970556074e-05, + "loss": 0.9322, + "step": 5025 + }, + { + "epoch": 0.30854231253261305, + "grad_norm": 0.6901724817346169, + "learning_rate": 1.619952395548787e-05, + "loss": 0.9481, + "step": 5026 + }, + { + "epoch": 0.30860370177107954, + "grad_norm": 0.6235975397351553, + "learning_rate": 1.6197963695319323e-05, + "loss": 0.9601, + "step": 5027 + }, + { + "epoch": 0.30866509100954603, + "grad_norm": 0.6938889486193254, + "learning_rate": 1.6196403190112128e-05, + "loss": 0.9739, + "step": 5028 + }, + { + "epoch": 0.3087264802480125, + "grad_norm": 0.694305168659476, + "learning_rate": 1.619484243992797e-05, + "loss": 0.9926, + "step": 5029 + }, + { + "epoch": 0.308787869486479, + "grad_norm": 0.7385472037372391, + "learning_rate": 1.6193281444828555e-05, + "loss": 0.9983, + "step": 5030 + }, + { + "epoch": 0.3088492587249455, + "grad_norm": 0.6506536903272212, + "learning_rate": 1.6191720204875604e-05, + "loss": 0.7426, + "step": 5031 + }, + { + "epoch": 0.308910647963412, + "grad_norm": 0.7030356165384549, + "learning_rate": 1.619015872013084e-05, + "loss": 0.9557, + "step": 5032 + }, + { + "epoch": 0.3089720372018785, + "grad_norm": 0.6686159680525449, + "learning_rate": 1.618859699065599e-05, + "loss": 0.9847, + "step": 5033 + }, + { + "epoch": 0.309033426440345, + "grad_norm": 0.7257889345585704, + "learning_rate": 1.6187035016512807e-05, + "loss": 0.9474, + "step": 5034 + }, + { + "epoch": 0.30909481567881153, + "grad_norm": 0.6762386214568354, + "learning_rate": 1.6185472797763036e-05, + "loss": 0.9367, + "step": 5035 + }, + { + "epoch": 0.309156204917278, + "grad_norm": 0.6596723399801218, + "learning_rate": 1.6183910334468445e-05, + "loss": 0.9056, + "step": 5036 + }, + { + "epoch": 0.3092175941557445, + "grad_norm": 0.6428468265910767, + "learning_rate": 1.6182347626690802e-05, + "loss": 0.9724, + "step": 5037 + }, + { + "epoch": 0.309278983394211, + "grad_norm": 0.6857477274647056, + "learning_rate": 1.6180784674491894e-05, + "loss": 0.9573, + "step": 5038 + }, + { + "epoch": 0.3093403726326775, + "grad_norm": 0.6532722015009567, + "learning_rate": 1.617922147793351e-05, + "loss": 0.9063, + "step": 5039 + }, + { + "epoch": 0.309401761871144, + "grad_norm": 0.6360872085367888, + "learning_rate": 1.6177658037077452e-05, + "loss": 0.9112, + "step": 5040 + }, + { + "epoch": 0.3094631511096105, + "grad_norm": 0.634761419033819, + "learning_rate": 1.6176094351985527e-05, + "loss": 0.9256, + "step": 5041 + }, + { + "epoch": 0.30952454034807697, + "grad_norm": 1.7041738623994869, + "learning_rate": 1.617453042271957e-05, + "loss": 0.9671, + "step": 5042 + }, + { + "epoch": 0.30958592958654346, + "grad_norm": 0.679643191958788, + "learning_rate": 1.6172966249341393e-05, + "loss": 0.9246, + "step": 5043 + }, + { + "epoch": 0.30964731882500995, + "grad_norm": 0.6007101783083573, + "learning_rate": 1.617140183191285e-05, + "loss": 0.9205, + "step": 5044 + }, + { + "epoch": 0.30970870806347645, + "grad_norm": 0.6620429936567992, + "learning_rate": 1.6169837170495782e-05, + "loss": 0.9605, + "step": 5045 + }, + { + "epoch": 0.309770097301943, + "grad_norm": 0.668396785566694, + "learning_rate": 1.6168272265152052e-05, + "loss": 0.9395, + "step": 5046 + }, + { + "epoch": 0.3098314865404095, + "grad_norm": 0.6519394296216723, + "learning_rate": 1.616670711594353e-05, + "loss": 0.9496, + "step": 5047 + }, + { + "epoch": 0.309892875778876, + "grad_norm": 0.6964007492769771, + "learning_rate": 1.6165141722932095e-05, + "loss": 0.9683, + "step": 5048 + }, + { + "epoch": 0.30995426501734247, + "grad_norm": 0.667484063660302, + "learning_rate": 1.6163576086179636e-05, + "loss": 0.9196, + "step": 5049 + }, + { + "epoch": 0.31001565425580896, + "grad_norm": 0.6711975767197647, + "learning_rate": 1.6162010205748046e-05, + "loss": 0.9199, + "step": 5050 + }, + { + "epoch": 0.31007704349427545, + "grad_norm": 0.5915135961516911, + "learning_rate": 1.6160444081699237e-05, + "loss": 0.9097, + "step": 5051 + }, + { + "epoch": 0.31013843273274194, + "grad_norm": 0.6566499472862894, + "learning_rate": 1.6158877714095127e-05, + "loss": 0.9588, + "step": 5052 + }, + { + "epoch": 0.31019982197120843, + "grad_norm": 0.6355059646835891, + "learning_rate": 1.6157311102997636e-05, + "loss": 0.9107, + "step": 5053 + }, + { + "epoch": 0.3102612112096749, + "grad_norm": 0.7101835471805662, + "learning_rate": 1.6155744248468708e-05, + "loss": 0.9427, + "step": 5054 + }, + { + "epoch": 0.3103226004481414, + "grad_norm": 0.6604793022614039, + "learning_rate": 1.6154177150570287e-05, + "loss": 0.9327, + "step": 5055 + }, + { + "epoch": 0.31038398968660796, + "grad_norm": 0.740162363444149, + "learning_rate": 1.615260980936433e-05, + "loss": 0.9601, + "step": 5056 + }, + { + "epoch": 0.31044537892507446, + "grad_norm": 0.6667029083559846, + "learning_rate": 1.6151042224912797e-05, + "loss": 0.9427, + "step": 5057 + }, + { + "epoch": 0.31050676816354095, + "grad_norm": 0.6867698841387482, + "learning_rate": 1.614947439727767e-05, + "loss": 0.8996, + "step": 5058 + }, + { + "epoch": 0.31056815740200744, + "grad_norm": 0.6855582095754665, + "learning_rate": 1.614790632652093e-05, + "loss": 0.9657, + "step": 5059 + }, + { + "epoch": 0.31062954664047393, + "grad_norm": 0.6854892034206193, + "learning_rate": 1.614633801270457e-05, + "loss": 0.9182, + "step": 5060 + }, + { + "epoch": 0.3106909358789404, + "grad_norm": 0.7763926269537572, + "learning_rate": 1.6144769455890595e-05, + "loss": 0.9698, + "step": 5061 + }, + { + "epoch": 0.3107523251174069, + "grad_norm": 0.6755456076222024, + "learning_rate": 1.614320065614102e-05, + "loss": 0.9255, + "step": 5062 + }, + { + "epoch": 0.3108137143558734, + "grad_norm": 0.7328637133989723, + "learning_rate": 1.614163161351787e-05, + "loss": 0.9347, + "step": 5063 + }, + { + "epoch": 0.3108751035943399, + "grad_norm": 0.6740147521183807, + "learning_rate": 1.614006232808317e-05, + "loss": 0.9203, + "step": 5064 + }, + { + "epoch": 0.3109364928328064, + "grad_norm": 0.6548913907147724, + "learning_rate": 1.613849279989897e-05, + "loss": 0.9174, + "step": 5065 + }, + { + "epoch": 0.3109978820712729, + "grad_norm": 0.6105973296064144, + "learning_rate": 1.6136923029027315e-05, + "loss": 0.932, + "step": 5066 + }, + { + "epoch": 0.3110592713097394, + "grad_norm": 0.6677429531376274, + "learning_rate": 1.6135353015530274e-05, + "loss": 0.9897, + "step": 5067 + }, + { + "epoch": 0.3111206605482059, + "grad_norm": 0.6860417830083861, + "learning_rate": 1.6133782759469912e-05, + "loss": 0.972, + "step": 5068 + }, + { + "epoch": 0.3111820497866724, + "grad_norm": 0.6487659031752687, + "learning_rate": 1.613221226090831e-05, + "loss": 0.9324, + "step": 5069 + }, + { + "epoch": 0.3112434390251389, + "grad_norm": 0.7062637010439967, + "learning_rate": 1.6130641519907562e-05, + "loss": 0.983, + "step": 5070 + }, + { + "epoch": 0.3113048282636054, + "grad_norm": 0.6503173418595175, + "learning_rate": 1.6129070536529767e-05, + "loss": 0.8963, + "step": 5071 + }, + { + "epoch": 0.3113662175020719, + "grad_norm": 0.6162332942304839, + "learning_rate": 1.612749931083703e-05, + "loss": 0.9607, + "step": 5072 + }, + { + "epoch": 0.3114276067405384, + "grad_norm": 0.6789719842541707, + "learning_rate": 1.6125927842891476e-05, + "loss": 0.9545, + "step": 5073 + }, + { + "epoch": 0.31148899597900487, + "grad_norm": 0.6601118069406514, + "learning_rate": 1.612435613275523e-05, + "loss": 0.9681, + "step": 5074 + }, + { + "epoch": 0.31155038521747136, + "grad_norm": 0.6393375267514142, + "learning_rate": 1.612278418049043e-05, + "loss": 0.8905, + "step": 5075 + }, + { + "epoch": 0.31161177445593785, + "grad_norm": 0.6411708091788293, + "learning_rate": 1.6121211986159228e-05, + "loss": 0.9646, + "step": 5076 + }, + { + "epoch": 0.3116731636944044, + "grad_norm": 0.5982416349115852, + "learning_rate": 1.611963954982377e-05, + "loss": 0.9308, + "step": 5077 + }, + { + "epoch": 0.3117345529328709, + "grad_norm": 0.6350036596749116, + "learning_rate": 1.6118066871546238e-05, + "loss": 0.9457, + "step": 5078 + }, + { + "epoch": 0.3117959421713374, + "grad_norm": 0.6721178010539632, + "learning_rate": 1.6116493951388794e-05, + "loss": 0.9427, + "step": 5079 + }, + { + "epoch": 0.3118573314098039, + "grad_norm": 0.7213436247094591, + "learning_rate": 1.6114920789413635e-05, + "loss": 0.9231, + "step": 5080 + }, + { + "epoch": 0.31191872064827036, + "grad_norm": 0.6393859293102114, + "learning_rate": 1.6113347385682953e-05, + "loss": 0.9629, + "step": 5081 + }, + { + "epoch": 0.31198010988673686, + "grad_norm": 0.585725055599223, + "learning_rate": 1.611177374025895e-05, + "loss": 0.9081, + "step": 5082 + }, + { + "epoch": 0.31204149912520335, + "grad_norm": 0.6260066587675877, + "learning_rate": 1.6110199853203844e-05, + "loss": 0.9159, + "step": 5083 + }, + { + "epoch": 0.31210288836366984, + "grad_norm": 0.6611443257021095, + "learning_rate": 1.610862572457986e-05, + "loss": 0.9542, + "step": 5084 + }, + { + "epoch": 0.31216427760213633, + "grad_norm": 0.7176702435849025, + "learning_rate": 1.6107051354449227e-05, + "loss": 0.9215, + "step": 5085 + }, + { + "epoch": 0.3122256668406028, + "grad_norm": 0.6360744881814414, + "learning_rate": 1.610547674287419e-05, + "loss": 0.9646, + "step": 5086 + }, + { + "epoch": 0.3122870560790693, + "grad_norm": 0.7632728366039974, + "learning_rate": 1.6103901889917005e-05, + "loss": 1.0116, + "step": 5087 + }, + { + "epoch": 0.31234844531753586, + "grad_norm": 0.6559803582406022, + "learning_rate": 1.6102326795639936e-05, + "loss": 0.9759, + "step": 5088 + }, + { + "epoch": 0.31240983455600235, + "grad_norm": 0.7731377430013621, + "learning_rate": 1.6100751460105244e-05, + "loss": 1.0019, + "step": 5089 + }, + { + "epoch": 0.31247122379446884, + "grad_norm": 0.6737756074950217, + "learning_rate": 1.6099175883375223e-05, + "loss": 0.9174, + "step": 5090 + }, + { + "epoch": 0.31253261303293534, + "grad_norm": 0.6934547950881078, + "learning_rate": 1.6097600065512157e-05, + "loss": 0.9803, + "step": 5091 + }, + { + "epoch": 0.3125940022714018, + "grad_norm": 0.6560014222877707, + "learning_rate": 1.6096024006578348e-05, + "loss": 0.972, + "step": 5092 + }, + { + "epoch": 0.3126553915098683, + "grad_norm": 0.6303164586978276, + "learning_rate": 1.6094447706636106e-05, + "loss": 0.9211, + "step": 5093 + }, + { + "epoch": 0.3127167807483348, + "grad_norm": 0.6684420633792099, + "learning_rate": 1.609287116574775e-05, + "loss": 0.9252, + "step": 5094 + }, + { + "epoch": 0.3127781699868013, + "grad_norm": 0.7041314185347942, + "learning_rate": 1.6091294383975613e-05, + "loss": 0.992, + "step": 5095 + }, + { + "epoch": 0.3128395592252678, + "grad_norm": 0.7171679826522964, + "learning_rate": 1.608971736138203e-05, + "loss": 0.9474, + "step": 5096 + }, + { + "epoch": 0.3129009484637343, + "grad_norm": 0.6927488245146343, + "learning_rate": 1.6088140098029344e-05, + "loss": 0.9435, + "step": 5097 + }, + { + "epoch": 0.3129623377022008, + "grad_norm": 0.6790299773106561, + "learning_rate": 1.6086562593979925e-05, + "loss": 0.9455, + "step": 5098 + }, + { + "epoch": 0.3130237269406673, + "grad_norm": 0.6049201900962984, + "learning_rate": 1.608498484929613e-05, + "loss": 0.9039, + "step": 5099 + }, + { + "epoch": 0.3130851161791338, + "grad_norm": 0.7694871999649516, + "learning_rate": 1.6083406864040338e-05, + "loss": 0.9733, + "step": 5100 + }, + { + "epoch": 0.3131465054176003, + "grad_norm": 0.6611247331778762, + "learning_rate": 1.6081828638274937e-05, + "loss": 0.9183, + "step": 5101 + }, + { + "epoch": 0.3132078946560668, + "grad_norm": 0.6652573619614808, + "learning_rate": 1.6080250172062325e-05, + "loss": 0.9319, + "step": 5102 + }, + { + "epoch": 0.3132692838945333, + "grad_norm": 0.7648411180563911, + "learning_rate": 1.6078671465464903e-05, + "loss": 0.9271, + "step": 5103 + }, + { + "epoch": 0.3133306731329998, + "grad_norm": 0.7024690818094869, + "learning_rate": 1.6077092518545087e-05, + "loss": 0.9746, + "step": 5104 + }, + { + "epoch": 0.3133920623714663, + "grad_norm": 0.6853785187987327, + "learning_rate": 1.60755133313653e-05, + "loss": 0.9426, + "step": 5105 + }, + { + "epoch": 0.31345345160993277, + "grad_norm": 0.6896087671823706, + "learning_rate": 1.607393390398798e-05, + "loss": 0.9393, + "step": 5106 + }, + { + "epoch": 0.31351484084839926, + "grad_norm": 0.6483195528911071, + "learning_rate": 1.6072354236475562e-05, + "loss": 0.9566, + "step": 5107 + }, + { + "epoch": 0.31357623008686575, + "grad_norm": 0.6536409733196842, + "learning_rate": 1.6070774328890507e-05, + "loss": 0.9511, + "step": 5108 + }, + { + "epoch": 0.3136376193253323, + "grad_norm": 0.6669278794650595, + "learning_rate": 1.6069194181295275e-05, + "loss": 0.9498, + "step": 5109 + }, + { + "epoch": 0.3136990085637988, + "grad_norm": 0.7218924586362762, + "learning_rate": 1.6067613793752333e-05, + "loss": 0.9665, + "step": 5110 + }, + { + "epoch": 0.3137603978022653, + "grad_norm": 0.6639062474768159, + "learning_rate": 1.6066033166324167e-05, + "loss": 0.8961, + "step": 5111 + }, + { + "epoch": 0.31382178704073177, + "grad_norm": 0.6310412444564455, + "learning_rate": 1.6064452299073267e-05, + "loss": 0.9235, + "step": 5112 + }, + { + "epoch": 0.31388317627919826, + "grad_norm": 0.6699151565128589, + "learning_rate": 1.6062871192062135e-05, + "loss": 0.9444, + "step": 5113 + }, + { + "epoch": 0.31394456551766475, + "grad_norm": 0.7165925254109069, + "learning_rate": 1.6061289845353276e-05, + "loss": 0.9573, + "step": 5114 + }, + { + "epoch": 0.31400595475613124, + "grad_norm": 0.6836803629820608, + "learning_rate": 1.605970825900921e-05, + "loss": 0.9801, + "step": 5115 + }, + { + "epoch": 0.31406734399459774, + "grad_norm": 0.7051899302704148, + "learning_rate": 1.605812643309247e-05, + "loss": 0.958, + "step": 5116 + }, + { + "epoch": 0.31412873323306423, + "grad_norm": 0.6842148698067152, + "learning_rate": 1.605654436766559e-05, + "loss": 0.9499, + "step": 5117 + }, + { + "epoch": 0.3141901224715307, + "grad_norm": 0.6556330130942613, + "learning_rate": 1.605496206279112e-05, + "loss": 0.9262, + "step": 5118 + }, + { + "epoch": 0.3142515117099972, + "grad_norm": 0.6677441603594595, + "learning_rate": 1.6053379518531612e-05, + "loss": 0.8695, + "step": 5119 + }, + { + "epoch": 0.31431290094846376, + "grad_norm": 0.7122989181027228, + "learning_rate": 1.6051796734949638e-05, + "loss": 0.9247, + "step": 5120 + }, + { + "epoch": 0.31437429018693025, + "grad_norm": 0.6980641430229241, + "learning_rate": 1.6050213712107768e-05, + "loss": 0.9544, + "step": 5121 + }, + { + "epoch": 0.31443567942539674, + "grad_norm": 0.6637086156864356, + "learning_rate": 1.6048630450068598e-05, + "loss": 0.9303, + "step": 5122 + }, + { + "epoch": 0.31449706866386323, + "grad_norm": 0.6253732005880964, + "learning_rate": 1.604704694889471e-05, + "loss": 0.9085, + "step": 5123 + }, + { + "epoch": 0.3145584579023297, + "grad_norm": 0.6793885915597424, + "learning_rate": 1.6045463208648717e-05, + "loss": 0.9729, + "step": 5124 + }, + { + "epoch": 0.3146198471407962, + "grad_norm": 0.7208327315231484, + "learning_rate": 1.604387922939323e-05, + "loss": 0.9523, + "step": 5125 + }, + { + "epoch": 0.3146812363792627, + "grad_norm": 0.6402322241038115, + "learning_rate": 1.604229501119087e-05, + "loss": 0.9178, + "step": 5126 + }, + { + "epoch": 0.3147426256177292, + "grad_norm": 0.6254250690016344, + "learning_rate": 1.6040710554104273e-05, + "loss": 0.9044, + "step": 5127 + }, + { + "epoch": 0.3148040148561957, + "grad_norm": 0.6286451590969699, + "learning_rate": 1.603912585819608e-05, + "loss": 0.9337, + "step": 5128 + }, + { + "epoch": 0.3148654040946622, + "grad_norm": 0.707120467016833, + "learning_rate": 1.6037540923528943e-05, + "loss": 0.9786, + "step": 5129 + }, + { + "epoch": 0.31492679333312873, + "grad_norm": 0.6513484872827482, + "learning_rate": 1.603595575016552e-05, + "loss": 0.9157, + "step": 5130 + }, + { + "epoch": 0.3149881825715952, + "grad_norm": 0.6700173534851783, + "learning_rate": 1.6034370338168487e-05, + "loss": 0.9267, + "step": 5131 + }, + { + "epoch": 0.3150495718100617, + "grad_norm": 0.6201079724785892, + "learning_rate": 1.603278468760052e-05, + "loss": 0.9056, + "step": 5132 + }, + { + "epoch": 0.3151109610485282, + "grad_norm": 0.6724455247077332, + "learning_rate": 1.6031198798524307e-05, + "loss": 0.9555, + "step": 5133 + }, + { + "epoch": 0.3151723502869947, + "grad_norm": 0.6921338357145279, + "learning_rate": 1.6029612671002546e-05, + "loss": 0.9451, + "step": 5134 + }, + { + "epoch": 0.3152337395254612, + "grad_norm": 0.7415571079862218, + "learning_rate": 1.602802630509795e-05, + "loss": 1.026, + "step": 5135 + }, + { + "epoch": 0.3152951287639277, + "grad_norm": 0.582810797226988, + "learning_rate": 1.6026439700873234e-05, + "loss": 0.9061, + "step": 5136 + }, + { + "epoch": 0.31535651800239417, + "grad_norm": 0.6408855335316038, + "learning_rate": 1.6024852858391125e-05, + "loss": 0.9111, + "step": 5137 + }, + { + "epoch": 0.31541790724086066, + "grad_norm": 0.6963857320971923, + "learning_rate": 1.6023265777714363e-05, + "loss": 0.9575, + "step": 5138 + }, + { + "epoch": 0.31547929647932715, + "grad_norm": 0.7050626202786482, + "learning_rate": 1.6021678458905686e-05, + "loss": 0.9638, + "step": 5139 + }, + { + "epoch": 0.31554068571779365, + "grad_norm": 0.7561022914360338, + "learning_rate": 1.6020090902027854e-05, + "loss": 0.9829, + "step": 5140 + }, + { + "epoch": 0.3156020749562602, + "grad_norm": 0.6340228924411828, + "learning_rate": 1.601850310714363e-05, + "loss": 0.8996, + "step": 5141 + }, + { + "epoch": 0.3156634641947267, + "grad_norm": 0.7128395441625835, + "learning_rate": 1.6016915074315788e-05, + "loss": 0.9817, + "step": 5142 + }, + { + "epoch": 0.3157248534331932, + "grad_norm": 0.647033929782914, + "learning_rate": 1.6015326803607117e-05, + "loss": 0.9218, + "step": 5143 + }, + { + "epoch": 0.31578624267165967, + "grad_norm": 0.721238367050015, + "learning_rate": 1.6013738295080403e-05, + "loss": 0.9544, + "step": 5144 + }, + { + "epoch": 0.31584763191012616, + "grad_norm": 0.6611442947761722, + "learning_rate": 1.601214954879845e-05, + "loss": 0.9398, + "step": 5145 + }, + { + "epoch": 0.31590902114859265, + "grad_norm": 0.6924108624886407, + "learning_rate": 1.601056056482407e-05, + "loss": 0.9502, + "step": 5146 + }, + { + "epoch": 0.31597041038705914, + "grad_norm": 0.6375970815459788, + "learning_rate": 1.6008971343220084e-05, + "loss": 0.924, + "step": 5147 + }, + { + "epoch": 0.31603179962552563, + "grad_norm": 0.6779383999265025, + "learning_rate": 1.6007381884049324e-05, + "loss": 0.901, + "step": 5148 + }, + { + "epoch": 0.3160931888639921, + "grad_norm": 0.749311526489518, + "learning_rate": 1.6005792187374625e-05, + "loss": 0.9694, + "step": 5149 + }, + { + "epoch": 0.3161545781024586, + "grad_norm": 0.6826337848526088, + "learning_rate": 1.6004202253258844e-05, + "loss": 0.9458, + "step": 5150 + }, + { + "epoch": 0.3162159673409251, + "grad_norm": 0.7495539448199647, + "learning_rate": 1.600261208176483e-05, + "loss": 1.0094, + "step": 5151 + }, + { + "epoch": 0.31627735657939166, + "grad_norm": 0.6892566789624512, + "learning_rate": 1.600102167295546e-05, + "loss": 0.9931, + "step": 5152 + }, + { + "epoch": 0.31633874581785815, + "grad_norm": 0.6948883226068308, + "learning_rate": 1.5999431026893607e-05, + "loss": 0.9178, + "step": 5153 + }, + { + "epoch": 0.31640013505632464, + "grad_norm": 0.7533397834361119, + "learning_rate": 1.599784014364216e-05, + "loss": 0.9382, + "step": 5154 + }, + { + "epoch": 0.31646152429479113, + "grad_norm": 0.6624200496792169, + "learning_rate": 1.599624902326401e-05, + "loss": 0.9409, + "step": 5155 + }, + { + "epoch": 0.3165229135332576, + "grad_norm": 0.6682491379628496, + "learning_rate": 1.5994657665822066e-05, + "loss": 0.9143, + "step": 5156 + }, + { + "epoch": 0.3165843027717241, + "grad_norm": 0.7565049911731898, + "learning_rate": 1.5993066071379244e-05, + "loss": 0.9665, + "step": 5157 + }, + { + "epoch": 0.3166456920101906, + "grad_norm": 0.6892028558040292, + "learning_rate": 1.5991474239998468e-05, + "loss": 0.9355, + "step": 5158 + }, + { + "epoch": 0.3167070812486571, + "grad_norm": 0.6997256018989224, + "learning_rate": 1.598988217174267e-05, + "loss": 0.9556, + "step": 5159 + }, + { + "epoch": 0.3167684704871236, + "grad_norm": 0.6637540515394009, + "learning_rate": 1.5988289866674795e-05, + "loss": 0.9142, + "step": 5160 + }, + { + "epoch": 0.3168298597255901, + "grad_norm": 0.7177082032679395, + "learning_rate": 1.598669732485779e-05, + "loss": 0.9695, + "step": 5161 + }, + { + "epoch": 0.3168912489640566, + "grad_norm": 0.7787458478311885, + "learning_rate": 1.5985104546354623e-05, + "loss": 0.9954, + "step": 5162 + }, + { + "epoch": 0.3169526382025231, + "grad_norm": 0.7685065372476158, + "learning_rate": 1.5983511531228263e-05, + "loss": 0.9913, + "step": 5163 + }, + { + "epoch": 0.3170140274409896, + "grad_norm": 0.6758375465031801, + "learning_rate": 1.598191827954169e-05, + "loss": 0.9248, + "step": 5164 + }, + { + "epoch": 0.3170754166794561, + "grad_norm": 0.6581561892630414, + "learning_rate": 1.5980324791357894e-05, + "loss": 0.9178, + "step": 5165 + }, + { + "epoch": 0.3171368059179226, + "grad_norm": 0.6702677755332443, + "learning_rate": 1.5978731066739872e-05, + "loss": 0.9239, + "step": 5166 + }, + { + "epoch": 0.3171981951563891, + "grad_norm": 0.6699303354278557, + "learning_rate": 1.5977137105750638e-05, + "loss": 0.895, + "step": 5167 + }, + { + "epoch": 0.3172595843948556, + "grad_norm": 0.6770336555792918, + "learning_rate": 1.59755429084532e-05, + "loss": 0.951, + "step": 5168 + }, + { + "epoch": 0.31732097363332207, + "grad_norm": 0.6713134377520629, + "learning_rate": 1.5973948474910595e-05, + "loss": 0.9403, + "step": 5169 + }, + { + "epoch": 0.31738236287178856, + "grad_norm": 0.7100541678907134, + "learning_rate": 1.597235380518586e-05, + "loss": 0.943, + "step": 5170 + }, + { + "epoch": 0.31744375211025505, + "grad_norm": 0.6319656004774666, + "learning_rate": 1.597075889934203e-05, + "loss": 0.9378, + "step": 5171 + }, + { + "epoch": 0.31750514134872154, + "grad_norm": 0.7187863852670945, + "learning_rate": 1.5969163757442176e-05, + "loss": 0.9682, + "step": 5172 + }, + { + "epoch": 0.3175665305871881, + "grad_norm": 0.6824522386131797, + "learning_rate": 1.5967568379549347e-05, + "loss": 0.8611, + "step": 5173 + }, + { + "epoch": 0.3176279198256546, + "grad_norm": 0.6249963258803376, + "learning_rate": 1.596597276572662e-05, + "loss": 0.8562, + "step": 5174 + }, + { + "epoch": 0.3176893090641211, + "grad_norm": 0.7736018230626744, + "learning_rate": 1.5964376916037086e-05, + "loss": 0.9851, + "step": 5175 + }, + { + "epoch": 0.31775069830258756, + "grad_norm": 0.6715102906438775, + "learning_rate": 1.596278083054383e-05, + "loss": 0.9895, + "step": 5176 + }, + { + "epoch": 0.31781208754105406, + "grad_norm": 0.6627241559547115, + "learning_rate": 1.596118450930996e-05, + "loss": 1.0122, + "step": 5177 + }, + { + "epoch": 0.31787347677952055, + "grad_norm": 0.7174126754311936, + "learning_rate": 1.595958795239858e-05, + "loss": 0.9551, + "step": 5178 + }, + { + "epoch": 0.31793486601798704, + "grad_norm": 0.6764592485346496, + "learning_rate": 1.5957991159872818e-05, + "loss": 0.9376, + "step": 5179 + }, + { + "epoch": 0.31799625525645353, + "grad_norm": 0.6396584551544381, + "learning_rate": 1.5956394131795798e-05, + "loss": 0.8887, + "step": 5180 + }, + { + "epoch": 0.31805764449492, + "grad_norm": 0.6281144888476602, + "learning_rate": 1.595479686823066e-05, + "loss": 0.9607, + "step": 5181 + }, + { + "epoch": 0.3181190337333865, + "grad_norm": 0.6549037657237875, + "learning_rate": 1.5953199369240553e-05, + "loss": 0.8965, + "step": 5182 + }, + { + "epoch": 0.31818042297185306, + "grad_norm": 0.6684774173666034, + "learning_rate": 1.5951601634888637e-05, + "loss": 0.9189, + "step": 5183 + }, + { + "epoch": 0.31824181221031955, + "grad_norm": 0.7343659816437298, + "learning_rate": 1.5950003665238077e-05, + "loss": 0.9321, + "step": 5184 + }, + { + "epoch": 0.31830320144878604, + "grad_norm": 0.6756245824122027, + "learning_rate": 1.5948405460352048e-05, + "loss": 0.9438, + "step": 5185 + }, + { + "epoch": 0.31836459068725254, + "grad_norm": 0.6980547604689835, + "learning_rate": 1.5946807020293737e-05, + "loss": 1.0111, + "step": 5186 + }, + { + "epoch": 0.318425979925719, + "grad_norm": 0.6801327769603064, + "learning_rate": 1.594520834512634e-05, + "loss": 0.9395, + "step": 5187 + }, + { + "epoch": 0.3184873691641855, + "grad_norm": 0.6218475425253795, + "learning_rate": 1.5943609434913057e-05, + "loss": 0.9028, + "step": 5188 + }, + { + "epoch": 0.318548758402652, + "grad_norm": 0.7337282695120471, + "learning_rate": 1.5942010289717108e-05, + "loss": 0.9521, + "step": 5189 + }, + { + "epoch": 0.3186101476411185, + "grad_norm": 0.6961980492665053, + "learning_rate": 1.594041090960171e-05, + "loss": 0.9224, + "step": 5190 + }, + { + "epoch": 0.318671536879585, + "grad_norm": 0.7108555167715893, + "learning_rate": 1.5938811294630095e-05, + "loss": 0.9337, + "step": 5191 + }, + { + "epoch": 0.3187329261180515, + "grad_norm": 0.7387977854468132, + "learning_rate": 1.5937211444865513e-05, + "loss": 0.9691, + "step": 5192 + }, + { + "epoch": 0.318794315356518, + "grad_norm": 0.7438106750630585, + "learning_rate": 1.59356113603712e-05, + "loss": 0.9991, + "step": 5193 + }, + { + "epoch": 0.3188557045949845, + "grad_norm": 0.6846379942439822, + "learning_rate": 1.593401104121043e-05, + "loss": 0.8847, + "step": 5194 + }, + { + "epoch": 0.318917093833451, + "grad_norm": 0.6836604680725533, + "learning_rate": 1.5932410487446466e-05, + "loss": 0.922, + "step": 5195 + }, + { + "epoch": 0.3189784830719175, + "grad_norm": 0.7111814809568234, + "learning_rate": 1.5930809699142585e-05, + "loss": 0.7503, + "step": 5196 + }, + { + "epoch": 0.319039872310384, + "grad_norm": 0.6741231092636673, + "learning_rate": 1.5929208676362075e-05, + "loss": 0.9201, + "step": 5197 + }, + { + "epoch": 0.3191012615488505, + "grad_norm": 0.6847635552167712, + "learning_rate": 1.5927607419168232e-05, + "loss": 0.9657, + "step": 5198 + }, + { + "epoch": 0.319162650787317, + "grad_norm": 0.647667115107936, + "learning_rate": 1.592600592762437e-05, + "loss": 0.9001, + "step": 5199 + }, + { + "epoch": 0.3192240400257835, + "grad_norm": 0.652818073956599, + "learning_rate": 1.5924404201793803e-05, + "loss": 0.907, + "step": 5200 + }, + { + "epoch": 0.31928542926424996, + "grad_norm": 0.6706914600966942, + "learning_rate": 1.5922802241739844e-05, + "loss": 0.9429, + "step": 5201 + }, + { + "epoch": 0.31934681850271646, + "grad_norm": 0.7460886637682668, + "learning_rate": 1.592120004752584e-05, + "loss": 0.9172, + "step": 5202 + }, + { + "epoch": 0.31940820774118295, + "grad_norm": 0.8092163931381288, + "learning_rate": 1.5919597619215123e-05, + "loss": 0.9995, + "step": 5203 + }, + { + "epoch": 0.3194695969796495, + "grad_norm": 0.7546223336651657, + "learning_rate": 1.5917994956871056e-05, + "loss": 0.9796, + "step": 5204 + }, + { + "epoch": 0.319530986218116, + "grad_norm": 0.699380755347681, + "learning_rate": 1.5916392060556998e-05, + "loss": 0.9447, + "step": 5205 + }, + { + "epoch": 0.3195923754565825, + "grad_norm": 0.6802140749644725, + "learning_rate": 1.5914788930336316e-05, + "loss": 0.9359, + "step": 5206 + }, + { + "epoch": 0.31965376469504897, + "grad_norm": 0.7175585602730841, + "learning_rate": 1.5913185566272396e-05, + "loss": 0.9343, + "step": 5207 + }, + { + "epoch": 0.31971515393351546, + "grad_norm": 0.625876222793989, + "learning_rate": 1.591158196842862e-05, + "loss": 0.9421, + "step": 5208 + }, + { + "epoch": 0.31977654317198195, + "grad_norm": 0.6668165917951268, + "learning_rate": 1.5909978136868396e-05, + "loss": 0.9055, + "step": 5209 + }, + { + "epoch": 0.31983793241044844, + "grad_norm": 0.6393603415669508, + "learning_rate": 1.5908374071655125e-05, + "loss": 0.9604, + "step": 5210 + }, + { + "epoch": 0.31989932164891494, + "grad_norm": 0.6331521866482436, + "learning_rate": 1.5906769772852228e-05, + "loss": 0.895, + "step": 5211 + }, + { + "epoch": 0.3199607108873814, + "grad_norm": 0.6722607443760066, + "learning_rate": 1.5905165240523133e-05, + "loss": 0.935, + "step": 5212 + }, + { + "epoch": 0.3200221001258479, + "grad_norm": 0.700245467478255, + "learning_rate": 1.590356047473127e-05, + "loss": 0.916, + "step": 5213 + }, + { + "epoch": 0.3200834893643144, + "grad_norm": 0.6598383125605181, + "learning_rate": 1.5901955475540087e-05, + "loss": 0.8993, + "step": 5214 + }, + { + "epoch": 0.32014487860278096, + "grad_norm": 0.6661114861058623, + "learning_rate": 1.5900350243013035e-05, + "loss": 0.9737, + "step": 5215 + }, + { + "epoch": 0.32020626784124745, + "grad_norm": 0.7169673045930921, + "learning_rate": 1.5898744777213584e-05, + "loss": 0.9721, + "step": 5216 + }, + { + "epoch": 0.32026765707971394, + "grad_norm": 0.883052061656227, + "learning_rate": 1.5897139078205204e-05, + "loss": 0.9587, + "step": 5217 + }, + { + "epoch": 0.32032904631818043, + "grad_norm": 0.7059420792513463, + "learning_rate": 1.5895533146051375e-05, + "loss": 0.9589, + "step": 5218 + }, + { + "epoch": 0.3203904355566469, + "grad_norm": 0.6499597802446926, + "learning_rate": 1.589392698081559e-05, + "loss": 0.9665, + "step": 5219 + }, + { + "epoch": 0.3204518247951134, + "grad_norm": 0.7359199246119089, + "learning_rate": 1.5892320582561348e-05, + "loss": 0.9135, + "step": 5220 + }, + { + "epoch": 0.3205132140335799, + "grad_norm": 0.6373351842261301, + "learning_rate": 1.589071395135216e-05, + "loss": 0.9005, + "step": 5221 + }, + { + "epoch": 0.3205746032720464, + "grad_norm": 0.6826359909020826, + "learning_rate": 1.5889107087251542e-05, + "loss": 0.9034, + "step": 5222 + }, + { + "epoch": 0.3206359925105129, + "grad_norm": 0.7139469064448548, + "learning_rate": 1.5887499990323025e-05, + "loss": 0.9365, + "step": 5223 + }, + { + "epoch": 0.3206973817489794, + "grad_norm": 0.6468833152054513, + "learning_rate": 1.588589266063014e-05, + "loss": 0.903, + "step": 5224 + }, + { + "epoch": 0.3207587709874459, + "grad_norm": 0.7252624129768099, + "learning_rate": 1.5884285098236444e-05, + "loss": 0.9653, + "step": 5225 + }, + { + "epoch": 0.3208201602259124, + "grad_norm": 0.7030068267379391, + "learning_rate": 1.5882677303205486e-05, + "loss": 0.946, + "step": 5226 + }, + { + "epoch": 0.3208815494643789, + "grad_norm": 0.6758797862077447, + "learning_rate": 1.588106927560083e-05, + "loss": 0.964, + "step": 5227 + }, + { + "epoch": 0.3209429387028454, + "grad_norm": 0.6867054734661474, + "learning_rate": 1.5879461015486052e-05, + "loss": 0.9069, + "step": 5228 + }, + { + "epoch": 0.3210043279413119, + "grad_norm": 0.7371620477043639, + "learning_rate": 1.5877852522924733e-05, + "loss": 0.9649, + "step": 5229 + }, + { + "epoch": 0.3210657171797784, + "grad_norm": 0.6908318739449242, + "learning_rate": 1.587624379798047e-05, + "loss": 0.9088, + "step": 5230 + }, + { + "epoch": 0.3211271064182449, + "grad_norm": 0.7166606690650369, + "learning_rate": 1.5874634840716858e-05, + "loss": 0.9824, + "step": 5231 + }, + { + "epoch": 0.32118849565671137, + "grad_norm": 0.6598701883568918, + "learning_rate": 1.587302565119751e-05, + "loss": 0.9321, + "step": 5232 + }, + { + "epoch": 0.32124988489517786, + "grad_norm": 0.7079566897132431, + "learning_rate": 1.587141622948605e-05, + "loss": 0.9382, + "step": 5233 + }, + { + "epoch": 0.32131127413364435, + "grad_norm": 0.6747609625759758, + "learning_rate": 1.5869806575646106e-05, + "loss": 0.9001, + "step": 5234 + }, + { + "epoch": 0.32137266337211084, + "grad_norm": 0.6871702007254276, + "learning_rate": 1.5868196689741308e-05, + "loss": 0.9361, + "step": 5235 + }, + { + "epoch": 0.3214340526105774, + "grad_norm": 0.6308111940035489, + "learning_rate": 1.5866586571835314e-05, + "loss": 0.9128, + "step": 5236 + }, + { + "epoch": 0.3214954418490439, + "grad_norm": 0.6994956904676022, + "learning_rate": 1.5864976221991773e-05, + "loss": 0.9336, + "step": 5237 + }, + { + "epoch": 0.3215568310875104, + "grad_norm": 0.6459273958138771, + "learning_rate": 1.586336564027436e-05, + "loss": 0.9275, + "step": 5238 + }, + { + "epoch": 0.32161822032597687, + "grad_norm": 0.6676783278397692, + "learning_rate": 1.5861754826746737e-05, + "loss": 0.9305, + "step": 5239 + }, + { + "epoch": 0.32167960956444336, + "grad_norm": 0.6631915660611346, + "learning_rate": 1.5860143781472596e-05, + "loss": 0.928, + "step": 5240 + }, + { + "epoch": 0.32174099880290985, + "grad_norm": 0.7248840937371396, + "learning_rate": 1.585853250451563e-05, + "loss": 1.01, + "step": 5241 + }, + { + "epoch": 0.32180238804137634, + "grad_norm": 0.6662556950105534, + "learning_rate": 1.5856920995939542e-05, + "loss": 0.9094, + "step": 5242 + }, + { + "epoch": 0.32186377727984283, + "grad_norm": 0.656272685146178, + "learning_rate": 1.585530925580804e-05, + "loss": 0.8755, + "step": 5243 + }, + { + "epoch": 0.3219251665183093, + "grad_norm": 0.6761551736123188, + "learning_rate": 1.5853697284184848e-05, + "loss": 0.911, + "step": 5244 + }, + { + "epoch": 0.3219865557567758, + "grad_norm": 0.670712790754011, + "learning_rate": 1.5852085081133694e-05, + "loss": 0.9183, + "step": 5245 + }, + { + "epoch": 0.3220479449952423, + "grad_norm": 0.6985831076406585, + "learning_rate": 1.585047264671832e-05, + "loss": 0.9306, + "step": 5246 + }, + { + "epoch": 0.32210933423370885, + "grad_norm": 0.6667817971733627, + "learning_rate": 1.5848859981002468e-05, + "loss": 0.9275, + "step": 5247 + }, + { + "epoch": 0.32217072347217535, + "grad_norm": 0.7074408835235325, + "learning_rate": 1.58472470840499e-05, + "loss": 0.9814, + "step": 5248 + }, + { + "epoch": 0.32223211271064184, + "grad_norm": 0.7127426062992511, + "learning_rate": 1.5845633955924382e-05, + "loss": 0.9674, + "step": 5249 + }, + { + "epoch": 0.32229350194910833, + "grad_norm": 0.6401521033902313, + "learning_rate": 1.5844020596689687e-05, + "loss": 0.9205, + "step": 5250 + }, + { + "epoch": 0.3223548911875748, + "grad_norm": 0.6498380812922521, + "learning_rate": 1.584240700640961e-05, + "loss": 0.9327, + "step": 5251 + }, + { + "epoch": 0.3224162804260413, + "grad_norm": 0.6877823467681549, + "learning_rate": 1.5840793185147924e-05, + "loss": 0.9528, + "step": 5252 + }, + { + "epoch": 0.3224776696645078, + "grad_norm": 0.6320324366200627, + "learning_rate": 1.5839179132968453e-05, + "loss": 0.9052, + "step": 5253 + }, + { + "epoch": 0.3225390589029743, + "grad_norm": 0.7226335082389812, + "learning_rate": 1.5837564849934998e-05, + "loss": 0.9834, + "step": 5254 + }, + { + "epoch": 0.3226004481414408, + "grad_norm": 0.6630170110893626, + "learning_rate": 1.5835950336111383e-05, + "loss": 0.931, + "step": 5255 + }, + { + "epoch": 0.3226618373799073, + "grad_norm": 0.6562263574242778, + "learning_rate": 1.583433559156144e-05, + "loss": 0.9168, + "step": 5256 + }, + { + "epoch": 0.3227232266183738, + "grad_norm": 0.691882448601559, + "learning_rate": 1.5832720616349006e-05, + "loss": 0.919, + "step": 5257 + }, + { + "epoch": 0.3227846158568403, + "grad_norm": 0.7140604678539993, + "learning_rate": 1.5831105410537932e-05, + "loss": 0.9627, + "step": 5258 + }, + { + "epoch": 0.3228460050953068, + "grad_norm": 0.7462368996397092, + "learning_rate": 1.5829489974192072e-05, + "loss": 0.9801, + "step": 5259 + }, + { + "epoch": 0.3229073943337733, + "grad_norm": 0.7440597173438356, + "learning_rate": 1.5827874307375294e-05, + "loss": 0.9484, + "step": 5260 + }, + { + "epoch": 0.3229687835722398, + "grad_norm": 0.658273418195567, + "learning_rate": 1.582625841015148e-05, + "loss": 0.892, + "step": 5261 + }, + { + "epoch": 0.3230301728107063, + "grad_norm": 0.648415711092037, + "learning_rate": 1.5824642282584505e-05, + "loss": 0.9161, + "step": 5262 + }, + { + "epoch": 0.3230915620491728, + "grad_norm": 0.6675749641454157, + "learning_rate": 1.5823025924738272e-05, + "loss": 0.9457, + "step": 5263 + }, + { + "epoch": 0.32315295128763927, + "grad_norm": 0.7125303759231456, + "learning_rate": 1.5821409336676676e-05, + "loss": 0.941, + "step": 5264 + }, + { + "epoch": 0.32321434052610576, + "grad_norm": 0.6613195820044442, + "learning_rate": 1.5819792518463634e-05, + "loss": 0.9395, + "step": 5265 + }, + { + "epoch": 0.32327572976457225, + "grad_norm": 0.6673462716238545, + "learning_rate": 1.581817547016307e-05, + "loss": 0.8902, + "step": 5266 + }, + { + "epoch": 0.32333711900303874, + "grad_norm": 0.7264562276210257, + "learning_rate": 1.5816558191838914e-05, + "loss": 0.9462, + "step": 5267 + }, + { + "epoch": 0.3233985082415053, + "grad_norm": 0.6042025791373897, + "learning_rate": 1.58149406835551e-05, + "loss": 0.8941, + "step": 5268 + }, + { + "epoch": 0.3234598974799718, + "grad_norm": 0.6947221417440819, + "learning_rate": 1.5813322945375583e-05, + "loss": 0.921, + "step": 5269 + }, + { + "epoch": 0.3235212867184383, + "grad_norm": 0.623453233786056, + "learning_rate": 1.5811704977364315e-05, + "loss": 0.9233, + "step": 5270 + }, + { + "epoch": 0.32358267595690476, + "grad_norm": 0.6762486504061316, + "learning_rate": 1.5810086779585267e-05, + "loss": 1.0039, + "step": 5271 + }, + { + "epoch": 0.32364406519537126, + "grad_norm": 0.749627995172635, + "learning_rate": 1.5808468352102416e-05, + "loss": 0.9611, + "step": 5272 + }, + { + "epoch": 0.32370545443383775, + "grad_norm": 0.660658022493324, + "learning_rate": 1.5806849694979742e-05, + "loss": 0.9456, + "step": 5273 + }, + { + "epoch": 0.32376684367230424, + "grad_norm": 0.7121304727064048, + "learning_rate": 1.5805230808281245e-05, + "loss": 0.942, + "step": 5274 + }, + { + "epoch": 0.32382823291077073, + "grad_norm": 0.7215186772943799, + "learning_rate": 1.5803611692070925e-05, + "loss": 0.9878, + "step": 5275 + }, + { + "epoch": 0.3238896221492372, + "grad_norm": 0.6414209920640765, + "learning_rate": 1.5801992346412793e-05, + "loss": 0.9725, + "step": 5276 + }, + { + "epoch": 0.3239510113877037, + "grad_norm": 0.7153785387984697, + "learning_rate": 1.5800372771370874e-05, + "loss": 0.9219, + "step": 5277 + }, + { + "epoch": 0.3240124006261702, + "grad_norm": 0.6603735169774614, + "learning_rate": 1.57987529670092e-05, + "loss": 0.9393, + "step": 5278 + }, + { + "epoch": 0.32407378986463675, + "grad_norm": 0.6686617084570444, + "learning_rate": 1.57971329333918e-05, + "loss": 0.9305, + "step": 5279 + }, + { + "epoch": 0.32413517910310324, + "grad_norm": 0.6717969649217669, + "learning_rate": 1.5795512670582734e-05, + "loss": 0.9471, + "step": 5280 + }, + { + "epoch": 0.32419656834156974, + "grad_norm": 0.6577202687586128, + "learning_rate": 1.5793892178646055e-05, + "loss": 0.9068, + "step": 5281 + }, + { + "epoch": 0.3242579575800362, + "grad_norm": 0.6084735502094601, + "learning_rate": 1.5792271457645832e-05, + "loss": 0.9185, + "step": 5282 + }, + { + "epoch": 0.3243193468185027, + "grad_norm": 0.6451743671441855, + "learning_rate": 1.579065050764614e-05, + "loss": 0.9033, + "step": 5283 + }, + { + "epoch": 0.3243807360569692, + "grad_norm": 0.7265994898800536, + "learning_rate": 1.5789029328711058e-05, + "loss": 0.971, + "step": 5284 + }, + { + "epoch": 0.3244421252954357, + "grad_norm": 0.7480831458246368, + "learning_rate": 1.5787407920904686e-05, + "loss": 0.9405, + "step": 5285 + }, + { + "epoch": 0.3245035145339022, + "grad_norm": 0.6380205981144169, + "learning_rate": 1.5785786284291127e-05, + "loss": 0.8808, + "step": 5286 + }, + { + "epoch": 0.3245649037723687, + "grad_norm": 0.7867028869009735, + "learning_rate": 1.5784164418934495e-05, + "loss": 0.9219, + "step": 5287 + }, + { + "epoch": 0.3246262930108352, + "grad_norm": 0.6673493486536517, + "learning_rate": 1.5782542324898903e-05, + "loss": 0.9098, + "step": 5288 + }, + { + "epoch": 0.3246876822493017, + "grad_norm": 0.6766318531449086, + "learning_rate": 1.5780920002248484e-05, + "loss": 0.9982, + "step": 5289 + }, + { + "epoch": 0.3247490714877682, + "grad_norm": 0.6600494978790435, + "learning_rate": 1.5779297451047384e-05, + "loss": 0.9784, + "step": 5290 + }, + { + "epoch": 0.3248104607262347, + "grad_norm": 0.6835199524592398, + "learning_rate": 1.5777674671359742e-05, + "loss": 0.9037, + "step": 5291 + }, + { + "epoch": 0.3248718499647012, + "grad_norm": 0.6194101111436532, + "learning_rate": 1.577605166324972e-05, + "loss": 0.9299, + "step": 5292 + }, + { + "epoch": 0.3249332392031677, + "grad_norm": 0.629387662191456, + "learning_rate": 1.5774428426781487e-05, + "loss": 0.8895, + "step": 5293 + }, + { + "epoch": 0.3249946284416342, + "grad_norm": 0.6127980795684158, + "learning_rate": 1.5772804962019208e-05, + "loss": 0.9021, + "step": 5294 + }, + { + "epoch": 0.3250560176801007, + "grad_norm": 0.6690803328062385, + "learning_rate": 1.577118126902708e-05, + "loss": 0.9294, + "step": 5295 + }, + { + "epoch": 0.32511740691856716, + "grad_norm": 0.6369900853476262, + "learning_rate": 1.5769557347869287e-05, + "loss": 0.8937, + "step": 5296 + }, + { + "epoch": 0.32517879615703366, + "grad_norm": 0.7508363334800109, + "learning_rate": 1.576793319861003e-05, + "loss": 0.9677, + "step": 5297 + }, + { + "epoch": 0.32524018539550015, + "grad_norm": 0.6538357509932988, + "learning_rate": 1.576630882131353e-05, + "loss": 0.9362, + "step": 5298 + }, + { + "epoch": 0.32530157463396664, + "grad_norm": 0.6583826320707833, + "learning_rate": 1.5764684216044e-05, + "loss": 0.8958, + "step": 5299 + }, + { + "epoch": 0.3253629638724332, + "grad_norm": 0.7632156773439212, + "learning_rate": 1.5763059382865675e-05, + "loss": 0.9584, + "step": 5300 + }, + { + "epoch": 0.3254243531108997, + "grad_norm": 0.6143614813185595, + "learning_rate": 1.5761434321842787e-05, + "loss": 0.9522, + "step": 5301 + }, + { + "epoch": 0.32548574234936617, + "grad_norm": 0.7136469722618689, + "learning_rate": 1.5759809033039583e-05, + "loss": 0.9235, + "step": 5302 + }, + { + "epoch": 0.32554713158783266, + "grad_norm": 0.6858322512807736, + "learning_rate": 1.5758183516520326e-05, + "loss": 0.9115, + "step": 5303 + }, + { + "epoch": 0.32560852082629915, + "grad_norm": 0.6406049844448649, + "learning_rate": 1.5756557772349276e-05, + "loss": 0.9199, + "step": 5304 + }, + { + "epoch": 0.32566991006476564, + "grad_norm": 0.67299128394794, + "learning_rate": 1.5754931800590712e-05, + "loss": 0.9486, + "step": 5305 + }, + { + "epoch": 0.32573129930323214, + "grad_norm": 0.6618607970611289, + "learning_rate": 1.575330560130891e-05, + "loss": 0.9516, + "step": 5306 + }, + { + "epoch": 0.3257926885416986, + "grad_norm": 0.6844334051824674, + "learning_rate": 1.5751679174568167e-05, + "loss": 0.9204, + "step": 5307 + }, + { + "epoch": 0.3258540777801651, + "grad_norm": 0.6679864739277839, + "learning_rate": 1.575005252043279e-05, + "loss": 0.9124, + "step": 5308 + }, + { + "epoch": 0.3259154670186316, + "grad_norm": 0.5978740304805251, + "learning_rate": 1.5748425638967074e-05, + "loss": 0.8605, + "step": 5309 + }, + { + "epoch": 0.32597685625709816, + "grad_norm": 0.6251051520900135, + "learning_rate": 1.5746798530235355e-05, + "loss": 0.9026, + "step": 5310 + }, + { + "epoch": 0.32603824549556465, + "grad_norm": 0.6204966585030938, + "learning_rate": 1.5745171194301952e-05, + "loss": 0.9259, + "step": 5311 + }, + { + "epoch": 0.32609963473403114, + "grad_norm": 0.7191422631991984, + "learning_rate": 1.5743543631231206e-05, + "loss": 0.9239, + "step": 5312 + }, + { + "epoch": 0.32616102397249763, + "grad_norm": 0.7032260532984568, + "learning_rate": 1.5741915841087457e-05, + "loss": 0.9562, + "step": 5313 + }, + { + "epoch": 0.3262224132109641, + "grad_norm": 0.7535379218831251, + "learning_rate": 1.5740287823935067e-05, + "loss": 0.943, + "step": 5314 + }, + { + "epoch": 0.3262838024494306, + "grad_norm": 0.6815608427443779, + "learning_rate": 1.57386595798384e-05, + "loss": 0.8825, + "step": 5315 + }, + { + "epoch": 0.3263451916878971, + "grad_norm": 0.7356681403331815, + "learning_rate": 1.5737031108861826e-05, + "loss": 0.9668, + "step": 5316 + }, + { + "epoch": 0.3264065809263636, + "grad_norm": 0.6286809249396242, + "learning_rate": 1.573540241106973e-05, + "loss": 0.9511, + "step": 5317 + }, + { + "epoch": 0.3264679701648301, + "grad_norm": 0.5818671857743317, + "learning_rate": 1.57337734865265e-05, + "loss": 0.8843, + "step": 5318 + }, + { + "epoch": 0.3265293594032966, + "grad_norm": 0.6792878424611644, + "learning_rate": 1.5732144335296537e-05, + "loss": 0.9218, + "step": 5319 + }, + { + "epoch": 0.3265907486417631, + "grad_norm": 0.6504496836650128, + "learning_rate": 1.5730514957444254e-05, + "loss": 0.939, + "step": 5320 + }, + { + "epoch": 0.3266521378802296, + "grad_norm": 0.6741410149573744, + "learning_rate": 1.5728885353034063e-05, + "loss": 0.9424, + "step": 5321 + }, + { + "epoch": 0.3267135271186961, + "grad_norm": 0.6652738083397144, + "learning_rate": 1.5727255522130395e-05, + "loss": 0.9712, + "step": 5322 + }, + { + "epoch": 0.3267749163571626, + "grad_norm": 0.7276178529187664, + "learning_rate": 1.5725625464797684e-05, + "loss": 0.9165, + "step": 5323 + }, + { + "epoch": 0.3268363055956291, + "grad_norm": 0.5945980951584373, + "learning_rate": 1.5723995181100374e-05, + "loss": 0.9313, + "step": 5324 + }, + { + "epoch": 0.3268976948340956, + "grad_norm": 0.6557728683738087, + "learning_rate": 1.5722364671102922e-05, + "loss": 0.924, + "step": 5325 + }, + { + "epoch": 0.3269590840725621, + "grad_norm": 0.64685550254387, + "learning_rate": 1.572073393486979e-05, + "loss": 0.7292, + "step": 5326 + }, + { + "epoch": 0.32702047331102857, + "grad_norm": 0.6498458060298742, + "learning_rate": 1.5719102972465447e-05, + "loss": 0.9371, + "step": 5327 + }, + { + "epoch": 0.32708186254949506, + "grad_norm": 0.6566281645859373, + "learning_rate": 1.571747178395438e-05, + "loss": 0.8989, + "step": 5328 + }, + { + "epoch": 0.32714325178796155, + "grad_norm": 0.6308188253809605, + "learning_rate": 1.571584036940107e-05, + "loss": 0.9255, + "step": 5329 + }, + { + "epoch": 0.32720464102642804, + "grad_norm": 0.7519759756942412, + "learning_rate": 1.571420872887002e-05, + "loss": 0.9708, + "step": 5330 + }, + { + "epoch": 0.32726603026489454, + "grad_norm": 0.7568806358563936, + "learning_rate": 1.571257686242574e-05, + "loss": 0.9871, + "step": 5331 + }, + { + "epoch": 0.3273274195033611, + "grad_norm": 0.7204581629995933, + "learning_rate": 1.571094477013274e-05, + "loss": 0.9684, + "step": 5332 + }, + { + "epoch": 0.3273888087418276, + "grad_norm": 0.6477312367065382, + "learning_rate": 1.570931245205555e-05, + "loss": 0.9058, + "step": 5333 + }, + { + "epoch": 0.32745019798029407, + "grad_norm": 0.6634327899857247, + "learning_rate": 1.5707679908258702e-05, + "loss": 0.9143, + "step": 5334 + }, + { + "epoch": 0.32751158721876056, + "grad_norm": 0.72237836371575, + "learning_rate": 1.5706047138806742e-05, + "loss": 0.9499, + "step": 5335 + }, + { + "epoch": 0.32757297645722705, + "grad_norm": 0.6298584975888765, + "learning_rate": 1.570441414376422e-05, + "loss": 0.9445, + "step": 5336 + }, + { + "epoch": 0.32763436569569354, + "grad_norm": 0.70367748044759, + "learning_rate": 1.57027809231957e-05, + "loss": 0.9917, + "step": 5337 + }, + { + "epoch": 0.32769575493416003, + "grad_norm": 0.6225267504737673, + "learning_rate": 1.5701147477165748e-05, + "loss": 0.9059, + "step": 5338 + }, + { + "epoch": 0.3277571441726265, + "grad_norm": 0.7166531509538806, + "learning_rate": 1.5699513805738942e-05, + "loss": 0.9694, + "step": 5339 + }, + { + "epoch": 0.327818533411093, + "grad_norm": 0.6798864770166742, + "learning_rate": 1.5697879908979875e-05, + "loss": 0.9473, + "step": 5340 + }, + { + "epoch": 0.3278799226495595, + "grad_norm": 0.6750104508660509, + "learning_rate": 1.5696245786953138e-05, + "loss": 0.9394, + "step": 5341 + }, + { + "epoch": 0.32794131188802605, + "grad_norm": 0.6634405935117033, + "learning_rate": 1.5694611439723342e-05, + "loss": 0.9067, + "step": 5342 + }, + { + "epoch": 0.32800270112649255, + "grad_norm": 0.7233321523916899, + "learning_rate": 1.56929768673551e-05, + "loss": 0.9013, + "step": 5343 + }, + { + "epoch": 0.32806409036495904, + "grad_norm": 0.6954294162757672, + "learning_rate": 1.569134206991303e-05, + "loss": 0.9732, + "step": 5344 + }, + { + "epoch": 0.32812547960342553, + "grad_norm": 0.7141062219508081, + "learning_rate": 1.5689707047461772e-05, + "loss": 0.9465, + "step": 5345 + }, + { + "epoch": 0.328186868841892, + "grad_norm": 0.6735290332968618, + "learning_rate": 1.5688071800065964e-05, + "loss": 0.9372, + "step": 5346 + }, + { + "epoch": 0.3282482580803585, + "grad_norm": 0.6739979778621006, + "learning_rate": 1.5686436327790253e-05, + "loss": 0.9416, + "step": 5347 + }, + { + "epoch": 0.328309647318825, + "grad_norm": 0.7439504184600768, + "learning_rate": 1.5684800630699302e-05, + "loss": 0.9429, + "step": 5348 + }, + { + "epoch": 0.3283710365572915, + "grad_norm": 0.6444440778934901, + "learning_rate": 1.5683164708857778e-05, + "loss": 0.8798, + "step": 5349 + }, + { + "epoch": 0.328432425795758, + "grad_norm": 0.7028836164368465, + "learning_rate": 1.5681528562330356e-05, + "loss": 0.9535, + "step": 5350 + }, + { + "epoch": 0.3284938150342245, + "grad_norm": 0.7698736693305522, + "learning_rate": 1.5679892191181726e-05, + "loss": 1.0171, + "step": 5351 + }, + { + "epoch": 0.32855520427269097, + "grad_norm": 0.6868408641869476, + "learning_rate": 1.5678255595476578e-05, + "loss": 0.9646, + "step": 5352 + }, + { + "epoch": 0.3286165935111575, + "grad_norm": 0.6662867621793654, + "learning_rate": 1.5676618775279615e-05, + "loss": 0.9482, + "step": 5353 + }, + { + "epoch": 0.328677982749624, + "grad_norm": 0.6178457830971825, + "learning_rate": 1.5674981730655553e-05, + "loss": 0.8725, + "step": 5354 + }, + { + "epoch": 0.3287393719880905, + "grad_norm": 0.6880179449354146, + "learning_rate": 1.567334446166911e-05, + "loss": 0.9089, + "step": 5355 + }, + { + "epoch": 0.328800761226557, + "grad_norm": 0.7281457753447684, + "learning_rate": 1.5671706968385017e-05, + "loss": 1.002, + "step": 5356 + }, + { + "epoch": 0.3288621504650235, + "grad_norm": 0.644847524201082, + "learning_rate": 1.5670069250868018e-05, + "loss": 0.9074, + "step": 5357 + }, + { + "epoch": 0.32892353970349, + "grad_norm": 0.6510572222992512, + "learning_rate": 1.566843130918285e-05, + "loss": 0.7412, + "step": 5358 + }, + { + "epoch": 0.32898492894195647, + "grad_norm": 0.7064033221492785, + "learning_rate": 1.5666793143394277e-05, + "loss": 0.9563, + "step": 5359 + }, + { + "epoch": 0.32904631818042296, + "grad_norm": 0.686571333855317, + "learning_rate": 1.5665154753567064e-05, + "loss": 0.9051, + "step": 5360 + }, + { + "epoch": 0.32910770741888945, + "grad_norm": 0.6240392158554794, + "learning_rate": 1.5663516139765983e-05, + "loss": 0.9172, + "step": 5361 + }, + { + "epoch": 0.32916909665735594, + "grad_norm": 0.7092668896867135, + "learning_rate": 1.5661877302055822e-05, + "loss": 0.961, + "step": 5362 + }, + { + "epoch": 0.3292304858958225, + "grad_norm": 0.6769021730717221, + "learning_rate": 1.5660238240501365e-05, + "loss": 0.9397, + "step": 5363 + }, + { + "epoch": 0.329291875134289, + "grad_norm": 0.6915585791441472, + "learning_rate": 1.565859895516742e-05, + "loss": 0.918, + "step": 5364 + }, + { + "epoch": 0.32935326437275547, + "grad_norm": 0.7015533911661967, + "learning_rate": 1.565695944611879e-05, + "loss": 0.9861, + "step": 5365 + }, + { + "epoch": 0.32941465361122196, + "grad_norm": 0.6838397509321159, + "learning_rate": 1.56553197134203e-05, + "loss": 0.9081, + "step": 5366 + }, + { + "epoch": 0.32947604284968846, + "grad_norm": 0.7317327464433736, + "learning_rate": 1.5653679757136776e-05, + "loss": 0.9839, + "step": 5367 + }, + { + "epoch": 0.32953743208815495, + "grad_norm": 0.68981444019879, + "learning_rate": 1.565203957733305e-05, + "loss": 0.933, + "step": 5368 + }, + { + "epoch": 0.32959882132662144, + "grad_norm": 0.6681456194418274, + "learning_rate": 1.5650399174073977e-05, + "loss": 0.764, + "step": 5369 + }, + { + "epoch": 0.32966021056508793, + "grad_norm": 0.6781338793068528, + "learning_rate": 1.5648758547424397e-05, + "loss": 0.9281, + "step": 5370 + }, + { + "epoch": 0.3297215998035544, + "grad_norm": 0.6806385079537443, + "learning_rate": 1.564711769744918e-05, + "loss": 0.8822, + "step": 5371 + }, + { + "epoch": 0.3297829890420209, + "grad_norm": 0.6340008839163745, + "learning_rate": 1.5645476624213204e-05, + "loss": 0.9403, + "step": 5372 + }, + { + "epoch": 0.3298443782804874, + "grad_norm": 0.7077323199942408, + "learning_rate": 1.5643835327781337e-05, + "loss": 0.9536, + "step": 5373 + }, + { + "epoch": 0.32990576751895395, + "grad_norm": 0.6829317795297892, + "learning_rate": 1.564219380821848e-05, + "loss": 0.9446, + "step": 5374 + }, + { + "epoch": 0.32996715675742044, + "grad_norm": 0.6742896095431056, + "learning_rate": 1.564055206558952e-05, + "loss": 0.9594, + "step": 5375 + }, + { + "epoch": 0.33002854599588693, + "grad_norm": 0.672283936542283, + "learning_rate": 1.563891009995937e-05, + "loss": 0.9404, + "step": 5376 + }, + { + "epoch": 0.3300899352343534, + "grad_norm": 0.6750180606462417, + "learning_rate": 1.5637267911392947e-05, + "loss": 0.9636, + "step": 5377 + }, + { + "epoch": 0.3301513244728199, + "grad_norm": 0.6287265203442871, + "learning_rate": 1.5635625499955168e-05, + "loss": 0.8892, + "step": 5378 + }, + { + "epoch": 0.3302127137112864, + "grad_norm": 0.7395760594457685, + "learning_rate": 1.5633982865710976e-05, + "loss": 0.9442, + "step": 5379 + }, + { + "epoch": 0.3302741029497529, + "grad_norm": 0.728238616878009, + "learning_rate": 1.5632340008725306e-05, + "loss": 0.9853, + "step": 5380 + }, + { + "epoch": 0.3303354921882194, + "grad_norm": 0.6132369947880151, + "learning_rate": 1.5630696929063116e-05, + "loss": 0.8992, + "step": 5381 + }, + { + "epoch": 0.3303968814266859, + "grad_norm": 0.6801266749718353, + "learning_rate": 1.562905362678936e-05, + "loss": 0.9444, + "step": 5382 + }, + { + "epoch": 0.3304582706651524, + "grad_norm": 0.710791251111037, + "learning_rate": 1.5627410101969004e-05, + "loss": 0.9659, + "step": 5383 + }, + { + "epoch": 0.3305196599036189, + "grad_norm": 0.7340616667347103, + "learning_rate": 1.5625766354667033e-05, + "loss": 1.028, + "step": 5384 + }, + { + "epoch": 0.3305810491420854, + "grad_norm": 0.6343758534648477, + "learning_rate": 1.562412238494843e-05, + "loss": 0.8839, + "step": 5385 + }, + { + "epoch": 0.3306424383805519, + "grad_norm": 0.653977463831161, + "learning_rate": 1.5622478192878182e-05, + "loss": 0.94, + "step": 5386 + }, + { + "epoch": 0.3307038276190184, + "grad_norm": 0.5892861620059281, + "learning_rate": 1.5620833778521306e-05, + "loss": 0.9026, + "step": 5387 + }, + { + "epoch": 0.3307652168574849, + "grad_norm": 0.6049551615145095, + "learning_rate": 1.5619189141942808e-05, + "loss": 0.9571, + "step": 5388 + }, + { + "epoch": 0.3308266060959514, + "grad_norm": 0.7275789781416648, + "learning_rate": 1.561754428320771e-05, + "loss": 0.9604, + "step": 5389 + }, + { + "epoch": 0.3308879953344179, + "grad_norm": 0.6558621663921832, + "learning_rate": 1.561589920238104e-05, + "loss": 0.8912, + "step": 5390 + }, + { + "epoch": 0.33094938457288436, + "grad_norm": 0.6390451044306611, + "learning_rate": 1.5614253899527843e-05, + "loss": 0.9272, + "step": 5391 + }, + { + "epoch": 0.33101077381135086, + "grad_norm": 0.738947700662404, + "learning_rate": 1.5612608374713155e-05, + "loss": 0.8806, + "step": 5392 + }, + { + "epoch": 0.33107216304981735, + "grad_norm": 0.7054047978376838, + "learning_rate": 1.5610962628002044e-05, + "loss": 0.98, + "step": 5393 + }, + { + "epoch": 0.33113355228828384, + "grad_norm": 0.7053576583951197, + "learning_rate": 1.560931665945957e-05, + "loss": 0.9647, + "step": 5394 + }, + { + "epoch": 0.3311949415267504, + "grad_norm": 0.6908794690226369, + "learning_rate": 1.5607670469150808e-05, + "loss": 0.9539, + "step": 5395 + }, + { + "epoch": 0.3312563307652169, + "grad_norm": 0.6657808154909619, + "learning_rate": 1.560602405714084e-05, + "loss": 0.9006, + "step": 5396 + }, + { + "epoch": 0.33131772000368337, + "grad_norm": 0.7090034730860674, + "learning_rate": 1.560437742349476e-05, + "loss": 1.0023, + "step": 5397 + }, + { + "epoch": 0.33137910924214986, + "grad_norm": 0.696725084604902, + "learning_rate": 1.560273056827766e-05, + "loss": 0.958, + "step": 5398 + }, + { + "epoch": 0.33144049848061635, + "grad_norm": 0.6299919365328608, + "learning_rate": 1.560108349155466e-05, + "loss": 0.9246, + "step": 5399 + }, + { + "epoch": 0.33150188771908284, + "grad_norm": 0.729260176291398, + "learning_rate": 1.5599436193390873e-05, + "loss": 0.9411, + "step": 5400 + }, + { + "epoch": 0.33156327695754934, + "grad_norm": 0.5987868745056717, + "learning_rate": 1.5597788673851426e-05, + "loss": 0.918, + "step": 5401 + }, + { + "epoch": 0.3316246661960158, + "grad_norm": 0.6174378309952891, + "learning_rate": 1.5596140933001452e-05, + "loss": 0.8699, + "step": 5402 + }, + { + "epoch": 0.3316860554344823, + "grad_norm": 0.7000431425327821, + "learning_rate": 1.5594492970906097e-05, + "loss": 0.9615, + "step": 5403 + }, + { + "epoch": 0.3317474446729488, + "grad_norm": 0.6253015232524276, + "learning_rate": 1.5592844787630514e-05, + "loss": 0.9202, + "step": 5404 + }, + { + "epoch": 0.3318088339114153, + "grad_norm": 0.6922346501394402, + "learning_rate": 1.559119638323986e-05, + "loss": 0.9358, + "step": 5405 + }, + { + "epoch": 0.33187022314988185, + "grad_norm": 0.6103413749647021, + "learning_rate": 1.5589547757799316e-05, + "loss": 0.8709, + "step": 5406 + }, + { + "epoch": 0.33193161238834834, + "grad_norm": 0.6656681779249708, + "learning_rate": 1.558789891137405e-05, + "loss": 0.9525, + "step": 5407 + }, + { + "epoch": 0.33199300162681483, + "grad_norm": 0.718169693019818, + "learning_rate": 1.5586249844029254e-05, + "loss": 1.0122, + "step": 5408 + }, + { + "epoch": 0.3320543908652813, + "grad_norm": 0.6520734131869521, + "learning_rate": 1.5584600555830125e-05, + "loss": 0.9294, + "step": 5409 + }, + { + "epoch": 0.3321157801037478, + "grad_norm": 0.6601600465946845, + "learning_rate": 1.5582951046841866e-05, + "loss": 0.878, + "step": 5410 + }, + { + "epoch": 0.3321771693422143, + "grad_norm": 0.690630522860946, + "learning_rate": 1.5581301317129693e-05, + "loss": 0.9264, + "step": 5411 + }, + { + "epoch": 0.3322385585806808, + "grad_norm": 0.7055851882997658, + "learning_rate": 1.557965136675883e-05, + "loss": 0.9255, + "step": 5412 + }, + { + "epoch": 0.3322999478191473, + "grad_norm": 0.668438474155427, + "learning_rate": 1.5578001195794507e-05, + "loss": 0.9534, + "step": 5413 + }, + { + "epoch": 0.3323613370576138, + "grad_norm": 0.6503892312208905, + "learning_rate": 1.557635080430196e-05, + "loss": 0.9046, + "step": 5414 + }, + { + "epoch": 0.3324227262960803, + "grad_norm": 0.6670479255864433, + "learning_rate": 1.5574700192346442e-05, + "loss": 0.8903, + "step": 5415 + }, + { + "epoch": 0.3324841155345468, + "grad_norm": 0.7291287088199296, + "learning_rate": 1.557304935999321e-05, + "loss": 0.9201, + "step": 5416 + }, + { + "epoch": 0.3325455047730133, + "grad_norm": 0.7040196452013506, + "learning_rate": 1.557139830730753e-05, + "loss": 0.9775, + "step": 5417 + }, + { + "epoch": 0.3326068940114798, + "grad_norm": 0.6454578357269581, + "learning_rate": 1.556974703435468e-05, + "loss": 0.9144, + "step": 5418 + }, + { + "epoch": 0.3326682832499463, + "grad_norm": 0.7157105239442292, + "learning_rate": 1.5568095541199935e-05, + "loss": 0.9283, + "step": 5419 + }, + { + "epoch": 0.3327296724884128, + "grad_norm": 0.656629937192564, + "learning_rate": 1.5566443827908598e-05, + "loss": 0.9764, + "step": 5420 + }, + { + "epoch": 0.3327910617268793, + "grad_norm": 0.730476936268898, + "learning_rate": 1.5564791894545962e-05, + "loss": 0.9134, + "step": 5421 + }, + { + "epoch": 0.33285245096534577, + "grad_norm": 0.7176338982463606, + "learning_rate": 1.5563139741177343e-05, + "loss": 0.9594, + "step": 5422 + }, + { + "epoch": 0.33291384020381226, + "grad_norm": 0.6236033206857925, + "learning_rate": 1.5561487367868053e-05, + "loss": 0.8936, + "step": 5423 + }, + { + "epoch": 0.33297522944227875, + "grad_norm": 0.6264098799060023, + "learning_rate": 1.5559834774683424e-05, + "loss": 0.9407, + "step": 5424 + }, + { + "epoch": 0.33303661868074524, + "grad_norm": 0.6775232909142476, + "learning_rate": 1.5558181961688788e-05, + "loss": 0.9297, + "step": 5425 + }, + { + "epoch": 0.33309800791921174, + "grad_norm": 0.6870175500012387, + "learning_rate": 1.5556528928949496e-05, + "loss": 0.9339, + "step": 5426 + }, + { + "epoch": 0.3331593971576783, + "grad_norm": 0.6662171542676156, + "learning_rate": 1.5554875676530894e-05, + "loss": 0.9246, + "step": 5427 + }, + { + "epoch": 0.3332207863961448, + "grad_norm": 0.6648367466868892, + "learning_rate": 1.5553222204498347e-05, + "loss": 0.8808, + "step": 5428 + }, + { + "epoch": 0.33328217563461127, + "grad_norm": 0.6178827388708268, + "learning_rate": 1.5551568512917228e-05, + "loss": 0.8955, + "step": 5429 + }, + { + "epoch": 0.33334356487307776, + "grad_norm": 0.6402700404504443, + "learning_rate": 1.554991460185291e-05, + "loss": 0.9657, + "step": 5430 + }, + { + "epoch": 0.33340495411154425, + "grad_norm": 0.6625321050152697, + "learning_rate": 1.554826047137079e-05, + "loss": 0.8932, + "step": 5431 + }, + { + "epoch": 0.33346634335001074, + "grad_norm": 0.74978861205798, + "learning_rate": 1.5546606121536256e-05, + "loss": 1.0047, + "step": 5432 + }, + { + "epoch": 0.33352773258847723, + "grad_norm": 0.7363424643145458, + "learning_rate": 1.5544951552414716e-05, + "loss": 0.9826, + "step": 5433 + }, + { + "epoch": 0.3335891218269437, + "grad_norm": 0.7131510773466019, + "learning_rate": 1.5543296764071586e-05, + "loss": 0.9111, + "step": 5434 + }, + { + "epoch": 0.3336505110654102, + "grad_norm": 0.7416891465659392, + "learning_rate": 1.5541641756572284e-05, + "loss": 0.9475, + "step": 5435 + }, + { + "epoch": 0.3337119003038767, + "grad_norm": 0.6836091375861963, + "learning_rate": 1.553998652998225e-05, + "loss": 0.9649, + "step": 5436 + }, + { + "epoch": 0.33377328954234325, + "grad_norm": 0.7387210551114529, + "learning_rate": 1.5538331084366916e-05, + "loss": 0.9225, + "step": 5437 + }, + { + "epoch": 0.33383467878080975, + "grad_norm": 0.6252834485674361, + "learning_rate": 1.5536675419791732e-05, + "loss": 0.7615, + "step": 5438 + }, + { + "epoch": 0.33389606801927624, + "grad_norm": 0.6586932672447902, + "learning_rate": 1.5535019536322158e-05, + "loss": 0.9399, + "step": 5439 + }, + { + "epoch": 0.33395745725774273, + "grad_norm": 0.6041526061248026, + "learning_rate": 1.5533363434023658e-05, + "loss": 0.9001, + "step": 5440 + }, + { + "epoch": 0.3340188464962092, + "grad_norm": 0.6749224226292151, + "learning_rate": 1.5531707112961708e-05, + "loss": 0.962, + "step": 5441 + }, + { + "epoch": 0.3340802357346757, + "grad_norm": 0.6959567891087236, + "learning_rate": 1.5530050573201787e-05, + "loss": 0.9233, + "step": 5442 + }, + { + "epoch": 0.3341416249731422, + "grad_norm": 0.6144481553028867, + "learning_rate": 1.5528393814809394e-05, + "loss": 0.9332, + "step": 5443 + }, + { + "epoch": 0.3342030142116087, + "grad_norm": 0.6748906702337466, + "learning_rate": 1.5526736837850023e-05, + "loss": 0.9246, + "step": 5444 + }, + { + "epoch": 0.3342644034500752, + "grad_norm": 0.7073935605846653, + "learning_rate": 1.5525079642389188e-05, + "loss": 0.9236, + "step": 5445 + }, + { + "epoch": 0.3343257926885417, + "grad_norm": 0.7169440069741154, + "learning_rate": 1.55234222284924e-05, + "loss": 0.9536, + "step": 5446 + }, + { + "epoch": 0.33438718192700817, + "grad_norm": 0.6811398863958155, + "learning_rate": 1.5521764596225197e-05, + "loss": 0.9532, + "step": 5447 + }, + { + "epoch": 0.3344485711654747, + "grad_norm": 0.6478165480025428, + "learning_rate": 1.5520106745653102e-05, + "loss": 0.9138, + "step": 5448 + }, + { + "epoch": 0.3345099604039412, + "grad_norm": 0.6922990583302837, + "learning_rate": 1.5518448676841665e-05, + "loss": 0.9087, + "step": 5449 + }, + { + "epoch": 0.3345713496424077, + "grad_norm": 0.6744798305245184, + "learning_rate": 1.5516790389856434e-05, + "loss": 0.9235, + "step": 5450 + }, + { + "epoch": 0.3346327388808742, + "grad_norm": 0.7051783914331429, + "learning_rate": 1.5515131884762978e-05, + "loss": 0.9153, + "step": 5451 + }, + { + "epoch": 0.3346941281193407, + "grad_norm": 0.7190615929148438, + "learning_rate": 1.551347316162686e-05, + "loss": 0.994, + "step": 5452 + }, + { + "epoch": 0.3347555173578072, + "grad_norm": 0.6474440617195358, + "learning_rate": 1.551181422051366e-05, + "loss": 0.901, + "step": 5453 + }, + { + "epoch": 0.33481690659627367, + "grad_norm": 0.7200100210713987, + "learning_rate": 1.551015506148896e-05, + "loss": 0.971, + "step": 5454 + }, + { + "epoch": 0.33487829583474016, + "grad_norm": 0.7196030706629593, + "learning_rate": 1.5508495684618366e-05, + "loss": 0.95, + "step": 5455 + }, + { + "epoch": 0.33493968507320665, + "grad_norm": 0.6087393323722237, + "learning_rate": 1.5506836089967473e-05, + "loss": 0.926, + "step": 5456 + }, + { + "epoch": 0.33500107431167314, + "grad_norm": 0.7603585294961138, + "learning_rate": 1.55051762776019e-05, + "loss": 0.975, + "step": 5457 + }, + { + "epoch": 0.33506246355013963, + "grad_norm": 0.7424024506069867, + "learning_rate": 1.550351624758726e-05, + "loss": 0.963, + "step": 5458 + }, + { + "epoch": 0.3351238527886062, + "grad_norm": 0.6990514123602968, + "learning_rate": 1.550185599998919e-05, + "loss": 0.9318, + "step": 5459 + }, + { + "epoch": 0.33518524202707267, + "grad_norm": 0.6795392207199331, + "learning_rate": 1.5500195534873328e-05, + "loss": 0.9006, + "step": 5460 + }, + { + "epoch": 0.33524663126553916, + "grad_norm": 0.7119270548424468, + "learning_rate": 1.5498534852305318e-05, + "loss": 0.9201, + "step": 5461 + }, + { + "epoch": 0.33530802050400565, + "grad_norm": 0.6783384479578749, + "learning_rate": 1.549687395235082e-05, + "loss": 0.918, + "step": 5462 + }, + { + "epoch": 0.33536940974247215, + "grad_norm": 0.6957442932998052, + "learning_rate": 1.549521283507549e-05, + "loss": 0.9185, + "step": 5463 + }, + { + "epoch": 0.33543079898093864, + "grad_norm": 0.6903963900600587, + "learning_rate": 1.549355150054501e-05, + "loss": 0.914, + "step": 5464 + }, + { + "epoch": 0.33549218821940513, + "grad_norm": 0.656981635867602, + "learning_rate": 1.5491889948825054e-05, + "loss": 0.8869, + "step": 5465 + }, + { + "epoch": 0.3355535774578716, + "grad_norm": 0.6695796662141189, + "learning_rate": 1.549022817998132e-05, + "loss": 0.9458, + "step": 5466 + }, + { + "epoch": 0.3356149666963381, + "grad_norm": 0.6850170701657549, + "learning_rate": 1.5488566194079497e-05, + "loss": 0.9376, + "step": 5467 + }, + { + "epoch": 0.3356763559348046, + "grad_norm": 0.7081775432633859, + "learning_rate": 1.5486903991185304e-05, + "loss": 0.9434, + "step": 5468 + }, + { + "epoch": 0.33573774517327115, + "grad_norm": 0.7047308289637365, + "learning_rate": 1.5485241571364446e-05, + "loss": 0.9105, + "step": 5469 + }, + { + "epoch": 0.33579913441173764, + "grad_norm": 0.6008207222417034, + "learning_rate": 1.548357893468265e-05, + "loss": 0.7353, + "step": 5470 + }, + { + "epoch": 0.33586052365020413, + "grad_norm": 0.6507180040469835, + "learning_rate": 1.5481916081205654e-05, + "loss": 0.922, + "step": 5471 + }, + { + "epoch": 0.3359219128886706, + "grad_norm": 0.7696330831595413, + "learning_rate": 1.5480253010999197e-05, + "loss": 0.9963, + "step": 5472 + }, + { + "epoch": 0.3359833021271371, + "grad_norm": 0.6746552724175646, + "learning_rate": 1.5478589724129027e-05, + "loss": 0.8928, + "step": 5473 + }, + { + "epoch": 0.3360446913656036, + "grad_norm": 0.6534417028985103, + "learning_rate": 1.54769262206609e-05, + "loss": 0.8664, + "step": 5474 + }, + { + "epoch": 0.3361060806040701, + "grad_norm": 0.7302693595648138, + "learning_rate": 1.547526250066059e-05, + "loss": 0.944, + "step": 5475 + }, + { + "epoch": 0.3361674698425366, + "grad_norm": 0.6080259674878734, + "learning_rate": 1.547359856419387e-05, + "loss": 0.8756, + "step": 5476 + }, + { + "epoch": 0.3362288590810031, + "grad_norm": 0.6792805282160745, + "learning_rate": 1.5471934411326524e-05, + "loss": 0.9341, + "step": 5477 + }, + { + "epoch": 0.3362902483194696, + "grad_norm": 0.6775595927171484, + "learning_rate": 1.547027004212434e-05, + "loss": 0.9293, + "step": 5478 + }, + { + "epoch": 0.33635163755793607, + "grad_norm": 0.6936057925536088, + "learning_rate": 1.5468605456653128e-05, + "loss": 0.9252, + "step": 5479 + }, + { + "epoch": 0.3364130267964026, + "grad_norm": 0.7517495000923438, + "learning_rate": 1.5466940654978694e-05, + "loss": 0.9225, + "step": 5480 + }, + { + "epoch": 0.3364744160348691, + "grad_norm": 0.7559227259777287, + "learning_rate": 1.5465275637166857e-05, + "loss": 0.9804, + "step": 5481 + }, + { + "epoch": 0.3365358052733356, + "grad_norm": 0.7038893270337151, + "learning_rate": 1.5463610403283445e-05, + "loss": 0.9268, + "step": 5482 + }, + { + "epoch": 0.3365971945118021, + "grad_norm": 0.6348174805241598, + "learning_rate": 1.546194495339429e-05, + "loss": 0.9109, + "step": 5483 + }, + { + "epoch": 0.3366585837502686, + "grad_norm": 0.7340810631584087, + "learning_rate": 1.5460279287565237e-05, + "loss": 0.9536, + "step": 5484 + }, + { + "epoch": 0.3367199729887351, + "grad_norm": 0.655553386632965, + "learning_rate": 1.5458613405862146e-05, + "loss": 0.9203, + "step": 5485 + }, + { + "epoch": 0.33678136222720156, + "grad_norm": 0.698855344231224, + "learning_rate": 1.5456947308350865e-05, + "loss": 0.9758, + "step": 5486 + }, + { + "epoch": 0.33684275146566806, + "grad_norm": 0.7311290012249454, + "learning_rate": 1.5455280995097277e-05, + "loss": 0.974, + "step": 5487 + }, + { + "epoch": 0.33690414070413455, + "grad_norm": 0.6251336419887843, + "learning_rate": 1.545361446616725e-05, + "loss": 0.9387, + "step": 5488 + }, + { + "epoch": 0.33696552994260104, + "grad_norm": 0.6344429445434119, + "learning_rate": 1.5451947721626676e-05, + "loss": 0.6812, + "step": 5489 + }, + { + "epoch": 0.3370269191810676, + "grad_norm": 0.6977544196696889, + "learning_rate": 1.5450280761541453e-05, + "loss": 0.9108, + "step": 5490 + }, + { + "epoch": 0.3370883084195341, + "grad_norm": 0.7474874642392585, + "learning_rate": 1.5448613585977476e-05, + "loss": 0.9822, + "step": 5491 + }, + { + "epoch": 0.33714969765800057, + "grad_norm": 0.7633744217288374, + "learning_rate": 1.5446946195000668e-05, + "loss": 0.9441, + "step": 5492 + }, + { + "epoch": 0.33721108689646706, + "grad_norm": 0.707872372542762, + "learning_rate": 1.544527858867694e-05, + "loss": 0.9183, + "step": 5493 + }, + { + "epoch": 0.33727247613493355, + "grad_norm": 0.7308434671984007, + "learning_rate": 1.544361076707223e-05, + "loss": 0.9516, + "step": 5494 + }, + { + "epoch": 0.33733386537340004, + "grad_norm": 0.7507641006779426, + "learning_rate": 1.544194273025247e-05, + "loss": 0.938, + "step": 5495 + }, + { + "epoch": 0.33739525461186654, + "grad_norm": 0.6903917663200254, + "learning_rate": 1.544027447828361e-05, + "loss": 0.8938, + "step": 5496 + }, + { + "epoch": 0.337456643850333, + "grad_norm": 0.6665597775682714, + "learning_rate": 1.5438606011231604e-05, + "loss": 0.9221, + "step": 5497 + }, + { + "epoch": 0.3375180330887995, + "grad_norm": 0.6183304090090338, + "learning_rate": 1.543693732916241e-05, + "loss": 0.8993, + "step": 5498 + }, + { + "epoch": 0.337579422327266, + "grad_norm": 0.6880446576310174, + "learning_rate": 1.5435268432142007e-05, + "loss": 0.9304, + "step": 5499 + }, + { + "epoch": 0.3376408115657325, + "grad_norm": 0.6858772295407559, + "learning_rate": 1.5433599320236372e-05, + "loss": 0.9755, + "step": 5500 + }, + { + "epoch": 0.33770220080419905, + "grad_norm": 0.6814884972980221, + "learning_rate": 1.5431929993511496e-05, + "loss": 0.8752, + "step": 5501 + }, + { + "epoch": 0.33776359004266554, + "grad_norm": 0.7491942643292576, + "learning_rate": 1.5430260452033377e-05, + "loss": 0.929, + "step": 5502 + }, + { + "epoch": 0.33782497928113203, + "grad_norm": 0.6308246006851934, + "learning_rate": 1.5428590695868018e-05, + "loss": 0.8637, + "step": 5503 + }, + { + "epoch": 0.3378863685195985, + "grad_norm": 0.6598154215110663, + "learning_rate": 1.5426920725081434e-05, + "loss": 0.9713, + "step": 5504 + }, + { + "epoch": 0.337947757758065, + "grad_norm": 0.72336405530156, + "learning_rate": 1.542525053973965e-05, + "loss": 0.8996, + "step": 5505 + }, + { + "epoch": 0.3380091469965315, + "grad_norm": 0.694613969739906, + "learning_rate": 1.5423580139908692e-05, + "loss": 0.9045, + "step": 5506 + }, + { + "epoch": 0.338070536234998, + "grad_norm": 0.7017033587950722, + "learning_rate": 1.5421909525654607e-05, + "loss": 1.0073, + "step": 5507 + }, + { + "epoch": 0.3381319254734645, + "grad_norm": 0.6823340887632955, + "learning_rate": 1.542023869704344e-05, + "loss": 0.899, + "step": 5508 + }, + { + "epoch": 0.338193314711931, + "grad_norm": 0.7016239150227419, + "learning_rate": 1.541856765414125e-05, + "loss": 0.7414, + "step": 5509 + }, + { + "epoch": 0.3382547039503975, + "grad_norm": 0.701569798255262, + "learning_rate": 1.5416896397014094e-05, + "loss": 0.9551, + "step": 5510 + }, + { + "epoch": 0.33831609318886396, + "grad_norm": 0.6687195632327994, + "learning_rate": 1.5415224925728054e-05, + "loss": 0.9739, + "step": 5511 + }, + { + "epoch": 0.3383774824273305, + "grad_norm": 0.679845033762257, + "learning_rate": 1.5413553240349213e-05, + "loss": 0.9161, + "step": 5512 + }, + { + "epoch": 0.338438871665797, + "grad_norm": 0.6999813166910149, + "learning_rate": 1.5411881340943655e-05, + "loss": 0.9466, + "step": 5513 + }, + { + "epoch": 0.3385002609042635, + "grad_norm": 0.6991555818849108, + "learning_rate": 1.5410209227577487e-05, + "loss": 0.9358, + "step": 5514 + }, + { + "epoch": 0.33856165014273, + "grad_norm": 0.7143827461768026, + "learning_rate": 1.5408536900316807e-05, + "loss": 0.9589, + "step": 5515 + }, + { + "epoch": 0.3386230393811965, + "grad_norm": 0.6739208837914461, + "learning_rate": 1.540686435922774e-05, + "loss": 0.9866, + "step": 5516 + }, + { + "epoch": 0.33868442861966297, + "grad_norm": 0.6431878064101222, + "learning_rate": 1.5405191604376407e-05, + "loss": 0.8968, + "step": 5517 + }, + { + "epoch": 0.33874581785812946, + "grad_norm": 0.7691647533939909, + "learning_rate": 1.540351863582894e-05, + "loss": 0.9898, + "step": 5518 + }, + { + "epoch": 0.33880720709659595, + "grad_norm": 0.7506246156523317, + "learning_rate": 1.5401845453651482e-05, + "loss": 0.9917, + "step": 5519 + }, + { + "epoch": 0.33886859633506244, + "grad_norm": 0.6557966332270516, + "learning_rate": 1.5400172057910184e-05, + "loss": 0.9428, + "step": 5520 + }, + { + "epoch": 0.33892998557352894, + "grad_norm": 0.7683840558933973, + "learning_rate": 1.5398498448671197e-05, + "loss": 0.9808, + "step": 5521 + }, + { + "epoch": 0.3389913748119955, + "grad_norm": 0.715111295853362, + "learning_rate": 1.53968246260007e-05, + "loss": 0.9374, + "step": 5522 + }, + { + "epoch": 0.339052764050462, + "grad_norm": 0.732772036046599, + "learning_rate": 1.539515058996486e-05, + "loss": 0.9022, + "step": 5523 + }, + { + "epoch": 0.33911415328892847, + "grad_norm": 0.7016723191122805, + "learning_rate": 1.5393476340629856e-05, + "loss": 0.9413, + "step": 5524 + }, + { + "epoch": 0.33917554252739496, + "grad_norm": 0.7193912373575216, + "learning_rate": 1.539180187806189e-05, + "loss": 0.9281, + "step": 5525 + }, + { + "epoch": 0.33923693176586145, + "grad_norm": 0.6662044760004974, + "learning_rate": 1.5390127202327156e-05, + "loss": 0.9174, + "step": 5526 + }, + { + "epoch": 0.33929832100432794, + "grad_norm": 0.6942314214323874, + "learning_rate": 1.538845231349187e-05, + "loss": 0.9949, + "step": 5527 + }, + { + "epoch": 0.33935971024279443, + "grad_norm": 0.6474349668603055, + "learning_rate": 1.538677721162224e-05, + "loss": 0.898, + "step": 5528 + }, + { + "epoch": 0.3394210994812609, + "grad_norm": 0.7006762603689344, + "learning_rate": 1.5385101896784497e-05, + "loss": 0.9419, + "step": 5529 + }, + { + "epoch": 0.3394824887197274, + "grad_norm": 0.6079641152974817, + "learning_rate": 1.5383426369044876e-05, + "loss": 0.8815, + "step": 5530 + }, + { + "epoch": 0.3395438779581939, + "grad_norm": 0.7503753303835753, + "learning_rate": 1.5381750628469616e-05, + "loss": 0.9985, + "step": 5531 + }, + { + "epoch": 0.3396052671966604, + "grad_norm": 0.690315027501973, + "learning_rate": 1.5380074675124972e-05, + "loss": 0.9281, + "step": 5532 + }, + { + "epoch": 0.33966665643512695, + "grad_norm": 0.6639766235375575, + "learning_rate": 1.53783985090772e-05, + "loss": 0.9115, + "step": 5533 + }, + { + "epoch": 0.33972804567359344, + "grad_norm": 0.6936787352719272, + "learning_rate": 1.5376722130392572e-05, + "loss": 0.9294, + "step": 5534 + }, + { + "epoch": 0.33978943491205993, + "grad_norm": 0.6995835867386361, + "learning_rate": 1.537504553913736e-05, + "loss": 0.951, + "step": 5535 + }, + { + "epoch": 0.3398508241505264, + "grad_norm": 0.6922822459682191, + "learning_rate": 1.5373368735377847e-05, + "loss": 0.9296, + "step": 5536 + }, + { + "epoch": 0.3399122133889929, + "grad_norm": 0.6939216172599217, + "learning_rate": 1.5371691719180333e-05, + "loss": 0.9194, + "step": 5537 + }, + { + "epoch": 0.3399736026274594, + "grad_norm": 0.6778552136164626, + "learning_rate": 1.5370014490611114e-05, + "loss": 0.8702, + "step": 5538 + }, + { + "epoch": 0.3400349918659259, + "grad_norm": 0.7164412000332557, + "learning_rate": 1.5368337049736505e-05, + "loss": 0.9371, + "step": 5539 + }, + { + "epoch": 0.3400963811043924, + "grad_norm": 0.6895178985215044, + "learning_rate": 1.5366659396622813e-05, + "loss": 0.9032, + "step": 5540 + }, + { + "epoch": 0.3401577703428589, + "grad_norm": 0.7448648177581378, + "learning_rate": 1.536498153133638e-05, + "loss": 0.937, + "step": 5541 + }, + { + "epoch": 0.34021915958132537, + "grad_norm": 0.6236071619608271, + "learning_rate": 1.5363303453943527e-05, + "loss": 0.9247, + "step": 5542 + }, + { + "epoch": 0.3402805488197919, + "grad_norm": 0.6866610831649761, + "learning_rate": 1.5361625164510604e-05, + "loss": 0.9503, + "step": 5543 + }, + { + "epoch": 0.3403419380582584, + "grad_norm": 0.7092566181136385, + "learning_rate": 1.535994666310397e-05, + "loss": 0.9381, + "step": 5544 + }, + { + "epoch": 0.3404033272967249, + "grad_norm": 0.7006570806908636, + "learning_rate": 1.5358267949789968e-05, + "loss": 0.9765, + "step": 5545 + }, + { + "epoch": 0.3404647165351914, + "grad_norm": 0.620455536772322, + "learning_rate": 1.535658902463498e-05, + "loss": 0.877, + "step": 5546 + }, + { + "epoch": 0.3405261057736579, + "grad_norm": 0.6014670757096602, + "learning_rate": 1.5354909887705378e-05, + "loss": 0.8511, + "step": 5547 + }, + { + "epoch": 0.3405874950121244, + "grad_norm": 0.6973892275835146, + "learning_rate": 1.535323053906755e-05, + "loss": 0.8947, + "step": 5548 + }, + { + "epoch": 0.34064888425059087, + "grad_norm": 0.7115606270689898, + "learning_rate": 1.5351550978787882e-05, + "loss": 1.0017, + "step": 5549 + }, + { + "epoch": 0.34071027348905736, + "grad_norm": 0.71137241720868, + "learning_rate": 1.5349871206932786e-05, + "loss": 0.9273, + "step": 5550 + }, + { + "epoch": 0.34077166272752385, + "grad_norm": 0.7120040902149349, + "learning_rate": 1.534819122356867e-05, + "loss": 0.9205, + "step": 5551 + }, + { + "epoch": 0.34083305196599034, + "grad_norm": 0.6671263106567178, + "learning_rate": 1.534651102876195e-05, + "loss": 0.9109, + "step": 5552 + }, + { + "epoch": 0.34089444120445683, + "grad_norm": 0.7036939473118119, + "learning_rate": 1.534483062257905e-05, + "loss": 0.9167, + "step": 5553 + }, + { + "epoch": 0.3409558304429234, + "grad_norm": 0.6931124156833788, + "learning_rate": 1.534315000508641e-05, + "loss": 0.9207, + "step": 5554 + }, + { + "epoch": 0.34101721968138987, + "grad_norm": 0.6832149922772206, + "learning_rate": 1.5341469176350478e-05, + "loss": 0.9113, + "step": 5555 + }, + { + "epoch": 0.34107860891985636, + "grad_norm": 0.6536061963151882, + "learning_rate": 1.5339788136437698e-05, + "loss": 0.8999, + "step": 5556 + }, + { + "epoch": 0.34113999815832285, + "grad_norm": 0.6094911146738586, + "learning_rate": 1.5338106885414535e-05, + "loss": 0.9305, + "step": 5557 + }, + { + "epoch": 0.34120138739678935, + "grad_norm": 0.6594418683561295, + "learning_rate": 1.5336425423347453e-05, + "loss": 0.9162, + "step": 5558 + }, + { + "epoch": 0.34126277663525584, + "grad_norm": 0.6425682949521349, + "learning_rate": 1.5334743750302935e-05, + "loss": 0.8731, + "step": 5559 + }, + { + "epoch": 0.34132416587372233, + "grad_norm": 0.6712945121023524, + "learning_rate": 1.5333061866347464e-05, + "loss": 0.9193, + "step": 5560 + }, + { + "epoch": 0.3413855551121888, + "grad_norm": 0.7625779543950385, + "learning_rate": 1.5331379771547536e-05, + "loss": 0.9199, + "step": 5561 + }, + { + "epoch": 0.3414469443506553, + "grad_norm": 0.6529757940767729, + "learning_rate": 1.532969746596965e-05, + "loss": 0.9198, + "step": 5562 + }, + { + "epoch": 0.3415083335891218, + "grad_norm": 0.703347817272609, + "learning_rate": 1.5328014949680318e-05, + "loss": 0.9619, + "step": 5563 + }, + { + "epoch": 0.34156972282758835, + "grad_norm": 0.7633928983599031, + "learning_rate": 1.532633222274606e-05, + "loss": 0.9698, + "step": 5564 + }, + { + "epoch": 0.34163111206605484, + "grad_norm": 0.7529161711409004, + "learning_rate": 1.53246492852334e-05, + "loss": 0.9659, + "step": 5565 + }, + { + "epoch": 0.34169250130452133, + "grad_norm": 0.6808975791098318, + "learning_rate": 1.5322966137208877e-05, + "loss": 0.9374, + "step": 5566 + }, + { + "epoch": 0.3417538905429878, + "grad_norm": 0.633641541922863, + "learning_rate": 1.5321282778739035e-05, + "loss": 0.8978, + "step": 5567 + }, + { + "epoch": 0.3418152797814543, + "grad_norm": 0.6394567115031643, + "learning_rate": 1.531959920989042e-05, + "loss": 0.8896, + "step": 5568 + }, + { + "epoch": 0.3418766690199208, + "grad_norm": 0.7377198519841495, + "learning_rate": 1.5317915430729602e-05, + "loss": 0.9386, + "step": 5569 + }, + { + "epoch": 0.3419380582583873, + "grad_norm": 0.6714395979921197, + "learning_rate": 1.531623144132314e-05, + "loss": 0.9466, + "step": 5570 + }, + { + "epoch": 0.3419994474968538, + "grad_norm": 0.6080367818609037, + "learning_rate": 1.5314547241737622e-05, + "loss": 0.9053, + "step": 5571 + }, + { + "epoch": 0.3420608367353203, + "grad_norm": 0.7139053503831891, + "learning_rate": 1.5312862832039624e-05, + "loss": 0.9125, + "step": 5572 + }, + { + "epoch": 0.3421222259737868, + "grad_norm": 0.7093599814455434, + "learning_rate": 1.531117821229574e-05, + "loss": 0.9196, + "step": 5573 + }, + { + "epoch": 0.34218361521225327, + "grad_norm": 0.6603809784945923, + "learning_rate": 1.530949338257258e-05, + "loss": 0.9185, + "step": 5574 + }, + { + "epoch": 0.3422450044507198, + "grad_norm": 0.7870223325025621, + "learning_rate": 1.5307808342936747e-05, + "loss": 0.936, + "step": 5575 + }, + { + "epoch": 0.3423063936891863, + "grad_norm": 0.5986500324011139, + "learning_rate": 1.5306123093454865e-05, + "loss": 0.8833, + "step": 5576 + }, + { + "epoch": 0.3423677829276528, + "grad_norm": 0.7153582205471346, + "learning_rate": 1.530443763419355e-05, + "loss": 0.8864, + "step": 5577 + }, + { + "epoch": 0.3424291721661193, + "grad_norm": 0.7169686061324518, + "learning_rate": 1.5302751965219452e-05, + "loss": 0.9377, + "step": 5578 + }, + { + "epoch": 0.3424905614045858, + "grad_norm": 0.6529911909956957, + "learning_rate": 1.5301066086599207e-05, + "loss": 0.9276, + "step": 5579 + }, + { + "epoch": 0.34255195064305227, + "grad_norm": 0.6989013983952818, + "learning_rate": 1.5299379998399467e-05, + "loss": 0.8961, + "step": 5580 + }, + { + "epoch": 0.34261333988151876, + "grad_norm": 0.6206612631968131, + "learning_rate": 1.529769370068689e-05, + "loss": 0.8762, + "step": 5581 + }, + { + "epoch": 0.34267472911998526, + "grad_norm": 0.7497407865632681, + "learning_rate": 1.529600719352815e-05, + "loss": 0.9658, + "step": 5582 + }, + { + "epoch": 0.34273611835845175, + "grad_norm": 0.7043202701460292, + "learning_rate": 1.5294320476989923e-05, + "loss": 0.9484, + "step": 5583 + }, + { + "epoch": 0.34279750759691824, + "grad_norm": 0.7388102184330178, + "learning_rate": 1.5292633551138884e-05, + "loss": 0.9021, + "step": 5584 + }, + { + "epoch": 0.34285889683538473, + "grad_norm": 0.64804926636596, + "learning_rate": 1.5290946416041742e-05, + "loss": 0.8927, + "step": 5585 + }, + { + "epoch": 0.3429202860738513, + "grad_norm": 0.7281851860937206, + "learning_rate": 1.5289259071765182e-05, + "loss": 0.9339, + "step": 5586 + }, + { + "epoch": 0.34298167531231777, + "grad_norm": 0.7540429807028838, + "learning_rate": 1.528757151837593e-05, + "loss": 0.9151, + "step": 5587 + }, + { + "epoch": 0.34304306455078426, + "grad_norm": 0.6977856113941407, + "learning_rate": 1.528588375594069e-05, + "loss": 0.9159, + "step": 5588 + }, + { + "epoch": 0.34310445378925075, + "grad_norm": 0.6721093841908162, + "learning_rate": 1.5284195784526196e-05, + "loss": 0.8956, + "step": 5589 + }, + { + "epoch": 0.34316584302771724, + "grad_norm": 0.6787743470459298, + "learning_rate": 1.5282507604199183e-05, + "loss": 0.8739, + "step": 5590 + }, + { + "epoch": 0.34322723226618373, + "grad_norm": 0.656726516541783, + "learning_rate": 1.5280819215026388e-05, + "loss": 0.8885, + "step": 5591 + }, + { + "epoch": 0.3432886215046502, + "grad_norm": 0.6973153663639913, + "learning_rate": 1.527913061707457e-05, + "loss": 0.942, + "step": 5592 + }, + { + "epoch": 0.3433500107431167, + "grad_norm": 0.6980267642858563, + "learning_rate": 1.5277441810410478e-05, + "loss": 0.9556, + "step": 5593 + }, + { + "epoch": 0.3434113999815832, + "grad_norm": 0.7129800503486134, + "learning_rate": 1.5275752795100892e-05, + "loss": 0.8646, + "step": 5594 + }, + { + "epoch": 0.3434727892200497, + "grad_norm": 0.7334939874629195, + "learning_rate": 1.5274063571212577e-05, + "loss": 0.9726, + "step": 5595 + }, + { + "epoch": 0.34353417845851625, + "grad_norm": 0.71669202418126, + "learning_rate": 1.5272374138812324e-05, + "loss": 0.9503, + "step": 5596 + }, + { + "epoch": 0.34359556769698274, + "grad_norm": 0.6498654990963788, + "learning_rate": 1.5270684497966918e-05, + "loss": 0.9196, + "step": 5597 + }, + { + "epoch": 0.34365695693544923, + "grad_norm": 0.6702553618515342, + "learning_rate": 1.5268994648743167e-05, + "loss": 0.9082, + "step": 5598 + }, + { + "epoch": 0.3437183461739157, + "grad_norm": 0.6249176007966764, + "learning_rate": 1.526730459120788e-05, + "loss": 0.9117, + "step": 5599 + }, + { + "epoch": 0.3437797354123822, + "grad_norm": 0.6943686494983405, + "learning_rate": 1.5265614325427863e-05, + "loss": 0.9245, + "step": 5600 + }, + { + "epoch": 0.3438411246508487, + "grad_norm": 0.6764456273396372, + "learning_rate": 1.5263923851469957e-05, + "loss": 0.9274, + "step": 5601 + }, + { + "epoch": 0.3439025138893152, + "grad_norm": 0.6647602059114769, + "learning_rate": 1.5262233169400987e-05, + "loss": 0.9081, + "step": 5602 + }, + { + "epoch": 0.3439639031277817, + "grad_norm": 0.7281919475279311, + "learning_rate": 1.5260542279287792e-05, + "loss": 1.0018, + "step": 5603 + }, + { + "epoch": 0.3440252923662482, + "grad_norm": 0.661954401327459, + "learning_rate": 1.5258851181197227e-05, + "loss": 0.9047, + "step": 5604 + }, + { + "epoch": 0.3440866816047147, + "grad_norm": 0.7077002831305713, + "learning_rate": 1.525715987519615e-05, + "loss": 0.9123, + "step": 5605 + }, + { + "epoch": 0.34414807084318116, + "grad_norm": 0.7216274433592363, + "learning_rate": 1.5255468361351424e-05, + "loss": 0.9335, + "step": 5606 + }, + { + "epoch": 0.3442094600816477, + "grad_norm": 0.7248374095151886, + "learning_rate": 1.5253776639729925e-05, + "loss": 0.9539, + "step": 5607 + }, + { + "epoch": 0.3442708493201142, + "grad_norm": 0.7264641031633786, + "learning_rate": 1.5252084710398537e-05, + "loss": 0.9417, + "step": 5608 + }, + { + "epoch": 0.3443322385585807, + "grad_norm": 0.6883725860717713, + "learning_rate": 1.5250392573424152e-05, + "loss": 0.6872, + "step": 5609 + }, + { + "epoch": 0.3443936277970472, + "grad_norm": 0.7487290907597144, + "learning_rate": 1.5248700228873666e-05, + "loss": 0.9016, + "step": 5610 + }, + { + "epoch": 0.3444550170355137, + "grad_norm": 0.6359601016037634, + "learning_rate": 1.5247007676813984e-05, + "loss": 0.8803, + "step": 5611 + }, + { + "epoch": 0.34451640627398017, + "grad_norm": 0.7001481411335585, + "learning_rate": 1.5245314917312031e-05, + "loss": 0.9849, + "step": 5612 + }, + { + "epoch": 0.34457779551244666, + "grad_norm": 0.7869282570932999, + "learning_rate": 1.5243621950434723e-05, + "loss": 0.9639, + "step": 5613 + }, + { + "epoch": 0.34463918475091315, + "grad_norm": 0.7562162064397983, + "learning_rate": 1.5241928776248993e-05, + "loss": 0.9237, + "step": 5614 + }, + { + "epoch": 0.34470057398937964, + "grad_norm": 0.6819856236814191, + "learning_rate": 1.5240235394821787e-05, + "loss": 0.9135, + "step": 5615 + }, + { + "epoch": 0.34476196322784614, + "grad_norm": 0.6606551529453782, + "learning_rate": 1.5238541806220046e-05, + "loss": 0.9261, + "step": 5616 + }, + { + "epoch": 0.3448233524663127, + "grad_norm": 0.6153187693290807, + "learning_rate": 1.5236848010510733e-05, + "loss": 0.9129, + "step": 5617 + }, + { + "epoch": 0.3448847417047792, + "grad_norm": 0.6780804200813928, + "learning_rate": 1.5235154007760806e-05, + "loss": 0.9416, + "step": 5618 + }, + { + "epoch": 0.34494613094324567, + "grad_norm": 0.7369028327656875, + "learning_rate": 1.5233459798037245e-05, + "loss": 0.857, + "step": 5619 + }, + { + "epoch": 0.34500752018171216, + "grad_norm": 0.6925084461214789, + "learning_rate": 1.5231765381407021e-05, + "loss": 0.9285, + "step": 5620 + }, + { + "epoch": 0.34506890942017865, + "grad_norm": 0.7035716012738126, + "learning_rate": 1.5230070757937134e-05, + "loss": 0.963, + "step": 5621 + }, + { + "epoch": 0.34513029865864514, + "grad_norm": 0.7356540940381454, + "learning_rate": 1.5228375927694582e-05, + "loss": 0.8691, + "step": 5622 + }, + { + "epoch": 0.34519168789711163, + "grad_norm": 0.735923849635493, + "learning_rate": 1.5226680890746359e-05, + "loss": 0.9585, + "step": 5623 + }, + { + "epoch": 0.3452530771355781, + "grad_norm": 0.7297573611492143, + "learning_rate": 1.5224985647159489e-05, + "loss": 0.9537, + "step": 5624 + }, + { + "epoch": 0.3453144663740446, + "grad_norm": 0.676090249773379, + "learning_rate": 1.5223290197000993e-05, + "loss": 0.9349, + "step": 5625 + }, + { + "epoch": 0.3453758556125111, + "grad_norm": 0.6831718479154117, + "learning_rate": 1.5221594540337898e-05, + "loss": 0.9518, + "step": 5626 + }, + { + "epoch": 0.3454372448509776, + "grad_norm": 0.6421159269426224, + "learning_rate": 1.5219898677237242e-05, + "loss": 0.867, + "step": 5627 + }, + { + "epoch": 0.34549863408944415, + "grad_norm": 0.6671242931615423, + "learning_rate": 1.5218202607766077e-05, + "loss": 0.946, + "step": 5628 + }, + { + "epoch": 0.34556002332791064, + "grad_norm": 0.6444833853582821, + "learning_rate": 1.521650633199145e-05, + "loss": 0.849, + "step": 5629 + }, + { + "epoch": 0.34562141256637713, + "grad_norm": 0.6203306092547457, + "learning_rate": 1.5214809849980432e-05, + "loss": 0.9185, + "step": 5630 + }, + { + "epoch": 0.3456828018048436, + "grad_norm": 0.6622551047802617, + "learning_rate": 1.5213113161800087e-05, + "loss": 0.8523, + "step": 5631 + }, + { + "epoch": 0.3457441910433101, + "grad_norm": 0.6854646637263774, + "learning_rate": 1.5211416267517496e-05, + "loss": 0.9676, + "step": 5632 + }, + { + "epoch": 0.3458055802817766, + "grad_norm": 0.6401537127667624, + "learning_rate": 1.520971916719975e-05, + "loss": 0.9094, + "step": 5633 + }, + { + "epoch": 0.3458669695202431, + "grad_norm": 0.6528553182425785, + "learning_rate": 1.520802186091394e-05, + "loss": 0.9282, + "step": 5634 + }, + { + "epoch": 0.3459283587587096, + "grad_norm": 0.7326224705564426, + "learning_rate": 1.5206324348727175e-05, + "loss": 0.9341, + "step": 5635 + }, + { + "epoch": 0.3459897479971761, + "grad_norm": 0.6923159459777493, + "learning_rate": 1.5204626630706558e-05, + "loss": 0.8859, + "step": 5636 + }, + { + "epoch": 0.34605113723564257, + "grad_norm": 0.6652177128531673, + "learning_rate": 1.5202928706919218e-05, + "loss": 0.8918, + "step": 5637 + }, + { + "epoch": 0.34611252647410906, + "grad_norm": 0.6904344856411683, + "learning_rate": 1.5201230577432275e-05, + "loss": 0.9414, + "step": 5638 + }, + { + "epoch": 0.3461739157125756, + "grad_norm": 0.699079997239103, + "learning_rate": 1.5199532242312872e-05, + "loss": 0.9612, + "step": 5639 + }, + { + "epoch": 0.3462353049510421, + "grad_norm": 0.6697339108358767, + "learning_rate": 1.519783370162815e-05, + "loss": 0.9048, + "step": 5640 + }, + { + "epoch": 0.3462966941895086, + "grad_norm": 0.7042076904559313, + "learning_rate": 1.5196134955445261e-05, + "loss": 0.93, + "step": 5641 + }, + { + "epoch": 0.3463580834279751, + "grad_norm": 0.6924963537359302, + "learning_rate": 1.519443600383137e-05, + "loss": 0.8802, + "step": 5642 + }, + { + "epoch": 0.3464194726664416, + "grad_norm": 0.615269811161554, + "learning_rate": 1.5192736846853637e-05, + "loss": 0.9061, + "step": 5643 + }, + { + "epoch": 0.34648086190490807, + "grad_norm": 0.631919893660449, + "learning_rate": 1.5191037484579245e-05, + "loss": 0.8729, + "step": 5644 + }, + { + "epoch": 0.34654225114337456, + "grad_norm": 0.7028620879290417, + "learning_rate": 1.5189337917075379e-05, + "loss": 0.9342, + "step": 5645 + }, + { + "epoch": 0.34660364038184105, + "grad_norm": 0.6833823876719872, + "learning_rate": 1.5187638144409227e-05, + "loss": 0.9487, + "step": 5646 + }, + { + "epoch": 0.34666502962030754, + "grad_norm": 0.725334437742256, + "learning_rate": 1.5185938166648e-05, + "loss": 0.9191, + "step": 5647 + }, + { + "epoch": 0.34672641885877403, + "grad_norm": 0.6358174653922609, + "learning_rate": 1.5184237983858894e-05, + "loss": 0.9144, + "step": 5648 + }, + { + "epoch": 0.3467878080972406, + "grad_norm": 0.7432134113183968, + "learning_rate": 1.5182537596109139e-05, + "loss": 0.9228, + "step": 5649 + }, + { + "epoch": 0.34684919733570707, + "grad_norm": 0.7004628785947725, + "learning_rate": 1.5180837003465954e-05, + "loss": 0.9239, + "step": 5650 + }, + { + "epoch": 0.34691058657417356, + "grad_norm": 0.7057145770813711, + "learning_rate": 1.517913620599657e-05, + "loss": 0.8952, + "step": 5651 + }, + { + "epoch": 0.34697197581264005, + "grad_norm": 0.6356015786068946, + "learning_rate": 1.5177435203768233e-05, + "loss": 0.8735, + "step": 5652 + }, + { + "epoch": 0.34703336505110655, + "grad_norm": 0.7430988191451879, + "learning_rate": 1.5175733996848193e-05, + "loss": 0.9525, + "step": 5653 + }, + { + "epoch": 0.34709475428957304, + "grad_norm": 0.7436009839120753, + "learning_rate": 1.5174032585303703e-05, + "loss": 0.9227, + "step": 5654 + }, + { + "epoch": 0.34715614352803953, + "grad_norm": 0.6519524089197255, + "learning_rate": 1.5172330969202036e-05, + "loss": 0.8816, + "step": 5655 + }, + { + "epoch": 0.347217532766506, + "grad_norm": 0.6578464644078712, + "learning_rate": 1.5170629148610461e-05, + "loss": 0.8974, + "step": 5656 + }, + { + "epoch": 0.3472789220049725, + "grad_norm": 0.6541474385649723, + "learning_rate": 1.516892712359626e-05, + "loss": 0.8745, + "step": 5657 + }, + { + "epoch": 0.347340311243439, + "grad_norm": 0.735344819362269, + "learning_rate": 1.5167224894226726e-05, + "loss": 0.9663, + "step": 5658 + }, + { + "epoch": 0.3474017004819055, + "grad_norm": 0.7724723738723446, + "learning_rate": 1.5165522460569153e-05, + "loss": 1.0111, + "step": 5659 + }, + { + "epoch": 0.34746308972037204, + "grad_norm": 0.6849585389700683, + "learning_rate": 1.5163819822690852e-05, + "loss": 0.9107, + "step": 5660 + }, + { + "epoch": 0.34752447895883853, + "grad_norm": 0.7111440289776633, + "learning_rate": 1.5162116980659138e-05, + "loss": 0.8592, + "step": 5661 + }, + { + "epoch": 0.347585868197305, + "grad_norm": 0.6617692391638358, + "learning_rate": 1.5160413934541329e-05, + "loss": 0.9291, + "step": 5662 + }, + { + "epoch": 0.3476472574357715, + "grad_norm": 0.6853857870990658, + "learning_rate": 1.5158710684404756e-05, + "loss": 0.9125, + "step": 5663 + }, + { + "epoch": 0.347708646674238, + "grad_norm": 0.6797186466987432, + "learning_rate": 1.5157007230316757e-05, + "loss": 0.9128, + "step": 5664 + }, + { + "epoch": 0.3477700359127045, + "grad_norm": 0.7448502816428738, + "learning_rate": 1.5155303572344686e-05, + "loss": 0.9352, + "step": 5665 + }, + { + "epoch": 0.347831425151171, + "grad_norm": 0.7119314256314837, + "learning_rate": 1.5153599710555886e-05, + "loss": 0.9388, + "step": 5666 + }, + { + "epoch": 0.3478928143896375, + "grad_norm": 0.666063707304581, + "learning_rate": 1.5151895645017733e-05, + "loss": 0.8773, + "step": 5667 + }, + { + "epoch": 0.347954203628104, + "grad_norm": 0.7034862192398095, + "learning_rate": 1.5150191375797585e-05, + "loss": 0.9281, + "step": 5668 + }, + { + "epoch": 0.34801559286657047, + "grad_norm": 0.697153405430839, + "learning_rate": 1.5148486902962832e-05, + "loss": 0.918, + "step": 5669 + }, + { + "epoch": 0.348076982105037, + "grad_norm": 0.6382103725502125, + "learning_rate": 1.5146782226580849e-05, + "loss": 0.9039, + "step": 5670 + }, + { + "epoch": 0.3481383713435035, + "grad_norm": 0.6924043720132101, + "learning_rate": 1.5145077346719041e-05, + "loss": 0.8962, + "step": 5671 + }, + { + "epoch": 0.34819976058197, + "grad_norm": 0.7452015815297884, + "learning_rate": 1.514337226344481e-05, + "loss": 0.9749, + "step": 5672 + }, + { + "epoch": 0.3482611498204365, + "grad_norm": 0.8012563128364285, + "learning_rate": 1.5141666976825562e-05, + "loss": 0.9876, + "step": 5673 + }, + { + "epoch": 0.348322539058903, + "grad_norm": 0.6584116819878908, + "learning_rate": 1.5139961486928722e-05, + "loss": 0.8658, + "step": 5674 + }, + { + "epoch": 0.34838392829736947, + "grad_norm": 0.6770497390577722, + "learning_rate": 1.513825579382171e-05, + "loss": 0.8971, + "step": 5675 + }, + { + "epoch": 0.34844531753583596, + "grad_norm": 0.7157747228709632, + "learning_rate": 1.5136549897571967e-05, + "loss": 0.9378, + "step": 5676 + }, + { + "epoch": 0.34850670677430245, + "grad_norm": 0.6304352592659049, + "learning_rate": 1.5134843798246935e-05, + "loss": 0.9056, + "step": 5677 + }, + { + "epoch": 0.34856809601276895, + "grad_norm": 0.7230229426127109, + "learning_rate": 1.513313749591406e-05, + "loss": 0.9383, + "step": 5678 + }, + { + "epoch": 0.34862948525123544, + "grad_norm": 0.6778518308267318, + "learning_rate": 1.5131430990640815e-05, + "loss": 0.9422, + "step": 5679 + }, + { + "epoch": 0.34869087448970193, + "grad_norm": 0.691096352412062, + "learning_rate": 1.5129724282494649e-05, + "loss": 0.9341, + "step": 5680 + }, + { + "epoch": 0.3487522637281685, + "grad_norm": 0.7505624988005956, + "learning_rate": 1.5128017371543052e-05, + "loss": 0.9402, + "step": 5681 + }, + { + "epoch": 0.34881365296663497, + "grad_norm": 0.6913125165334315, + "learning_rate": 1.5126310257853499e-05, + "loss": 0.8793, + "step": 5682 + }, + { + "epoch": 0.34887504220510146, + "grad_norm": 0.729495236085274, + "learning_rate": 1.5124602941493485e-05, + "loss": 0.9939, + "step": 5683 + }, + { + "epoch": 0.34893643144356795, + "grad_norm": 0.6566601675822886, + "learning_rate": 1.512289542253051e-05, + "loss": 0.9447, + "step": 5684 + }, + { + "epoch": 0.34899782068203444, + "grad_norm": 0.6655561764233208, + "learning_rate": 1.5121187701032077e-05, + "loss": 0.8634, + "step": 5685 + }, + { + "epoch": 0.34905920992050093, + "grad_norm": 0.7195567922797846, + "learning_rate": 1.5119479777065704e-05, + "loss": 0.9372, + "step": 5686 + }, + { + "epoch": 0.3491205991589674, + "grad_norm": 0.7082547061650061, + "learning_rate": 1.5117771650698916e-05, + "loss": 0.8619, + "step": 5687 + }, + { + "epoch": 0.3491819883974339, + "grad_norm": 0.6172432225541551, + "learning_rate": 1.511606332199924e-05, + "loss": 0.9074, + "step": 5688 + }, + { + "epoch": 0.3492433776359004, + "grad_norm": 0.6144029864306418, + "learning_rate": 1.5114354791034225e-05, + "loss": 0.8618, + "step": 5689 + }, + { + "epoch": 0.3493047668743669, + "grad_norm": 0.6183289702444857, + "learning_rate": 1.5112646057871408e-05, + "loss": 0.7188, + "step": 5690 + }, + { + "epoch": 0.3493661561128334, + "grad_norm": 0.6863888092135387, + "learning_rate": 1.5110937122578343e-05, + "loss": 0.9209, + "step": 5691 + }, + { + "epoch": 0.34942754535129994, + "grad_norm": 0.6708512790608642, + "learning_rate": 1.5109227985222603e-05, + "loss": 0.8869, + "step": 5692 + }, + { + "epoch": 0.34948893458976643, + "grad_norm": 0.7843605842791445, + "learning_rate": 1.5107518645871757e-05, + "loss": 0.9642, + "step": 5693 + }, + { + "epoch": 0.3495503238282329, + "grad_norm": 0.6765806840831812, + "learning_rate": 1.5105809104593378e-05, + "loss": 0.8842, + "step": 5694 + }, + { + "epoch": 0.3496117130666994, + "grad_norm": 0.6392648427767444, + "learning_rate": 1.510409936145506e-05, + "loss": 0.8908, + "step": 5695 + }, + { + "epoch": 0.3496731023051659, + "grad_norm": 0.7263704362012422, + "learning_rate": 1.5102389416524392e-05, + "loss": 1.027, + "step": 5696 + }, + { + "epoch": 0.3497344915436324, + "grad_norm": 0.6683881095414084, + "learning_rate": 1.5100679269868988e-05, + "loss": 0.8792, + "step": 5697 + }, + { + "epoch": 0.3497958807820989, + "grad_norm": 0.7181746836783198, + "learning_rate": 1.5098968921556446e-05, + "loss": 0.9572, + "step": 5698 + }, + { + "epoch": 0.3498572700205654, + "grad_norm": 0.6729355384534769, + "learning_rate": 1.5097258371654392e-05, + "loss": 0.8941, + "step": 5699 + }, + { + "epoch": 0.3499186592590319, + "grad_norm": 0.6306858910533731, + "learning_rate": 1.5095547620230453e-05, + "loss": 0.9276, + "step": 5700 + }, + { + "epoch": 0.34998004849749836, + "grad_norm": 0.721556830628031, + "learning_rate": 1.5093836667352264e-05, + "loss": 0.9487, + "step": 5701 + }, + { + "epoch": 0.3500414377359649, + "grad_norm": 0.6699475755265406, + "learning_rate": 1.5092125513087468e-05, + "loss": 0.9211, + "step": 5702 + }, + { + "epoch": 0.3501028269744314, + "grad_norm": 0.6799012007224581, + "learning_rate": 1.5090414157503715e-05, + "loss": 0.8841, + "step": 5703 + }, + { + "epoch": 0.3501642162128979, + "grad_norm": 0.7090082774885926, + "learning_rate": 1.5088702600668668e-05, + "loss": 0.8897, + "step": 5704 + }, + { + "epoch": 0.3502256054513644, + "grad_norm": 0.739758620104435, + "learning_rate": 1.5086990842649984e-05, + "loss": 0.9193, + "step": 5705 + }, + { + "epoch": 0.3502869946898309, + "grad_norm": 0.7045159562075728, + "learning_rate": 1.508527888351535e-05, + "loss": 0.9921, + "step": 5706 + }, + { + "epoch": 0.35034838392829737, + "grad_norm": 0.6024691873011049, + "learning_rate": 1.5083566723332443e-05, + "loss": 0.8573, + "step": 5707 + }, + { + "epoch": 0.35040977316676386, + "grad_norm": 0.6247761702766135, + "learning_rate": 1.5081854362168955e-05, + "loss": 0.8935, + "step": 5708 + }, + { + "epoch": 0.35047116240523035, + "grad_norm": 0.6363194363223729, + "learning_rate": 1.5080141800092584e-05, + "loss": 0.9048, + "step": 5709 + }, + { + "epoch": 0.35053255164369684, + "grad_norm": 0.6839190193740802, + "learning_rate": 1.5078429037171037e-05, + "loss": 0.9321, + "step": 5710 + }, + { + "epoch": 0.35059394088216334, + "grad_norm": 0.6781806701194317, + "learning_rate": 1.507671607347203e-05, + "loss": 0.9042, + "step": 5711 + }, + { + "epoch": 0.3506553301206298, + "grad_norm": 0.7068450600600965, + "learning_rate": 1.5075002909063283e-05, + "loss": 0.9225, + "step": 5712 + }, + { + "epoch": 0.3507167193590964, + "grad_norm": 0.6574566057380129, + "learning_rate": 1.5073289544012526e-05, + "loss": 0.9089, + "step": 5713 + }, + { + "epoch": 0.35077810859756287, + "grad_norm": 0.7101196178935489, + "learning_rate": 1.5071575978387505e-05, + "loss": 0.9563, + "step": 5714 + }, + { + "epoch": 0.35083949783602936, + "grad_norm": 0.6787526084757607, + "learning_rate": 1.5069862212255957e-05, + "loss": 0.925, + "step": 5715 + }, + { + "epoch": 0.35090088707449585, + "grad_norm": 0.7702239593818396, + "learning_rate": 1.506814824568564e-05, + "loss": 0.9165, + "step": 5716 + }, + { + "epoch": 0.35096227631296234, + "grad_norm": 0.7045781464752051, + "learning_rate": 1.5066434078744316e-05, + "loss": 0.9172, + "step": 5717 + }, + { + "epoch": 0.35102366555142883, + "grad_norm": 0.6879785100363357, + "learning_rate": 1.5064719711499756e-05, + "loss": 0.9918, + "step": 5718 + }, + { + "epoch": 0.3510850547898953, + "grad_norm": 0.7174177778197619, + "learning_rate": 1.506300514401974e-05, + "loss": 0.9766, + "step": 5719 + }, + { + "epoch": 0.3511464440283618, + "grad_norm": 0.7184668291736536, + "learning_rate": 1.5061290376372052e-05, + "loss": 0.9149, + "step": 5720 + }, + { + "epoch": 0.3512078332668283, + "grad_norm": 0.6460282802158138, + "learning_rate": 1.5059575408624483e-05, + "loss": 0.8795, + "step": 5721 + }, + { + "epoch": 0.3512692225052948, + "grad_norm": 0.7457549313456944, + "learning_rate": 1.505786024084484e-05, + "loss": 0.9461, + "step": 5722 + }, + { + "epoch": 0.35133061174376135, + "grad_norm": 0.694529015048686, + "learning_rate": 1.5056144873100928e-05, + "loss": 0.8945, + "step": 5723 + }, + { + "epoch": 0.35139200098222784, + "grad_norm": 0.7019276987697448, + "learning_rate": 1.5054429305460568e-05, + "loss": 0.8789, + "step": 5724 + }, + { + "epoch": 0.35145339022069433, + "grad_norm": 0.6957287895819184, + "learning_rate": 1.5052713537991585e-05, + "loss": 0.9275, + "step": 5725 + }, + { + "epoch": 0.3515147794591608, + "grad_norm": 0.7326492770189805, + "learning_rate": 1.5050997570761814e-05, + "loss": 0.8855, + "step": 5726 + }, + { + "epoch": 0.3515761686976273, + "grad_norm": 0.6762024059191007, + "learning_rate": 1.5049281403839092e-05, + "loss": 0.9172, + "step": 5727 + }, + { + "epoch": 0.3516375579360938, + "grad_norm": 0.6614332507647659, + "learning_rate": 1.504756503729127e-05, + "loss": 0.9279, + "step": 5728 + }, + { + "epoch": 0.3516989471745603, + "grad_norm": 0.7042419098366007, + "learning_rate": 1.5045848471186206e-05, + "loss": 0.8986, + "step": 5729 + }, + { + "epoch": 0.3517603364130268, + "grad_norm": 0.6555506420856394, + "learning_rate": 1.5044131705591764e-05, + "loss": 0.8274, + "step": 5730 + }, + { + "epoch": 0.3518217256514933, + "grad_norm": 0.6954014362143079, + "learning_rate": 1.5042414740575822e-05, + "loss": 0.9538, + "step": 5731 + }, + { + "epoch": 0.35188311488995977, + "grad_norm": 0.7148638803183384, + "learning_rate": 1.5040697576206253e-05, + "loss": 0.9165, + "step": 5732 + }, + { + "epoch": 0.35194450412842626, + "grad_norm": 0.6368764894841665, + "learning_rate": 1.5038980212550951e-05, + "loss": 0.9167, + "step": 5733 + }, + { + "epoch": 0.3520058933668928, + "grad_norm": 0.6348073134934707, + "learning_rate": 1.5037262649677811e-05, + "loss": 0.8906, + "step": 5734 + }, + { + "epoch": 0.3520672826053593, + "grad_norm": 0.764984114605892, + "learning_rate": 1.5035544887654734e-05, + "loss": 0.9706, + "step": 5735 + }, + { + "epoch": 0.3521286718438258, + "grad_norm": 0.7312236778434742, + "learning_rate": 1.503382692654964e-05, + "loss": 0.9063, + "step": 5736 + }, + { + "epoch": 0.3521900610822923, + "grad_norm": 0.6500107081168839, + "learning_rate": 1.503210876643044e-05, + "loss": 0.914, + "step": 5737 + }, + { + "epoch": 0.3522514503207588, + "grad_norm": 0.7390857316950546, + "learning_rate": 1.503039040736507e-05, + "loss": 0.9415, + "step": 5738 + }, + { + "epoch": 0.35231283955922527, + "grad_norm": 0.6546511804810734, + "learning_rate": 1.5028671849421463e-05, + "loss": 0.885, + "step": 5739 + }, + { + "epoch": 0.35237422879769176, + "grad_norm": 0.6688526786650631, + "learning_rate": 1.5026953092667563e-05, + "loss": 0.9067, + "step": 5740 + }, + { + "epoch": 0.35243561803615825, + "grad_norm": 0.7243289179043227, + "learning_rate": 1.5025234137171319e-05, + "loss": 0.9487, + "step": 5741 + }, + { + "epoch": 0.35249700727462474, + "grad_norm": 0.7597088913472448, + "learning_rate": 1.5023514983000693e-05, + "loss": 0.9674, + "step": 5742 + }, + { + "epoch": 0.35255839651309123, + "grad_norm": 0.6648067131122056, + "learning_rate": 1.5021795630223655e-05, + "loss": 0.8948, + "step": 5743 + }, + { + "epoch": 0.3526197857515578, + "grad_norm": 0.6546098778439262, + "learning_rate": 1.5020076078908173e-05, + "loss": 0.9152, + "step": 5744 + }, + { + "epoch": 0.35268117499002427, + "grad_norm": 0.709359930687229, + "learning_rate": 1.5018356329122237e-05, + "loss": 0.9507, + "step": 5745 + }, + { + "epoch": 0.35274256422849076, + "grad_norm": 0.6894733164183039, + "learning_rate": 1.5016636380933833e-05, + "loss": 0.9557, + "step": 5746 + }, + { + "epoch": 0.35280395346695725, + "grad_norm": 0.6915003336543903, + "learning_rate": 1.5014916234410965e-05, + "loss": 0.9048, + "step": 5747 + }, + { + "epoch": 0.35286534270542375, + "grad_norm": 0.6862899008955132, + "learning_rate": 1.5013195889621637e-05, + "loss": 0.9344, + "step": 5748 + }, + { + "epoch": 0.35292673194389024, + "grad_norm": 0.7271008808783311, + "learning_rate": 1.501147534663386e-05, + "loss": 0.724, + "step": 5749 + }, + { + "epoch": 0.35298812118235673, + "grad_norm": 0.7683851058536311, + "learning_rate": 1.5009754605515659e-05, + "loss": 0.9358, + "step": 5750 + }, + { + "epoch": 0.3530495104208232, + "grad_norm": 0.6641563211842196, + "learning_rate": 1.5008033666335066e-05, + "loss": 0.8918, + "step": 5751 + }, + { + "epoch": 0.3531108996592897, + "grad_norm": 0.6738117927449315, + "learning_rate": 1.5006312529160119e-05, + "loss": 0.8685, + "step": 5752 + }, + { + "epoch": 0.3531722888977562, + "grad_norm": 0.6815942546974433, + "learning_rate": 1.5004591194058859e-05, + "loss": 0.9164, + "step": 5753 + }, + { + "epoch": 0.3532336781362227, + "grad_norm": 0.6393977446257937, + "learning_rate": 1.5002869661099346e-05, + "loss": 0.917, + "step": 5754 + }, + { + "epoch": 0.35329506737468924, + "grad_norm": 0.6581286435121058, + "learning_rate": 1.5001147930349635e-05, + "loss": 0.9037, + "step": 5755 + }, + { + "epoch": 0.35335645661315573, + "grad_norm": 0.6593408917857372, + "learning_rate": 1.49994260018778e-05, + "loss": 0.9254, + "step": 5756 + }, + { + "epoch": 0.3534178458516222, + "grad_norm": 0.7562049882262243, + "learning_rate": 1.4997703875751915e-05, + "loss": 0.9547, + "step": 5757 + }, + { + "epoch": 0.3534792350900887, + "grad_norm": 0.6863422957353371, + "learning_rate": 1.4995981552040069e-05, + "loss": 0.9505, + "step": 5758 + }, + { + "epoch": 0.3535406243285552, + "grad_norm": 0.6425801159487964, + "learning_rate": 1.499425903081035e-05, + "loss": 0.934, + "step": 5759 + }, + { + "epoch": 0.3536020135670217, + "grad_norm": 0.6834471968054864, + "learning_rate": 1.499253631213086e-05, + "loss": 0.9024, + "step": 5760 + }, + { + "epoch": 0.3536634028054882, + "grad_norm": 0.6609640001131024, + "learning_rate": 1.4990813396069707e-05, + "loss": 0.9041, + "step": 5761 + }, + { + "epoch": 0.3537247920439547, + "grad_norm": 0.6052369198748864, + "learning_rate": 1.498909028269501e-05, + "loss": 0.9006, + "step": 5762 + }, + { + "epoch": 0.3537861812824212, + "grad_norm": 0.7039031324370666, + "learning_rate": 1.4987366972074889e-05, + "loss": 0.9634, + "step": 5763 + }, + { + "epoch": 0.35384757052088767, + "grad_norm": 0.713939108784832, + "learning_rate": 1.4985643464277475e-05, + "loss": 0.9523, + "step": 5764 + }, + { + "epoch": 0.35390895975935416, + "grad_norm": 0.6910150683274976, + "learning_rate": 1.4983919759370913e-05, + "loss": 0.9528, + "step": 5765 + }, + { + "epoch": 0.3539703489978207, + "grad_norm": 0.6565850185024577, + "learning_rate": 1.4982195857423348e-05, + "loss": 0.948, + "step": 5766 + }, + { + "epoch": 0.3540317382362872, + "grad_norm": 0.7456607438352638, + "learning_rate": 1.498047175850293e-05, + "loss": 0.9369, + "step": 5767 + }, + { + "epoch": 0.3540931274747537, + "grad_norm": 0.6108209623841919, + "learning_rate": 1.497874746267783e-05, + "loss": 0.9206, + "step": 5768 + }, + { + "epoch": 0.3541545167132202, + "grad_norm": 0.7260943375404312, + "learning_rate": 1.4977022970016211e-05, + "loss": 0.9166, + "step": 5769 + }, + { + "epoch": 0.35421590595168667, + "grad_norm": 0.7231976149861065, + "learning_rate": 1.4975298280586257e-05, + "loss": 0.9612, + "step": 5770 + }, + { + "epoch": 0.35427729519015316, + "grad_norm": 0.6733754392884986, + "learning_rate": 1.4973573394456153e-05, + "loss": 0.9223, + "step": 5771 + }, + { + "epoch": 0.35433868442861965, + "grad_norm": 0.7243196798403009, + "learning_rate": 1.497184831169409e-05, + "loss": 0.9309, + "step": 5772 + }, + { + "epoch": 0.35440007366708615, + "grad_norm": 0.6719719031458095, + "learning_rate": 1.4970123032368275e-05, + "loss": 0.8936, + "step": 5773 + }, + { + "epoch": 0.35446146290555264, + "grad_norm": 0.7610804174556113, + "learning_rate": 1.496839755654691e-05, + "loss": 0.9503, + "step": 5774 + }, + { + "epoch": 0.35452285214401913, + "grad_norm": 0.7072562044214963, + "learning_rate": 1.4966671884298224e-05, + "loss": 0.9218, + "step": 5775 + }, + { + "epoch": 0.3545842413824857, + "grad_norm": 0.7278244480822293, + "learning_rate": 1.4964946015690427e-05, + "loss": 0.9255, + "step": 5776 + }, + { + "epoch": 0.35464563062095217, + "grad_norm": 0.7652302710091586, + "learning_rate": 1.4963219950791762e-05, + "loss": 0.9706, + "step": 5777 + }, + { + "epoch": 0.35470701985941866, + "grad_norm": 0.6951537063379353, + "learning_rate": 1.4961493689670468e-05, + "loss": 0.9019, + "step": 5778 + }, + { + "epoch": 0.35476840909788515, + "grad_norm": 0.7914868168577139, + "learning_rate": 1.4959767232394794e-05, + "loss": 0.9581, + "step": 5779 + }, + { + "epoch": 0.35482979833635164, + "grad_norm": 0.7436688187089097, + "learning_rate": 1.4958040579032992e-05, + "loss": 0.9802, + "step": 5780 + }, + { + "epoch": 0.35489118757481813, + "grad_norm": 0.698911050400324, + "learning_rate": 1.4956313729653329e-05, + "loss": 0.9244, + "step": 5781 + }, + { + "epoch": 0.3549525768132846, + "grad_norm": 0.7015351481380173, + "learning_rate": 1.4954586684324077e-05, + "loss": 0.9108, + "step": 5782 + }, + { + "epoch": 0.3550139660517511, + "grad_norm": 0.7254680615712372, + "learning_rate": 1.4952859443113514e-05, + "loss": 0.9517, + "step": 5783 + }, + { + "epoch": 0.3550753552902176, + "grad_norm": 0.6484991473819008, + "learning_rate": 1.4951132006089927e-05, + "loss": 0.8856, + "step": 5784 + }, + { + "epoch": 0.3551367445286841, + "grad_norm": 0.6989482607379897, + "learning_rate": 1.4949404373321612e-05, + "loss": 0.9261, + "step": 5785 + }, + { + "epoch": 0.3551981337671506, + "grad_norm": 0.6697124684354224, + "learning_rate": 1.4947676544876873e-05, + "loss": 0.9034, + "step": 5786 + }, + { + "epoch": 0.35525952300561714, + "grad_norm": 0.6881716633875268, + "learning_rate": 1.4945948520824012e-05, + "loss": 0.8983, + "step": 5787 + }, + { + "epoch": 0.35532091224408363, + "grad_norm": 0.7261321843840755, + "learning_rate": 1.4944220301231358e-05, + "loss": 0.9465, + "step": 5788 + }, + { + "epoch": 0.3553823014825501, + "grad_norm": 0.7484469390098006, + "learning_rate": 1.494249188616723e-05, + "loss": 0.9776, + "step": 5789 + }, + { + "epoch": 0.3554436907210166, + "grad_norm": 0.6731384225790281, + "learning_rate": 1.4940763275699966e-05, + "loss": 0.8993, + "step": 5790 + }, + { + "epoch": 0.3555050799594831, + "grad_norm": 0.6621023830751291, + "learning_rate": 1.4939034469897902e-05, + "loss": 0.9687, + "step": 5791 + }, + { + "epoch": 0.3555664691979496, + "grad_norm": 0.6969619050500445, + "learning_rate": 1.4937305468829388e-05, + "loss": 0.9158, + "step": 5792 + }, + { + "epoch": 0.3556278584364161, + "grad_norm": 0.6762535088230517, + "learning_rate": 1.4935576272562786e-05, + "loss": 0.8514, + "step": 5793 + }, + { + "epoch": 0.3556892476748826, + "grad_norm": 0.6434937758935195, + "learning_rate": 1.4933846881166454e-05, + "loss": 0.9355, + "step": 5794 + }, + { + "epoch": 0.35575063691334907, + "grad_norm": 0.652600863143705, + "learning_rate": 1.493211729470877e-05, + "loss": 0.9082, + "step": 5795 + }, + { + "epoch": 0.35581202615181556, + "grad_norm": 0.7232635558117737, + "learning_rate": 1.4930387513258108e-05, + "loss": 0.9175, + "step": 5796 + }, + { + "epoch": 0.3558734153902821, + "grad_norm": 0.6885776237754672, + "learning_rate": 1.4928657536882857e-05, + "loss": 0.9039, + "step": 5797 + }, + { + "epoch": 0.3559348046287486, + "grad_norm": 0.7109065793519583, + "learning_rate": 1.4926927365651418e-05, + "loss": 0.9271, + "step": 5798 + }, + { + "epoch": 0.3559961938672151, + "grad_norm": 0.7245622320911016, + "learning_rate": 1.4925196999632184e-05, + "loss": 0.9257, + "step": 5799 + }, + { + "epoch": 0.3560575831056816, + "grad_norm": 0.6582349432713507, + "learning_rate": 1.4923466438893575e-05, + "loss": 0.9129, + "step": 5800 + }, + { + "epoch": 0.3561189723441481, + "grad_norm": 0.6780763317537323, + "learning_rate": 1.4921735683504001e-05, + "loss": 0.9236, + "step": 5801 + }, + { + "epoch": 0.35618036158261457, + "grad_norm": 0.7480635133668868, + "learning_rate": 1.4920004733531895e-05, + "loss": 0.8731, + "step": 5802 + }, + { + "epoch": 0.35624175082108106, + "grad_norm": 0.6769739117521496, + "learning_rate": 1.4918273589045687e-05, + "loss": 0.8852, + "step": 5803 + }, + { + "epoch": 0.35630314005954755, + "grad_norm": 0.7210814259630092, + "learning_rate": 1.4916542250113818e-05, + "loss": 0.9418, + "step": 5804 + }, + { + "epoch": 0.35636452929801404, + "grad_norm": 0.7422575695291075, + "learning_rate": 1.4914810716804739e-05, + "loss": 0.9106, + "step": 5805 + }, + { + "epoch": 0.35642591853648053, + "grad_norm": 0.7156895365148618, + "learning_rate": 1.4913078989186907e-05, + "loss": 0.9209, + "step": 5806 + }, + { + "epoch": 0.356487307774947, + "grad_norm": 0.6927211782290307, + "learning_rate": 1.4911347067328788e-05, + "loss": 0.9271, + "step": 5807 + }, + { + "epoch": 0.3565486970134136, + "grad_norm": 0.6059616467670401, + "learning_rate": 1.4909614951298848e-05, + "loss": 0.7333, + "step": 5808 + }, + { + "epoch": 0.35661008625188007, + "grad_norm": 0.7124653164289888, + "learning_rate": 1.490788264116557e-05, + "loss": 0.9443, + "step": 5809 + }, + { + "epoch": 0.35667147549034656, + "grad_norm": 0.7713933554146845, + "learning_rate": 1.4906150136997443e-05, + "loss": 0.9469, + "step": 5810 + }, + { + "epoch": 0.35673286472881305, + "grad_norm": 0.6572308461680934, + "learning_rate": 1.4904417438862963e-05, + "loss": 0.9062, + "step": 5811 + }, + { + "epoch": 0.35679425396727954, + "grad_norm": 0.7684409484507232, + "learning_rate": 1.4902684546830629e-05, + "loss": 0.8924, + "step": 5812 + }, + { + "epoch": 0.35685564320574603, + "grad_norm": 0.7097802000215514, + "learning_rate": 1.4900951460968953e-05, + "loss": 0.8444, + "step": 5813 + }, + { + "epoch": 0.3569170324442125, + "grad_norm": 0.7686362095766728, + "learning_rate": 1.4899218181346453e-05, + "loss": 0.9448, + "step": 5814 + }, + { + "epoch": 0.356978421682679, + "grad_norm": 0.6232906789449749, + "learning_rate": 1.489748470803166e-05, + "loss": 0.8787, + "step": 5815 + }, + { + "epoch": 0.3570398109211455, + "grad_norm": 0.6945077966796486, + "learning_rate": 1.4895751041093099e-05, + "loss": 0.9651, + "step": 5816 + }, + { + "epoch": 0.357101200159612, + "grad_norm": 0.7306903814391695, + "learning_rate": 1.4894017180599317e-05, + "loss": 0.9492, + "step": 5817 + }, + { + "epoch": 0.3571625893980785, + "grad_norm": 0.6560148299477658, + "learning_rate": 1.489228312661886e-05, + "loss": 0.8608, + "step": 5818 + }, + { + "epoch": 0.35722397863654504, + "grad_norm": 0.6999739991623243, + "learning_rate": 1.4890548879220283e-05, + "loss": 0.9481, + "step": 5819 + }, + { + "epoch": 0.35728536787501153, + "grad_norm": 0.6832678515120241, + "learning_rate": 1.4888814438472154e-05, + "loss": 0.949, + "step": 5820 + }, + { + "epoch": 0.357346757113478, + "grad_norm": 0.7043451463031623, + "learning_rate": 1.4887079804443042e-05, + "loss": 0.9206, + "step": 5821 + }, + { + "epoch": 0.3574081463519445, + "grad_norm": 0.6857634092891451, + "learning_rate": 1.488534497720153e-05, + "loss": 0.877, + "step": 5822 + }, + { + "epoch": 0.357469535590411, + "grad_norm": 0.6701160404486106, + "learning_rate": 1.4883609956816204e-05, + "loss": 0.9182, + "step": 5823 + }, + { + "epoch": 0.3575309248288775, + "grad_norm": 0.7271971699978791, + "learning_rate": 1.4881874743355652e-05, + "loss": 0.9334, + "step": 5824 + }, + { + "epoch": 0.357592314067344, + "grad_norm": 0.7065653979888861, + "learning_rate": 1.4880139336888485e-05, + "loss": 0.8912, + "step": 5825 + }, + { + "epoch": 0.3576537033058105, + "grad_norm": 0.6058919608473208, + "learning_rate": 1.4878403737483304e-05, + "loss": 0.8149, + "step": 5826 + }, + { + "epoch": 0.35771509254427697, + "grad_norm": 0.7596426771010961, + "learning_rate": 1.4876667945208735e-05, + "loss": 0.9331, + "step": 5827 + }, + { + "epoch": 0.35777648178274346, + "grad_norm": 0.6620674128522532, + "learning_rate": 1.4874931960133403e-05, + "loss": 0.9464, + "step": 5828 + }, + { + "epoch": 0.35783787102121, + "grad_norm": 0.7636894572326608, + "learning_rate": 1.4873195782325934e-05, + "loss": 0.9069, + "step": 5829 + }, + { + "epoch": 0.3578992602596765, + "grad_norm": 0.7177329163972022, + "learning_rate": 1.4871459411854974e-05, + "loss": 0.8966, + "step": 5830 + }, + { + "epoch": 0.357960649498143, + "grad_norm": 0.6673298731228184, + "learning_rate": 1.4869722848789166e-05, + "loss": 0.901, + "step": 5831 + }, + { + "epoch": 0.3580220387366095, + "grad_norm": 0.6311363732141375, + "learning_rate": 1.4867986093197172e-05, + "loss": 0.8613, + "step": 5832 + }, + { + "epoch": 0.358083427975076, + "grad_norm": 0.7785185027069631, + "learning_rate": 1.4866249145147648e-05, + "loss": 0.9675, + "step": 5833 + }, + { + "epoch": 0.35814481721354247, + "grad_norm": 0.6356734178583922, + "learning_rate": 1.4864512004709272e-05, + "loss": 0.8801, + "step": 5834 + }, + { + "epoch": 0.35820620645200896, + "grad_norm": 0.7151489428293063, + "learning_rate": 1.4862774671950719e-05, + "loss": 0.91, + "step": 5835 + }, + { + "epoch": 0.35826759569047545, + "grad_norm": 0.7095131786748239, + "learning_rate": 1.4861037146940675e-05, + "loss": 0.9448, + "step": 5836 + }, + { + "epoch": 0.35832898492894194, + "grad_norm": 0.6661857243571769, + "learning_rate": 1.4859299429747835e-05, + "loss": 0.8824, + "step": 5837 + }, + { + "epoch": 0.35839037416740843, + "grad_norm": 0.6425913051191106, + "learning_rate": 1.4857561520440897e-05, + "loss": 0.9031, + "step": 5838 + }, + { + "epoch": 0.3584517634058749, + "grad_norm": 0.6487973320264504, + "learning_rate": 1.4855823419088576e-05, + "loss": 0.852, + "step": 5839 + }, + { + "epoch": 0.35851315264434147, + "grad_norm": 0.6590641253475691, + "learning_rate": 1.485408512575958e-05, + "loss": 0.9334, + "step": 5840 + }, + { + "epoch": 0.35857454188280796, + "grad_norm": 0.7575179979303328, + "learning_rate": 1.4852346640522636e-05, + "loss": 0.9252, + "step": 5841 + }, + { + "epoch": 0.35863593112127445, + "grad_norm": 0.6838030823036004, + "learning_rate": 1.4850607963446481e-05, + "loss": 0.8995, + "step": 5842 + }, + { + "epoch": 0.35869732035974095, + "grad_norm": 0.6787330471706617, + "learning_rate": 1.4848869094599851e-05, + "loss": 0.9289, + "step": 5843 + }, + { + "epoch": 0.35875870959820744, + "grad_norm": 0.7231895358931274, + "learning_rate": 1.484713003405149e-05, + "loss": 0.9637, + "step": 5844 + }, + { + "epoch": 0.35882009883667393, + "grad_norm": 0.6928210273691167, + "learning_rate": 1.4845390781870155e-05, + "loss": 0.8901, + "step": 5845 + }, + { + "epoch": 0.3588814880751404, + "grad_norm": 0.6728295757114807, + "learning_rate": 1.4843651338124608e-05, + "loss": 0.8628, + "step": 5846 + }, + { + "epoch": 0.3589428773136069, + "grad_norm": 0.7051634485063195, + "learning_rate": 1.4841911702883616e-05, + "loss": 0.9218, + "step": 5847 + }, + { + "epoch": 0.3590042665520734, + "grad_norm": 0.6939392263559707, + "learning_rate": 1.484017187621596e-05, + "loss": 0.9398, + "step": 5848 + }, + { + "epoch": 0.3590656557905399, + "grad_norm": 0.6489026784340437, + "learning_rate": 1.4838431858190423e-05, + "loss": 0.7783, + "step": 5849 + }, + { + "epoch": 0.35912704502900644, + "grad_norm": 0.699126947528254, + "learning_rate": 1.4836691648875796e-05, + "loss": 0.9455, + "step": 5850 + }, + { + "epoch": 0.35918843426747293, + "grad_norm": 0.6373559179286862, + "learning_rate": 1.4834951248340877e-05, + "loss": 0.8109, + "step": 5851 + }, + { + "epoch": 0.3592498235059394, + "grad_norm": 0.81195247296407, + "learning_rate": 1.483321065665448e-05, + "loss": 1.0424, + "step": 5852 + }, + { + "epoch": 0.3593112127444059, + "grad_norm": 0.7009995888680425, + "learning_rate": 1.4831469873885413e-05, + "loss": 0.8874, + "step": 5853 + }, + { + "epoch": 0.3593726019828724, + "grad_norm": 0.676726932400756, + "learning_rate": 1.4829728900102505e-05, + "loss": 0.8616, + "step": 5854 + }, + { + "epoch": 0.3594339912213389, + "grad_norm": 0.688893861333722, + "learning_rate": 1.4827987735374581e-05, + "loss": 0.8779, + "step": 5855 + }, + { + "epoch": 0.3594953804598054, + "grad_norm": 0.7500086358606921, + "learning_rate": 1.4826246379770477e-05, + "loss": 0.8823, + "step": 5856 + }, + { + "epoch": 0.3595567696982719, + "grad_norm": 0.6864020378836331, + "learning_rate": 1.4824504833359043e-05, + "loss": 0.8876, + "step": 5857 + }, + { + "epoch": 0.3596181589367384, + "grad_norm": 0.7335116016995683, + "learning_rate": 1.482276309620913e-05, + "loss": 0.894, + "step": 5858 + }, + { + "epoch": 0.35967954817520487, + "grad_norm": 0.6737501927665641, + "learning_rate": 1.4821021168389598e-05, + "loss": 0.9212, + "step": 5859 + }, + { + "epoch": 0.35974093741367136, + "grad_norm": 0.6677834118744113, + "learning_rate": 1.4819279049969314e-05, + "loss": 0.9142, + "step": 5860 + }, + { + "epoch": 0.3598023266521379, + "grad_norm": 0.7346310641775177, + "learning_rate": 1.4817536741017153e-05, + "loss": 0.8702, + "step": 5861 + }, + { + "epoch": 0.3598637158906044, + "grad_norm": 0.7101228679258756, + "learning_rate": 1.4815794241602001e-05, + "loss": 0.8935, + "step": 5862 + }, + { + "epoch": 0.3599251051290709, + "grad_norm": 0.7345073976206759, + "learning_rate": 1.4814051551792746e-05, + "loss": 0.9474, + "step": 5863 + }, + { + "epoch": 0.3599864943675374, + "grad_norm": 0.7533559259567503, + "learning_rate": 1.4812308671658285e-05, + "loss": 0.922, + "step": 5864 + }, + { + "epoch": 0.36004788360600387, + "grad_norm": 0.746433835398899, + "learning_rate": 1.4810565601267521e-05, + "loss": 0.9308, + "step": 5865 + }, + { + "epoch": 0.36010927284447036, + "grad_norm": 0.6793971992429627, + "learning_rate": 1.4808822340689375e-05, + "loss": 0.9026, + "step": 5866 + }, + { + "epoch": 0.36017066208293685, + "grad_norm": 0.6885365889747144, + "learning_rate": 1.4807078889992758e-05, + "loss": 0.9268, + "step": 5867 + }, + { + "epoch": 0.36023205132140335, + "grad_norm": 0.7238584842801016, + "learning_rate": 1.4805335249246603e-05, + "loss": 0.8887, + "step": 5868 + }, + { + "epoch": 0.36029344055986984, + "grad_norm": 0.6753049757038727, + "learning_rate": 1.4803591418519849e-05, + "loss": 0.9046, + "step": 5869 + }, + { + "epoch": 0.36035482979833633, + "grad_norm": 0.7239644961560665, + "learning_rate": 1.4801847397881433e-05, + "loss": 0.8881, + "step": 5870 + }, + { + "epoch": 0.3604162190368029, + "grad_norm": 0.642407649069458, + "learning_rate": 1.4800103187400308e-05, + "loss": 0.8957, + "step": 5871 + }, + { + "epoch": 0.36047760827526937, + "grad_norm": 0.7155434952193902, + "learning_rate": 1.4798358787145428e-05, + "loss": 0.9689, + "step": 5872 + }, + { + "epoch": 0.36053899751373586, + "grad_norm": 0.716298224981986, + "learning_rate": 1.4796614197185763e-05, + "loss": 0.9014, + "step": 5873 + }, + { + "epoch": 0.36060038675220235, + "grad_norm": 0.7489888208906557, + "learning_rate": 1.4794869417590287e-05, + "loss": 0.9452, + "step": 5874 + }, + { + "epoch": 0.36066177599066884, + "grad_norm": 0.6966983074653216, + "learning_rate": 1.4793124448427975e-05, + "loss": 0.941, + "step": 5875 + }, + { + "epoch": 0.36072316522913533, + "grad_norm": 0.691510658984018, + "learning_rate": 1.479137928976782e-05, + "loss": 0.9073, + "step": 5876 + }, + { + "epoch": 0.3607845544676018, + "grad_norm": 0.582116603227221, + "learning_rate": 1.4789633941678813e-05, + "loss": 0.8527, + "step": 5877 + }, + { + "epoch": 0.3608459437060683, + "grad_norm": 0.6818561759740249, + "learning_rate": 1.4787888404229964e-05, + "loss": 0.8865, + "step": 5878 + }, + { + "epoch": 0.3609073329445348, + "grad_norm": 0.6883926160049308, + "learning_rate": 1.4786142677490276e-05, + "loss": 0.8942, + "step": 5879 + }, + { + "epoch": 0.3609687221830013, + "grad_norm": 0.6360658377698412, + "learning_rate": 1.4784396761528772e-05, + "loss": 0.8738, + "step": 5880 + }, + { + "epoch": 0.3610301114214678, + "grad_norm": 0.7334577428249319, + "learning_rate": 1.4782650656414472e-05, + "loss": 0.9745, + "step": 5881 + }, + { + "epoch": 0.36109150065993434, + "grad_norm": 0.7031369210737756, + "learning_rate": 1.4780904362216415e-05, + "loss": 0.9085, + "step": 5882 + }, + { + "epoch": 0.36115288989840083, + "grad_norm": 0.7177007274442601, + "learning_rate": 1.4779157879003636e-05, + "loss": 0.9222, + "step": 5883 + }, + { + "epoch": 0.3612142791368673, + "grad_norm": 0.7056049742105558, + "learning_rate": 1.4777411206845187e-05, + "loss": 0.8925, + "step": 5884 + }, + { + "epoch": 0.3612756683753338, + "grad_norm": 0.6502112793068342, + "learning_rate": 1.4775664345810121e-05, + "loss": 0.8836, + "step": 5885 + }, + { + "epoch": 0.3613370576138003, + "grad_norm": 0.662336562473544, + "learning_rate": 1.4773917295967502e-05, + "loss": 0.9477, + "step": 5886 + }, + { + "epoch": 0.3613984468522668, + "grad_norm": 0.7425393342426696, + "learning_rate": 1.47721700573864e-05, + "loss": 0.9408, + "step": 5887 + }, + { + "epoch": 0.3614598360907333, + "grad_norm": 0.7358809752754332, + "learning_rate": 1.477042263013589e-05, + "loss": 0.9107, + "step": 5888 + }, + { + "epoch": 0.3615212253291998, + "grad_norm": 0.7010177706674658, + "learning_rate": 1.4768675014285063e-05, + "loss": 0.9177, + "step": 5889 + }, + { + "epoch": 0.36158261456766627, + "grad_norm": 0.7848676789935618, + "learning_rate": 1.4766927209903004e-05, + "loss": 0.9977, + "step": 5890 + }, + { + "epoch": 0.36164400380613276, + "grad_norm": 0.6318377450351307, + "learning_rate": 1.4765179217058818e-05, + "loss": 0.8586, + "step": 5891 + }, + { + "epoch": 0.36170539304459925, + "grad_norm": 0.6804760884833584, + "learning_rate": 1.4763431035821614e-05, + "loss": 0.908, + "step": 5892 + }, + { + "epoch": 0.3617667822830658, + "grad_norm": 0.6817703036888783, + "learning_rate": 1.4761682666260503e-05, + "loss": 0.928, + "step": 5893 + }, + { + "epoch": 0.3618281715215323, + "grad_norm": 0.7343693855330721, + "learning_rate": 1.475993410844461e-05, + "loss": 0.9531, + "step": 5894 + }, + { + "epoch": 0.3618895607599988, + "grad_norm": 0.7373495160266839, + "learning_rate": 1.4758185362443063e-05, + "loss": 0.9186, + "step": 5895 + }, + { + "epoch": 0.3619509499984653, + "grad_norm": 0.6947037715122495, + "learning_rate": 1.4756436428325e-05, + "loss": 0.9052, + "step": 5896 + }, + { + "epoch": 0.36201233923693177, + "grad_norm": 0.6720917984555754, + "learning_rate": 1.4754687306159565e-05, + "loss": 0.8956, + "step": 5897 + }, + { + "epoch": 0.36207372847539826, + "grad_norm": 0.7088899403993891, + "learning_rate": 1.475293799601591e-05, + "loss": 0.8778, + "step": 5898 + }, + { + "epoch": 0.36213511771386475, + "grad_norm": 0.6291956472346103, + "learning_rate": 1.4751188497963198e-05, + "loss": 0.7055, + "step": 5899 + }, + { + "epoch": 0.36219650695233124, + "grad_norm": 0.6668790026261273, + "learning_rate": 1.474943881207059e-05, + "loss": 0.9022, + "step": 5900 + }, + { + "epoch": 0.36225789619079773, + "grad_norm": 0.7462228175575452, + "learning_rate": 1.474768893840727e-05, + "loss": 0.8906, + "step": 5901 + }, + { + "epoch": 0.3623192854292642, + "grad_norm": 0.660245126398492, + "learning_rate": 1.474593887704241e-05, + "loss": 0.9093, + "step": 5902 + }, + { + "epoch": 0.3623806746677308, + "grad_norm": 0.6472493589527427, + "learning_rate": 1.4744188628045204e-05, + "loss": 0.9091, + "step": 5903 + }, + { + "epoch": 0.36244206390619726, + "grad_norm": 0.7410623211678934, + "learning_rate": 1.4742438191484847e-05, + "loss": 0.9454, + "step": 5904 + }, + { + "epoch": 0.36250345314466376, + "grad_norm": 0.6717787770214969, + "learning_rate": 1.4740687567430545e-05, + "loss": 0.9446, + "step": 5905 + }, + { + "epoch": 0.36256484238313025, + "grad_norm": 0.7341138437093239, + "learning_rate": 1.4738936755951507e-05, + "loss": 0.9266, + "step": 5906 + }, + { + "epoch": 0.36262623162159674, + "grad_norm": 0.7123649531139301, + "learning_rate": 1.4737185757116955e-05, + "loss": 0.9122, + "step": 5907 + }, + { + "epoch": 0.36268762086006323, + "grad_norm": 0.7702396163868427, + "learning_rate": 1.4735434570996115e-05, + "loss": 1.0034, + "step": 5908 + }, + { + "epoch": 0.3627490100985297, + "grad_norm": 0.7798246997198504, + "learning_rate": 1.4733683197658216e-05, + "loss": 0.9542, + "step": 5909 + }, + { + "epoch": 0.3628103993369962, + "grad_norm": 0.6692074251008929, + "learning_rate": 1.4731931637172503e-05, + "loss": 0.8894, + "step": 5910 + }, + { + "epoch": 0.3628717885754627, + "grad_norm": 0.6769929708557112, + "learning_rate": 1.4730179889608227e-05, + "loss": 0.9656, + "step": 5911 + }, + { + "epoch": 0.3629331778139292, + "grad_norm": 0.6933271847792396, + "learning_rate": 1.4728427955034639e-05, + "loss": 0.9274, + "step": 5912 + }, + { + "epoch": 0.3629945670523957, + "grad_norm": 0.5811121008608956, + "learning_rate": 1.4726675833521004e-05, + "loss": 0.8738, + "step": 5913 + }, + { + "epoch": 0.36305595629086224, + "grad_norm": 0.6906127470380575, + "learning_rate": 1.4724923525136597e-05, + "loss": 0.8999, + "step": 5914 + }, + { + "epoch": 0.36311734552932873, + "grad_norm": 0.6656799990425679, + "learning_rate": 1.4723171029950688e-05, + "loss": 0.8973, + "step": 5915 + }, + { + "epoch": 0.3631787347677952, + "grad_norm": 0.6716357893603964, + "learning_rate": 1.4721418348032569e-05, + "loss": 0.8686, + "step": 5916 + }, + { + "epoch": 0.3632401240062617, + "grad_norm": 0.6972230304364613, + "learning_rate": 1.4719665479451531e-05, + "loss": 0.892, + "step": 5917 + }, + { + "epoch": 0.3633015132447282, + "grad_norm": 0.7440291786369335, + "learning_rate": 1.4717912424276872e-05, + "loss": 0.921, + "step": 5918 + }, + { + "epoch": 0.3633629024831947, + "grad_norm": 0.6804525061265229, + "learning_rate": 1.4716159182577905e-05, + "loss": 0.8278, + "step": 5919 + }, + { + "epoch": 0.3634242917216612, + "grad_norm": 0.7087318793938839, + "learning_rate": 1.4714405754423938e-05, + "loss": 0.8809, + "step": 5920 + }, + { + "epoch": 0.3634856809601277, + "grad_norm": 0.7430194790643726, + "learning_rate": 1.47126521398843e-05, + "loss": 0.9164, + "step": 5921 + }, + { + "epoch": 0.36354707019859417, + "grad_norm": 0.6591769859961149, + "learning_rate": 1.4710898339028316e-05, + "loss": 0.8552, + "step": 5922 + }, + { + "epoch": 0.36360845943706066, + "grad_norm": 0.6756907618996233, + "learning_rate": 1.4709144351925327e-05, + "loss": 0.9081, + "step": 5923 + }, + { + "epoch": 0.3636698486755272, + "grad_norm": 0.7815450058684047, + "learning_rate": 1.4707390178644673e-05, + "loss": 0.938, + "step": 5924 + }, + { + "epoch": 0.3637312379139937, + "grad_norm": 0.6875779246541295, + "learning_rate": 1.470563581925571e-05, + "loss": 0.8559, + "step": 5925 + }, + { + "epoch": 0.3637926271524602, + "grad_norm": 0.6874561038211322, + "learning_rate": 1.4703881273827798e-05, + "loss": 0.9087, + "step": 5926 + }, + { + "epoch": 0.3638540163909267, + "grad_norm": 0.7273161329699872, + "learning_rate": 1.4702126542430298e-05, + "loss": 0.9097, + "step": 5927 + }, + { + "epoch": 0.3639154056293932, + "grad_norm": 0.687365289118007, + "learning_rate": 1.4700371625132588e-05, + "loss": 0.9137, + "step": 5928 + }, + { + "epoch": 0.36397679486785967, + "grad_norm": 0.7809079421583098, + "learning_rate": 1.4698616522004046e-05, + "loss": 0.9441, + "step": 5929 + }, + { + "epoch": 0.36403818410632616, + "grad_norm": 0.7009202393323134, + "learning_rate": 1.4696861233114067e-05, + "loss": 0.8914, + "step": 5930 + }, + { + "epoch": 0.36409957334479265, + "grad_norm": 0.7434256258716322, + "learning_rate": 1.469510575853204e-05, + "loss": 0.9035, + "step": 5931 + }, + { + "epoch": 0.36416096258325914, + "grad_norm": 0.6773558289525548, + "learning_rate": 1.469335009832737e-05, + "loss": 0.8757, + "step": 5932 + }, + { + "epoch": 0.36422235182172563, + "grad_norm": 0.6459712802893327, + "learning_rate": 1.4691594252569472e-05, + "loss": 0.7333, + "step": 5933 + }, + { + "epoch": 0.3642837410601921, + "grad_norm": 0.6652974835938568, + "learning_rate": 1.468983822132776e-05, + "loss": 0.9041, + "step": 5934 + }, + { + "epoch": 0.36434513029865867, + "grad_norm": 0.7692803760992449, + "learning_rate": 1.4688082004671658e-05, + "loss": 0.9466, + "step": 5935 + }, + { + "epoch": 0.36440651953712516, + "grad_norm": 0.6749972314952559, + "learning_rate": 1.4686325602670602e-05, + "loss": 0.8631, + "step": 5936 + }, + { + "epoch": 0.36446790877559165, + "grad_norm": 0.7885402255654737, + "learning_rate": 1.468456901539403e-05, + "loss": 0.9263, + "step": 5937 + }, + { + "epoch": 0.36452929801405815, + "grad_norm": 0.6673004585145277, + "learning_rate": 1.4682812242911393e-05, + "loss": 0.8988, + "step": 5938 + }, + { + "epoch": 0.36459068725252464, + "grad_norm": 0.7372030714675794, + "learning_rate": 1.4681055285292138e-05, + "loss": 0.9705, + "step": 5939 + }, + { + "epoch": 0.36465207649099113, + "grad_norm": 0.7238348826561074, + "learning_rate": 1.4679298142605735e-05, + "loss": 0.9444, + "step": 5940 + }, + { + "epoch": 0.3647134657294576, + "grad_norm": 0.7014746631622784, + "learning_rate": 1.467754081492165e-05, + "loss": 0.9207, + "step": 5941 + }, + { + "epoch": 0.3647748549679241, + "grad_norm": 0.6238235154492354, + "learning_rate": 1.4675783302309357e-05, + "loss": 0.8749, + "step": 5942 + }, + { + "epoch": 0.3648362442063906, + "grad_norm": 0.7012879899059918, + "learning_rate": 1.4674025604838344e-05, + "loss": 0.9528, + "step": 5943 + }, + { + "epoch": 0.3648976334448571, + "grad_norm": 0.7372667819612484, + "learning_rate": 1.46722677225781e-05, + "loss": 0.8668, + "step": 5944 + }, + { + "epoch": 0.3649590226833236, + "grad_norm": 0.6716296426543885, + "learning_rate": 1.4670509655598123e-05, + "loss": 0.9166, + "step": 5945 + }, + { + "epoch": 0.36502041192179013, + "grad_norm": 0.7993007409380217, + "learning_rate": 1.466875140396792e-05, + "loss": 0.9132, + "step": 5946 + }, + { + "epoch": 0.3650818011602566, + "grad_norm": 0.6420882135383146, + "learning_rate": 1.4666992967757003e-05, + "loss": 0.8493, + "step": 5947 + }, + { + "epoch": 0.3651431903987231, + "grad_norm": 0.7276541192350732, + "learning_rate": 1.4665234347034895e-05, + "loss": 0.8975, + "step": 5948 + }, + { + "epoch": 0.3652045796371896, + "grad_norm": 0.7250881428020401, + "learning_rate": 1.4663475541871121e-05, + "loss": 0.9286, + "step": 5949 + }, + { + "epoch": 0.3652659688756561, + "grad_norm": 0.6915813804985581, + "learning_rate": 1.4661716552335219e-05, + "loss": 0.9309, + "step": 5950 + }, + { + "epoch": 0.3653273581141226, + "grad_norm": 0.6696880348672853, + "learning_rate": 1.4659957378496726e-05, + "loss": 0.8889, + "step": 5951 + }, + { + "epoch": 0.3653887473525891, + "grad_norm": 0.752606039355379, + "learning_rate": 1.4658198020425194e-05, + "loss": 0.8948, + "step": 5952 + }, + { + "epoch": 0.3654501365910556, + "grad_norm": 0.6920584762952071, + "learning_rate": 1.4656438478190185e-05, + "loss": 0.9217, + "step": 5953 + }, + { + "epoch": 0.36551152582952207, + "grad_norm": 0.6185657543184581, + "learning_rate": 1.4654678751861254e-05, + "loss": 0.8538, + "step": 5954 + }, + { + "epoch": 0.36557291506798856, + "grad_norm": 0.6866279951468655, + "learning_rate": 1.4652918841507977e-05, + "loss": 0.8901, + "step": 5955 + }, + { + "epoch": 0.3656343043064551, + "grad_norm": 0.7188459880539706, + "learning_rate": 1.4651158747199936e-05, + "loss": 0.9109, + "step": 5956 + }, + { + "epoch": 0.3656956935449216, + "grad_norm": 0.6913645338278799, + "learning_rate": 1.4649398469006709e-05, + "loss": 0.9049, + "step": 5957 + }, + { + "epoch": 0.3657570827833881, + "grad_norm": 0.6534300769788329, + "learning_rate": 1.4647638006997899e-05, + "loss": 0.944, + "step": 5958 + }, + { + "epoch": 0.3658184720218546, + "grad_norm": 0.7277362500825134, + "learning_rate": 1.4645877361243098e-05, + "loss": 0.9376, + "step": 5959 + }, + { + "epoch": 0.36587986126032107, + "grad_norm": 0.6644242725149327, + "learning_rate": 1.4644116531811921e-05, + "loss": 0.9187, + "step": 5960 + }, + { + "epoch": 0.36594125049878756, + "grad_norm": 0.6780286343836744, + "learning_rate": 1.4642355518773973e-05, + "loss": 0.904, + "step": 5961 + }, + { + "epoch": 0.36600263973725405, + "grad_norm": 0.6978048817860898, + "learning_rate": 1.4640594322198884e-05, + "loss": 0.9245, + "step": 5962 + }, + { + "epoch": 0.36606402897572055, + "grad_norm": 0.6607264621499342, + "learning_rate": 1.4638832942156284e-05, + "loss": 0.9059, + "step": 5963 + }, + { + "epoch": 0.36612541821418704, + "grad_norm": 0.7048333329857259, + "learning_rate": 1.4637071378715807e-05, + "loss": 0.9168, + "step": 5964 + }, + { + "epoch": 0.36618680745265353, + "grad_norm": 0.7329922721460131, + "learning_rate": 1.4635309631947099e-05, + "loss": 0.9762, + "step": 5965 + }, + { + "epoch": 0.36624819669112, + "grad_norm": 0.6965926012578156, + "learning_rate": 1.4633547701919803e-05, + "loss": 0.9286, + "step": 5966 + }, + { + "epoch": 0.36630958592958657, + "grad_norm": 0.6379463976519655, + "learning_rate": 1.463178558870359e-05, + "loss": 0.8946, + "step": 5967 + }, + { + "epoch": 0.36637097516805306, + "grad_norm": 0.7259838625169946, + "learning_rate": 1.4630023292368121e-05, + "loss": 0.956, + "step": 5968 + }, + { + "epoch": 0.36643236440651955, + "grad_norm": 0.7811318789898049, + "learning_rate": 1.4628260812983066e-05, + "loss": 0.9387, + "step": 5969 + }, + { + "epoch": 0.36649375364498604, + "grad_norm": 0.7081831481808837, + "learning_rate": 1.4626498150618109e-05, + "loss": 0.8717, + "step": 5970 + }, + { + "epoch": 0.36655514288345253, + "grad_norm": 0.7624495490802976, + "learning_rate": 1.4624735305342934e-05, + "loss": 0.9259, + "step": 5971 + }, + { + "epoch": 0.366616532121919, + "grad_norm": 0.7270190460854893, + "learning_rate": 1.4622972277227242e-05, + "loss": 0.92, + "step": 5972 + }, + { + "epoch": 0.3666779213603855, + "grad_norm": 0.6989367646467175, + "learning_rate": 1.4621209066340724e-05, + "loss": 0.9427, + "step": 5973 + }, + { + "epoch": 0.366739310598852, + "grad_norm": 0.6954224373025473, + "learning_rate": 1.4619445672753099e-05, + "loss": 0.9441, + "step": 5974 + }, + { + "epoch": 0.3668006998373185, + "grad_norm": 0.6477866142905535, + "learning_rate": 1.461768209653408e-05, + "loss": 0.8893, + "step": 5975 + }, + { + "epoch": 0.366862089075785, + "grad_norm": 0.6959109461985814, + "learning_rate": 1.461591833775339e-05, + "loss": 0.9255, + "step": 5976 + }, + { + "epoch": 0.36692347831425154, + "grad_norm": 0.7847159760225704, + "learning_rate": 1.4614154396480761e-05, + "loss": 0.9438, + "step": 5977 + }, + { + "epoch": 0.36698486755271803, + "grad_norm": 0.7479387859657584, + "learning_rate": 1.4612390272785927e-05, + "loss": 0.968, + "step": 5978 + }, + { + "epoch": 0.3670462567911845, + "grad_norm": 0.7648353284162173, + "learning_rate": 1.4610625966738642e-05, + "loss": 0.9632, + "step": 5979 + }, + { + "epoch": 0.367107646029651, + "grad_norm": 0.7529342895687346, + "learning_rate": 1.4608861478408652e-05, + "loss": 0.8936, + "step": 5980 + }, + { + "epoch": 0.3671690352681175, + "grad_norm": 0.6336518317404194, + "learning_rate": 1.4607096807865717e-05, + "loss": 0.903, + "step": 5981 + }, + { + "epoch": 0.367230424506584, + "grad_norm": 0.7616907792083256, + "learning_rate": 1.4605331955179605e-05, + "loss": 0.9203, + "step": 5982 + }, + { + "epoch": 0.3672918137450505, + "grad_norm": 0.6260973245042829, + "learning_rate": 1.4603566920420089e-05, + "loss": 0.748, + "step": 5983 + }, + { + "epoch": 0.367353202983517, + "grad_norm": 0.7116733294922979, + "learning_rate": 1.460180170365695e-05, + "loss": 0.9133, + "step": 5984 + }, + { + "epoch": 0.36741459222198347, + "grad_norm": 0.7056713699791682, + "learning_rate": 1.4600036304959978e-05, + "loss": 0.8702, + "step": 5985 + }, + { + "epoch": 0.36747598146044996, + "grad_norm": 0.7122788444538583, + "learning_rate": 1.459827072439897e-05, + "loss": 0.9237, + "step": 5986 + }, + { + "epoch": 0.36753737069891645, + "grad_norm": 0.726164454676571, + "learning_rate": 1.4596504962043727e-05, + "loss": 0.9247, + "step": 5987 + }, + { + "epoch": 0.367598759937383, + "grad_norm": 0.6684545237979751, + "learning_rate": 1.4594739017964057e-05, + "loss": 0.8984, + "step": 5988 + }, + { + "epoch": 0.3676601491758495, + "grad_norm": 0.7210215163905387, + "learning_rate": 1.4592972892229779e-05, + "loss": 0.9433, + "step": 5989 + }, + { + "epoch": 0.367721538414316, + "grad_norm": 0.7027963887426609, + "learning_rate": 1.4591206584910723e-05, + "loss": 0.8884, + "step": 5990 + }, + { + "epoch": 0.3677829276527825, + "grad_norm": 0.606212575940477, + "learning_rate": 1.4589440096076708e-05, + "loss": 0.8975, + "step": 5991 + }, + { + "epoch": 0.36784431689124897, + "grad_norm": 0.6752421292442065, + "learning_rate": 1.4587673425797585e-05, + "loss": 0.9104, + "step": 5992 + }, + { + "epoch": 0.36790570612971546, + "grad_norm": 0.6798252504124913, + "learning_rate": 1.458590657414319e-05, + "loss": 0.9236, + "step": 5993 + }, + { + "epoch": 0.36796709536818195, + "grad_norm": 0.7726637574459895, + "learning_rate": 1.4584139541183383e-05, + "loss": 0.9237, + "step": 5994 + }, + { + "epoch": 0.36802848460664844, + "grad_norm": 0.6426319695198928, + "learning_rate": 1.4582372326988026e-05, + "loss": 0.8793, + "step": 5995 + }, + { + "epoch": 0.36808987384511493, + "grad_norm": 0.6691564949554807, + "learning_rate": 1.4580604931626978e-05, + "loss": 0.9047, + "step": 5996 + }, + { + "epoch": 0.3681512630835814, + "grad_norm": 0.6707795327785024, + "learning_rate": 1.4578837355170122e-05, + "loss": 0.8922, + "step": 5997 + }, + { + "epoch": 0.3682126523220479, + "grad_norm": 0.6818865668303549, + "learning_rate": 1.4577069597687332e-05, + "loss": 0.9403, + "step": 5998 + }, + { + "epoch": 0.36827404156051446, + "grad_norm": 0.7297557627886736, + "learning_rate": 1.4575301659248504e-05, + "loss": 0.9077, + "step": 5999 + }, + { + "epoch": 0.36833543079898096, + "grad_norm": 0.6768712818674739, + "learning_rate": 1.457353353992353e-05, + "loss": 0.9466, + "step": 6000 + }, + { + "epoch": 0.36839682003744745, + "grad_norm": 0.6829795207103663, + "learning_rate": 1.4571765239782314e-05, + "loss": 0.9024, + "step": 6001 + }, + { + "epoch": 0.36845820927591394, + "grad_norm": 0.7538086287353158, + "learning_rate": 1.4569996758894766e-05, + "loss": 0.9164, + "step": 6002 + }, + { + "epoch": 0.36851959851438043, + "grad_norm": 0.6654134758801596, + "learning_rate": 1.4568228097330805e-05, + "loss": 0.8924, + "step": 6003 + }, + { + "epoch": 0.3685809877528469, + "grad_norm": 0.7190558810546066, + "learning_rate": 1.4566459255160354e-05, + "loss": 0.9312, + "step": 6004 + }, + { + "epoch": 0.3686423769913134, + "grad_norm": 0.712933395268122, + "learning_rate": 1.4564690232453346e-05, + "loss": 0.9712, + "step": 6005 + }, + { + "epoch": 0.3687037662297799, + "grad_norm": 0.7653625587237232, + "learning_rate": 1.456292102927972e-05, + "loss": 0.9183, + "step": 6006 + }, + { + "epoch": 0.3687651554682464, + "grad_norm": 0.7119725737777391, + "learning_rate": 1.4561151645709421e-05, + "loss": 0.947, + "step": 6007 + }, + { + "epoch": 0.3688265447067129, + "grad_norm": 0.6277595257772685, + "learning_rate": 1.4559382081812402e-05, + "loss": 0.8895, + "step": 6008 + }, + { + "epoch": 0.36888793394517944, + "grad_norm": 0.7132585519938481, + "learning_rate": 1.4557612337658626e-05, + "loss": 0.9498, + "step": 6009 + }, + { + "epoch": 0.3689493231836459, + "grad_norm": 0.671964056659167, + "learning_rate": 1.4555842413318055e-05, + "loss": 0.969, + "step": 6010 + }, + { + "epoch": 0.3690107124221124, + "grad_norm": 0.6821957519550038, + "learning_rate": 1.455407230886067e-05, + "loss": 0.8976, + "step": 6011 + }, + { + "epoch": 0.3690721016605789, + "grad_norm": 0.6551124614229843, + "learning_rate": 1.4552302024356448e-05, + "loss": 0.8979, + "step": 6012 + }, + { + "epoch": 0.3691334908990454, + "grad_norm": 0.7143981578816696, + "learning_rate": 1.455053155987538e-05, + "loss": 0.9236, + "step": 6013 + }, + { + "epoch": 0.3691948801375119, + "grad_norm": 0.6872588550179694, + "learning_rate": 1.4548760915487463e-05, + "loss": 0.9374, + "step": 6014 + }, + { + "epoch": 0.3692562693759784, + "grad_norm": 0.6373205648737327, + "learning_rate": 1.4546990091262698e-05, + "loss": 0.8866, + "step": 6015 + }, + { + "epoch": 0.3693176586144449, + "grad_norm": 0.794313100875128, + "learning_rate": 1.4545219087271093e-05, + "loss": 0.9485, + "step": 6016 + }, + { + "epoch": 0.36937904785291137, + "grad_norm": 0.723620803150927, + "learning_rate": 1.454344790358267e-05, + "loss": 0.9663, + "step": 6017 + }, + { + "epoch": 0.36944043709137786, + "grad_norm": 0.659130817422956, + "learning_rate": 1.4541676540267452e-05, + "loss": 0.8673, + "step": 6018 + }, + { + "epoch": 0.36950182632984435, + "grad_norm": 0.7340551479898768, + "learning_rate": 1.4539904997395468e-05, + "loss": 0.9313, + "step": 6019 + }, + { + "epoch": 0.3695632155683109, + "grad_norm": 0.6920479095557974, + "learning_rate": 1.453813327503676e-05, + "loss": 0.9316, + "step": 6020 + }, + { + "epoch": 0.3696246048067774, + "grad_norm": 0.6686768873568256, + "learning_rate": 1.4536361373261372e-05, + "loss": 0.9338, + "step": 6021 + }, + { + "epoch": 0.3696859940452439, + "grad_norm": 0.7311406062224252, + "learning_rate": 1.4534589292139356e-05, + "loss": 0.8786, + "step": 6022 + }, + { + "epoch": 0.3697473832837104, + "grad_norm": 0.7012409897955976, + "learning_rate": 1.4532817031740773e-05, + "loss": 0.928, + "step": 6023 + }, + { + "epoch": 0.36980877252217687, + "grad_norm": 0.6913391826454067, + "learning_rate": 1.453104459213569e-05, + "loss": 0.9251, + "step": 6024 + }, + { + "epoch": 0.36987016176064336, + "grad_norm": 0.6910299734312065, + "learning_rate": 1.4529271973394178e-05, + "loss": 0.845, + "step": 6025 + }, + { + "epoch": 0.36993155099910985, + "grad_norm": 0.7344008636986913, + "learning_rate": 1.4527499175586323e-05, + "loss": 0.95, + "step": 6026 + }, + { + "epoch": 0.36999294023757634, + "grad_norm": 0.7429303774460592, + "learning_rate": 1.452572619878221e-05, + "loss": 0.9137, + "step": 6027 + }, + { + "epoch": 0.37005432947604283, + "grad_norm": 0.6482591367847621, + "learning_rate": 1.4523953043051935e-05, + "loss": 0.8992, + "step": 6028 + }, + { + "epoch": 0.3701157187145093, + "grad_norm": 0.752273818258368, + "learning_rate": 1.4522179708465603e-05, + "loss": 0.9521, + "step": 6029 + }, + { + "epoch": 0.37017710795297587, + "grad_norm": 0.6771051492814912, + "learning_rate": 1.4520406195093318e-05, + "loss": 0.8659, + "step": 6030 + }, + { + "epoch": 0.37023849719144236, + "grad_norm": 0.6868671343661947, + "learning_rate": 1.4518632503005199e-05, + "loss": 0.9348, + "step": 6031 + }, + { + "epoch": 0.37029988642990885, + "grad_norm": 0.7202455075778008, + "learning_rate": 1.451685863227137e-05, + "loss": 0.9109, + "step": 6032 + }, + { + "epoch": 0.37036127566837534, + "grad_norm": 0.7475252880759509, + "learning_rate": 1.4515084582961963e-05, + "loss": 0.889, + "step": 6033 + }, + { + "epoch": 0.37042266490684184, + "grad_norm": 0.7164379720619873, + "learning_rate": 1.4513310355147114e-05, + "loss": 0.9441, + "step": 6034 + }, + { + "epoch": 0.37048405414530833, + "grad_norm": 0.7239707613902895, + "learning_rate": 1.4511535948896964e-05, + "loss": 0.8975, + "step": 6035 + }, + { + "epoch": 0.3705454433837748, + "grad_norm": 0.7636039823608435, + "learning_rate": 1.4509761364281674e-05, + "loss": 0.8684, + "step": 6036 + }, + { + "epoch": 0.3706068326222413, + "grad_norm": 0.7274060530373352, + "learning_rate": 1.4507986601371392e-05, + "loss": 0.8963, + "step": 6037 + }, + { + "epoch": 0.3706682218607078, + "grad_norm": 0.6666888169499109, + "learning_rate": 1.4506211660236294e-05, + "loss": 0.8668, + "step": 6038 + }, + { + "epoch": 0.3707296110991743, + "grad_norm": 0.628419032288792, + "learning_rate": 1.4504436540946548e-05, + "loss": 0.686, + "step": 6039 + }, + { + "epoch": 0.3707910003376408, + "grad_norm": 0.6175209115297853, + "learning_rate": 1.4502661243572331e-05, + "loss": 0.8492, + "step": 6040 + }, + { + "epoch": 0.37085238957610733, + "grad_norm": 0.694886906824257, + "learning_rate": 1.4500885768183834e-05, + "loss": 0.8919, + "step": 6041 + }, + { + "epoch": 0.3709137788145738, + "grad_norm": 0.660286839892626, + "learning_rate": 1.4499110114851251e-05, + "loss": 0.9206, + "step": 6042 + }, + { + "epoch": 0.3709751680530403, + "grad_norm": 0.7305765839182216, + "learning_rate": 1.4497334283644782e-05, + "loss": 0.9505, + "step": 6043 + }, + { + "epoch": 0.3710365572915068, + "grad_norm": 0.6656940375408089, + "learning_rate": 1.4495558274634633e-05, + "loss": 0.8793, + "step": 6044 + }, + { + "epoch": 0.3710979465299733, + "grad_norm": 0.7129515548212314, + "learning_rate": 1.4493782087891026e-05, + "loss": 0.949, + "step": 6045 + }, + { + "epoch": 0.3711593357684398, + "grad_norm": 0.6508577341137319, + "learning_rate": 1.4492005723484174e-05, + "loss": 0.8901, + "step": 6046 + }, + { + "epoch": 0.3712207250069063, + "grad_norm": 0.5739314859450352, + "learning_rate": 1.4490229181484314e-05, + "loss": 0.6806, + "step": 6047 + }, + { + "epoch": 0.3712821142453728, + "grad_norm": 0.7017847654317978, + "learning_rate": 1.4488452461961677e-05, + "loss": 0.8701, + "step": 6048 + }, + { + "epoch": 0.37134350348383927, + "grad_norm": 0.7189378953929066, + "learning_rate": 1.448667556498651e-05, + "loss": 0.9126, + "step": 6049 + }, + { + "epoch": 0.37140489272230576, + "grad_norm": 0.6815654086110667, + "learning_rate": 1.4484898490629063e-05, + "loss": 0.8757, + "step": 6050 + }, + { + "epoch": 0.3714662819607723, + "grad_norm": 0.704458196996464, + "learning_rate": 1.448312123895959e-05, + "loss": 0.9346, + "step": 6051 + }, + { + "epoch": 0.3715276711992388, + "grad_norm": 0.7147463093238217, + "learning_rate": 1.4481343810048355e-05, + "loss": 0.9736, + "step": 6052 + }, + { + "epoch": 0.3715890604377053, + "grad_norm": 0.6992480663952606, + "learning_rate": 1.4479566203965632e-05, + "loss": 0.8734, + "step": 6053 + }, + { + "epoch": 0.3716504496761718, + "grad_norm": 0.7320610357473842, + "learning_rate": 1.4477788420781702e-05, + "loss": 0.8834, + "step": 6054 + }, + { + "epoch": 0.37171183891463827, + "grad_norm": 0.6470545986577478, + "learning_rate": 1.4476010460566842e-05, + "loss": 0.8614, + "step": 6055 + }, + { + "epoch": 0.37177322815310476, + "grad_norm": 0.7627918120527672, + "learning_rate": 1.4474232323391354e-05, + "loss": 0.887, + "step": 6056 + }, + { + "epoch": 0.37183461739157125, + "grad_norm": 0.7529245010404092, + "learning_rate": 1.4472454009325528e-05, + "loss": 0.9081, + "step": 6057 + }, + { + "epoch": 0.37189600663003775, + "grad_norm": 0.7121152586257823, + "learning_rate": 1.4470675518439677e-05, + "loss": 0.8624, + "step": 6058 + }, + { + "epoch": 0.37195739586850424, + "grad_norm": 0.7751717507518036, + "learning_rate": 1.4468896850804111e-05, + "loss": 0.9685, + "step": 6059 + }, + { + "epoch": 0.37201878510697073, + "grad_norm": 0.7970430020172533, + "learning_rate": 1.446711800648915e-05, + "loss": 0.9379, + "step": 6060 + }, + { + "epoch": 0.3720801743454372, + "grad_norm": 0.7754335469950796, + "learning_rate": 1.4465338985565126e-05, + "loss": 0.9143, + "step": 6061 + }, + { + "epoch": 0.37214156358390377, + "grad_norm": 0.6989994435304075, + "learning_rate": 1.4463559788102366e-05, + "loss": 0.9059, + "step": 6062 + }, + { + "epoch": 0.37220295282237026, + "grad_norm": 0.6667561853307149, + "learning_rate": 1.4461780414171216e-05, + "loss": 0.8968, + "step": 6063 + }, + { + "epoch": 0.37226434206083675, + "grad_norm": 0.6808809118145569, + "learning_rate": 1.4460000863842023e-05, + "loss": 0.9115, + "step": 6064 + }, + { + "epoch": 0.37232573129930324, + "grad_norm": 0.6591959210111853, + "learning_rate": 1.4458221137185142e-05, + "loss": 0.886, + "step": 6065 + }, + { + "epoch": 0.37238712053776973, + "grad_norm": 0.6672630361369082, + "learning_rate": 1.4456441234270938e-05, + "loss": 0.9041, + "step": 6066 + }, + { + "epoch": 0.3724485097762362, + "grad_norm": 0.6627473249453439, + "learning_rate": 1.445466115516977e-05, + "loss": 0.8591, + "step": 6067 + }, + { + "epoch": 0.3725098990147027, + "grad_norm": 0.7388805817837085, + "learning_rate": 1.4452880899952029e-05, + "loss": 0.9399, + "step": 6068 + }, + { + "epoch": 0.3725712882531692, + "grad_norm": 0.710757393983683, + "learning_rate": 1.4451100468688086e-05, + "loss": 0.9193, + "step": 6069 + }, + { + "epoch": 0.3726326774916357, + "grad_norm": 0.7417518454754656, + "learning_rate": 1.444931986144834e-05, + "loss": 0.9443, + "step": 6070 + }, + { + "epoch": 0.3726940667301022, + "grad_norm": 0.7154698040455844, + "learning_rate": 1.4447539078303177e-05, + "loss": 0.9138, + "step": 6071 + }, + { + "epoch": 0.3727554559685687, + "grad_norm": 0.7016547146643823, + "learning_rate": 1.444575811932301e-05, + "loss": 0.907, + "step": 6072 + }, + { + "epoch": 0.37281684520703523, + "grad_norm": 0.7457335801370595, + "learning_rate": 1.444397698457825e-05, + "loss": 0.9083, + "step": 6073 + }, + { + "epoch": 0.3728782344455017, + "grad_norm": 0.7524798585986088, + "learning_rate": 1.4442195674139306e-05, + "loss": 0.9172, + "step": 6074 + }, + { + "epoch": 0.3729396236839682, + "grad_norm": 0.6967826393159312, + "learning_rate": 1.444041418807661e-05, + "loss": 0.9539, + "step": 6075 + }, + { + "epoch": 0.3730010129224347, + "grad_norm": 0.7680206794181167, + "learning_rate": 1.4438632526460594e-05, + "loss": 0.9285, + "step": 6076 + }, + { + "epoch": 0.3730624021609012, + "grad_norm": 0.7067830815463553, + "learning_rate": 1.4436850689361697e-05, + "loss": 0.8907, + "step": 6077 + }, + { + "epoch": 0.3731237913993677, + "grad_norm": 0.728622808013846, + "learning_rate": 1.4435068676850356e-05, + "loss": 0.917, + "step": 6078 + }, + { + "epoch": 0.3731851806378342, + "grad_norm": 0.6176714314268483, + "learning_rate": 1.4433286488997036e-05, + "loss": 0.8544, + "step": 6079 + }, + { + "epoch": 0.37324656987630067, + "grad_norm": 0.7027387616761702, + "learning_rate": 1.4431504125872184e-05, + "loss": 0.8966, + "step": 6080 + }, + { + "epoch": 0.37330795911476716, + "grad_norm": 0.6887645510200939, + "learning_rate": 1.4429721587546277e-05, + "loss": 0.8972, + "step": 6081 + }, + { + "epoch": 0.37336934835323365, + "grad_norm": 0.6620830795675524, + "learning_rate": 1.4427938874089784e-05, + "loss": 0.8803, + "step": 6082 + }, + { + "epoch": 0.3734307375917002, + "grad_norm": 0.7041848712064083, + "learning_rate": 1.4426155985573185e-05, + "loss": 0.9498, + "step": 6083 + }, + { + "epoch": 0.3734921268301667, + "grad_norm": 0.6907583673759894, + "learning_rate": 1.4424372922066965e-05, + "loss": 0.7384, + "step": 6084 + }, + { + "epoch": 0.3735535160686332, + "grad_norm": 0.7425732092191849, + "learning_rate": 1.442258968364162e-05, + "loss": 0.9263, + "step": 6085 + }, + { + "epoch": 0.3736149053070997, + "grad_norm": 0.666614265862987, + "learning_rate": 1.4420806270367656e-05, + "loss": 0.885, + "step": 6086 + }, + { + "epoch": 0.37367629454556617, + "grad_norm": 0.6830953428581129, + "learning_rate": 1.4419022682315568e-05, + "loss": 0.8973, + "step": 6087 + }, + { + "epoch": 0.37373768378403266, + "grad_norm": 0.7453365122789339, + "learning_rate": 1.4417238919555885e-05, + "loss": 0.9167, + "step": 6088 + }, + { + "epoch": 0.37379907302249915, + "grad_norm": 0.6921890843208647, + "learning_rate": 1.4415454982159121e-05, + "loss": 0.8951, + "step": 6089 + }, + { + "epoch": 0.37386046226096564, + "grad_norm": 0.7461724147365678, + "learning_rate": 1.4413670870195805e-05, + "loss": 0.9347, + "step": 6090 + }, + { + "epoch": 0.37392185149943213, + "grad_norm": 0.7352687844988336, + "learning_rate": 1.4411886583736474e-05, + "loss": 0.9165, + "step": 6091 + }, + { + "epoch": 0.3739832407378986, + "grad_norm": 0.7174022902312361, + "learning_rate": 1.4410102122851668e-05, + "loss": 0.9211, + "step": 6092 + }, + { + "epoch": 0.3740446299763651, + "grad_norm": 0.7264897833477995, + "learning_rate": 1.4408317487611942e-05, + "loss": 0.937, + "step": 6093 + }, + { + "epoch": 0.37410601921483166, + "grad_norm": 0.7950506071769016, + "learning_rate": 1.4406532678087846e-05, + "loss": 0.9382, + "step": 6094 + }, + { + "epoch": 0.37416740845329816, + "grad_norm": 0.7563396868127061, + "learning_rate": 1.4404747694349946e-05, + "loss": 0.9792, + "step": 6095 + }, + { + "epoch": 0.37422879769176465, + "grad_norm": 0.692632927294285, + "learning_rate": 1.4402962536468812e-05, + "loss": 0.9128, + "step": 6096 + }, + { + "epoch": 0.37429018693023114, + "grad_norm": 0.6992485226498804, + "learning_rate": 1.440117720451502e-05, + "loss": 0.9218, + "step": 6097 + }, + { + "epoch": 0.37435157616869763, + "grad_norm": 0.732225318393037, + "learning_rate": 1.4399391698559153e-05, + "loss": 0.9189, + "step": 6098 + }, + { + "epoch": 0.3744129654071641, + "grad_norm": 0.628664607795243, + "learning_rate": 1.4397606018671803e-05, + "loss": 0.8629, + "step": 6099 + }, + { + "epoch": 0.3744743546456306, + "grad_norm": 0.7342492853455436, + "learning_rate": 1.4395820164923566e-05, + "loss": 0.8597, + "step": 6100 + }, + { + "epoch": 0.3745357438840971, + "grad_norm": 0.7300545444046995, + "learning_rate": 1.4394034137385049e-05, + "loss": 0.9035, + "step": 6101 + }, + { + "epoch": 0.3745971331225636, + "grad_norm": 0.6608336991722984, + "learning_rate": 1.4392247936126862e-05, + "loss": 0.8751, + "step": 6102 + }, + { + "epoch": 0.3746585223610301, + "grad_norm": 0.6772002030464656, + "learning_rate": 1.4390461561219622e-05, + "loss": 0.9298, + "step": 6103 + }, + { + "epoch": 0.37471991159949664, + "grad_norm": 0.7406847919535468, + "learning_rate": 1.4388675012733954e-05, + "loss": 0.8724, + "step": 6104 + }, + { + "epoch": 0.3747813008379631, + "grad_norm": 0.686734681826513, + "learning_rate": 1.4386888290740493e-05, + "loss": 0.874, + "step": 6105 + }, + { + "epoch": 0.3748426900764296, + "grad_norm": 0.6360136256379011, + "learning_rate": 1.438510139530987e-05, + "loss": 0.9148, + "step": 6106 + }, + { + "epoch": 0.3749040793148961, + "grad_norm": 0.6970198977084485, + "learning_rate": 1.4383314326512741e-05, + "loss": 0.9259, + "step": 6107 + }, + { + "epoch": 0.3749654685533626, + "grad_norm": 0.7619928659699506, + "learning_rate": 1.438152708441975e-05, + "loss": 0.8954, + "step": 6108 + }, + { + "epoch": 0.3750268577918291, + "grad_norm": 0.689282780897023, + "learning_rate": 1.437973966910156e-05, + "loss": 0.9066, + "step": 6109 + }, + { + "epoch": 0.3750882470302956, + "grad_norm": 0.7451712227164644, + "learning_rate": 1.4377952080628838e-05, + "loss": 0.8886, + "step": 6110 + }, + { + "epoch": 0.3751496362687621, + "grad_norm": 0.6923675219198562, + "learning_rate": 1.4376164319072254e-05, + "loss": 0.8631, + "step": 6111 + }, + { + "epoch": 0.37521102550722857, + "grad_norm": 0.6856094192916127, + "learning_rate": 1.4374376384502487e-05, + "loss": 0.8816, + "step": 6112 + }, + { + "epoch": 0.37527241474569506, + "grad_norm": 0.7173697106888086, + "learning_rate": 1.4372588276990227e-05, + "loss": 0.9652, + "step": 6113 + }, + { + "epoch": 0.37533380398416155, + "grad_norm": 0.7188194497392525, + "learning_rate": 1.4370799996606169e-05, + "loss": 0.884, + "step": 6114 + }, + { + "epoch": 0.3753951932226281, + "grad_norm": 0.7171266999944769, + "learning_rate": 1.4369011543421007e-05, + "loss": 0.8861, + "step": 6115 + }, + { + "epoch": 0.3754565824610946, + "grad_norm": 0.760919195051581, + "learning_rate": 1.4367222917505452e-05, + "loss": 0.9462, + "step": 6116 + }, + { + "epoch": 0.3755179716995611, + "grad_norm": 0.6839969098308671, + "learning_rate": 1.436543411893022e-05, + "loss": 0.8734, + "step": 6117 + }, + { + "epoch": 0.3755793609380276, + "grad_norm": 0.7318319853057148, + "learning_rate": 1.4363645147766028e-05, + "loss": 0.9245, + "step": 6118 + }, + { + "epoch": 0.37564075017649406, + "grad_norm": 0.782695679392615, + "learning_rate": 1.4361856004083604e-05, + "loss": 0.996, + "step": 6119 + }, + { + "epoch": 0.37570213941496056, + "grad_norm": 0.735037103412834, + "learning_rate": 1.4360066687953684e-05, + "loss": 0.9343, + "step": 6120 + }, + { + "epoch": 0.37576352865342705, + "grad_norm": 0.697987343691856, + "learning_rate": 1.4358277199447007e-05, + "loss": 0.9121, + "step": 6121 + }, + { + "epoch": 0.37582491789189354, + "grad_norm": 0.7361042711439989, + "learning_rate": 1.4356487538634323e-05, + "loss": 0.915, + "step": 6122 + }, + { + "epoch": 0.37588630713036003, + "grad_norm": 0.6403743231601181, + "learning_rate": 1.4354697705586392e-05, + "loss": 0.8623, + "step": 6123 + }, + { + "epoch": 0.3759476963688265, + "grad_norm": 0.7334300664872142, + "learning_rate": 1.4352907700373961e-05, + "loss": 0.903, + "step": 6124 + }, + { + "epoch": 0.376009085607293, + "grad_norm": 0.6736233896564315, + "learning_rate": 1.4351117523067814e-05, + "loss": 0.8972, + "step": 6125 + }, + { + "epoch": 0.37607047484575956, + "grad_norm": 0.7163693093953248, + "learning_rate": 1.4349327173738718e-05, + "loss": 0.8524, + "step": 6126 + }, + { + "epoch": 0.37613186408422605, + "grad_norm": 0.6966229201078069, + "learning_rate": 1.434753665245746e-05, + "loss": 0.9326, + "step": 6127 + }, + { + "epoch": 0.37619325332269254, + "grad_norm": 0.6173046278282212, + "learning_rate": 1.4345745959294822e-05, + "loss": 0.7265, + "step": 6128 + }, + { + "epoch": 0.37625464256115904, + "grad_norm": 0.7758915646989223, + "learning_rate": 1.4343955094321605e-05, + "loss": 0.9306, + "step": 6129 + }, + { + "epoch": 0.3763160317996255, + "grad_norm": 0.7317225799917101, + "learning_rate": 1.4342164057608608e-05, + "loss": 0.9288, + "step": 6130 + }, + { + "epoch": 0.376377421038092, + "grad_norm": 0.7040454475681395, + "learning_rate": 1.4340372849226643e-05, + "loss": 0.8847, + "step": 6131 + }, + { + "epoch": 0.3764388102765585, + "grad_norm": 0.6622456714455963, + "learning_rate": 1.4338581469246527e-05, + "loss": 0.8846, + "step": 6132 + }, + { + "epoch": 0.376500199515025, + "grad_norm": 0.737730821375013, + "learning_rate": 1.433678991773908e-05, + "loss": 0.9124, + "step": 6133 + }, + { + "epoch": 0.3765615887534915, + "grad_norm": 0.677235604961781, + "learning_rate": 1.4334998194775133e-05, + "loss": 0.9436, + "step": 6134 + }, + { + "epoch": 0.376622977991958, + "grad_norm": 0.776853352632263, + "learning_rate": 1.4333206300425522e-05, + "loss": 0.9453, + "step": 6135 + }, + { + "epoch": 0.37668436723042453, + "grad_norm": 0.7614772899044407, + "learning_rate": 1.4331414234761092e-05, + "loss": 0.9088, + "step": 6136 + }, + { + "epoch": 0.376745756468891, + "grad_norm": 0.7729073090483141, + "learning_rate": 1.432962199785269e-05, + "loss": 0.9073, + "step": 6137 + }, + { + "epoch": 0.3768071457073575, + "grad_norm": 0.654375913127654, + "learning_rate": 1.4327829589771172e-05, + "loss": 0.9017, + "step": 6138 + }, + { + "epoch": 0.376868534945824, + "grad_norm": 0.6658330264075041, + "learning_rate": 1.4326037010587406e-05, + "loss": 0.8607, + "step": 6139 + }, + { + "epoch": 0.3769299241842905, + "grad_norm": 0.6703439173848399, + "learning_rate": 1.4324244260372257e-05, + "loss": 0.9041, + "step": 6140 + }, + { + "epoch": 0.376991313422757, + "grad_norm": 0.7085263829676487, + "learning_rate": 1.4322451339196608e-05, + "loss": 0.9072, + "step": 6141 + }, + { + "epoch": 0.3770527026612235, + "grad_norm": 0.7197646534239134, + "learning_rate": 1.432065824713134e-05, + "loss": 0.8545, + "step": 6142 + }, + { + "epoch": 0.37711409189969, + "grad_norm": 0.7069548512972457, + "learning_rate": 1.431886498424734e-05, + "loss": 0.8561, + "step": 6143 + }, + { + "epoch": 0.37717548113815647, + "grad_norm": 0.5904415816840004, + "learning_rate": 1.4317071550615508e-05, + "loss": 0.8423, + "step": 6144 + }, + { + "epoch": 0.37723687037662296, + "grad_norm": 0.6769725907023272, + "learning_rate": 1.431527794630675e-05, + "loss": 0.9394, + "step": 6145 + }, + { + "epoch": 0.37729825961508945, + "grad_norm": 0.7266570496559069, + "learning_rate": 1.4313484171391976e-05, + "loss": 0.8787, + "step": 6146 + }, + { + "epoch": 0.377359648853556, + "grad_norm": 0.7426773129568031, + "learning_rate": 1.4311690225942102e-05, + "loss": 0.8814, + "step": 6147 + }, + { + "epoch": 0.3774210380920225, + "grad_norm": 0.6800560929967129, + "learning_rate": 1.4309896110028053e-05, + "loss": 0.8895, + "step": 6148 + }, + { + "epoch": 0.377482427330489, + "grad_norm": 0.7500448421222252, + "learning_rate": 1.4308101823720755e-05, + "loss": 0.9717, + "step": 6149 + }, + { + "epoch": 0.37754381656895547, + "grad_norm": 0.7312114308387289, + "learning_rate": 1.4306307367091157e-05, + "loss": 0.8645, + "step": 6150 + }, + { + "epoch": 0.37760520580742196, + "grad_norm": 0.6506500702264794, + "learning_rate": 1.4304512740210193e-05, + "loss": 0.8647, + "step": 6151 + }, + { + "epoch": 0.37766659504588845, + "grad_norm": 0.7513186010090724, + "learning_rate": 1.4302717943148821e-05, + "loss": 0.9193, + "step": 6152 + }, + { + "epoch": 0.37772798428435495, + "grad_norm": 0.6403731389595132, + "learning_rate": 1.4300922975977995e-05, + "loss": 0.8965, + "step": 6153 + }, + { + "epoch": 0.37778937352282144, + "grad_norm": 0.6951916033517159, + "learning_rate": 1.4299127838768678e-05, + "loss": 0.8979, + "step": 6154 + }, + { + "epoch": 0.37785076276128793, + "grad_norm": 0.7269460464783196, + "learning_rate": 1.429733253159185e-05, + "loss": 0.9157, + "step": 6155 + }, + { + "epoch": 0.3779121519997544, + "grad_norm": 0.7401514372980779, + "learning_rate": 1.4295537054518478e-05, + "loss": 0.9036, + "step": 6156 + }, + { + "epoch": 0.37797354123822097, + "grad_norm": 0.7803431145624521, + "learning_rate": 1.4293741407619556e-05, + "loss": 0.8809, + "step": 6157 + }, + { + "epoch": 0.37803493047668746, + "grad_norm": 0.7478924732403089, + "learning_rate": 1.429194559096607e-05, + "loss": 0.917, + "step": 6158 + }, + { + "epoch": 0.37809631971515395, + "grad_norm": 0.7253190265517597, + "learning_rate": 1.4290149604629017e-05, + "loss": 0.973, + "step": 6159 + }, + { + "epoch": 0.37815770895362044, + "grad_norm": 0.7439293851819544, + "learning_rate": 1.428835344867941e-05, + "loss": 0.9418, + "step": 6160 + }, + { + "epoch": 0.37821909819208693, + "grad_norm": 0.7407055301799713, + "learning_rate": 1.4286557123188254e-05, + "loss": 0.9652, + "step": 6161 + }, + { + "epoch": 0.3782804874305534, + "grad_norm": 0.8039702733454749, + "learning_rate": 1.4284760628226568e-05, + "loss": 0.916, + "step": 6162 + }, + { + "epoch": 0.3783418766690199, + "grad_norm": 0.6898735204663358, + "learning_rate": 1.4282963963865375e-05, + "loss": 0.8603, + "step": 6163 + }, + { + "epoch": 0.3784032659074864, + "grad_norm": 0.7861316158222673, + "learning_rate": 1.4281167130175712e-05, + "loss": 0.9413, + "step": 6164 + }, + { + "epoch": 0.3784646551459529, + "grad_norm": 0.7397414413609674, + "learning_rate": 1.4279370127228615e-05, + "loss": 0.9334, + "step": 6165 + }, + { + "epoch": 0.3785260443844194, + "grad_norm": 0.7908098801981568, + "learning_rate": 1.427757295509513e-05, + "loss": 0.918, + "step": 6166 + }, + { + "epoch": 0.3785874336228859, + "grad_norm": 0.7040401206741945, + "learning_rate": 1.4275775613846308e-05, + "loss": 0.8712, + "step": 6167 + }, + { + "epoch": 0.37864882286135243, + "grad_norm": 0.7573373857365495, + "learning_rate": 1.4273978103553207e-05, + "loss": 0.9209, + "step": 6168 + }, + { + "epoch": 0.3787102120998189, + "grad_norm": 0.6724445587056651, + "learning_rate": 1.4272180424286895e-05, + "loss": 0.928, + "step": 6169 + }, + { + "epoch": 0.3787716013382854, + "grad_norm": 0.6605042905764653, + "learning_rate": 1.4270382576118438e-05, + "loss": 0.8778, + "step": 6170 + }, + { + "epoch": 0.3788329905767519, + "grad_norm": 0.741943201138213, + "learning_rate": 1.4268584559118919e-05, + "loss": 0.9264, + "step": 6171 + }, + { + "epoch": 0.3788943798152184, + "grad_norm": 0.7614708444872113, + "learning_rate": 1.4266786373359423e-05, + "loss": 0.9625, + "step": 6172 + }, + { + "epoch": 0.3789557690536849, + "grad_norm": 0.6928045804076419, + "learning_rate": 1.4264988018911041e-05, + "loss": 0.899, + "step": 6173 + }, + { + "epoch": 0.3790171582921514, + "grad_norm": 0.6529939728568231, + "learning_rate": 1.4263189495844874e-05, + "loss": 0.881, + "step": 6174 + }, + { + "epoch": 0.37907854753061787, + "grad_norm": 0.7535090014249134, + "learning_rate": 1.4261390804232023e-05, + "loss": 0.9425, + "step": 6175 + }, + { + "epoch": 0.37913993676908436, + "grad_norm": 0.6810043669099883, + "learning_rate": 1.4259591944143601e-05, + "loss": 0.8778, + "step": 6176 + }, + { + "epoch": 0.37920132600755085, + "grad_norm": 0.7034196967325126, + "learning_rate": 1.4257792915650728e-05, + "loss": 0.8782, + "step": 6177 + }, + { + "epoch": 0.37926271524601735, + "grad_norm": 0.718176860815227, + "learning_rate": 1.425599371882453e-05, + "loss": 0.95, + "step": 6178 + }, + { + "epoch": 0.3793241044844839, + "grad_norm": 0.7103840235807847, + "learning_rate": 1.4254194353736138e-05, + "loss": 0.9194, + "step": 6179 + }, + { + "epoch": 0.3793854937229504, + "grad_norm": 0.6104742409711084, + "learning_rate": 1.4252394820456688e-05, + "loss": 0.8547, + "step": 6180 + }, + { + "epoch": 0.3794468829614169, + "grad_norm": 0.7234220832955962, + "learning_rate": 1.4250595119057327e-05, + "loss": 0.9416, + "step": 6181 + }, + { + "epoch": 0.37950827219988337, + "grad_norm": 0.730932505343041, + "learning_rate": 1.4248795249609211e-05, + "loss": 0.9411, + "step": 6182 + }, + { + "epoch": 0.37956966143834986, + "grad_norm": 0.6815130887896336, + "learning_rate": 1.424699521218349e-05, + "loss": 0.872, + "step": 6183 + }, + { + "epoch": 0.37963105067681635, + "grad_norm": 0.641023896586194, + "learning_rate": 1.4245195006851338e-05, + "loss": 0.7852, + "step": 6184 + }, + { + "epoch": 0.37969243991528284, + "grad_norm": 0.7259554168191269, + "learning_rate": 1.424339463368392e-05, + "loss": 0.9493, + "step": 6185 + }, + { + "epoch": 0.37975382915374933, + "grad_norm": 0.6804449545756747, + "learning_rate": 1.4241594092752415e-05, + "loss": 0.9042, + "step": 6186 + }, + { + "epoch": 0.3798152183922158, + "grad_norm": 0.7506539608609285, + "learning_rate": 1.4239793384128015e-05, + "loss": 0.9277, + "step": 6187 + }, + { + "epoch": 0.3798766076306823, + "grad_norm": 0.7401163602119389, + "learning_rate": 1.4237992507881902e-05, + "loss": 0.9159, + "step": 6188 + }, + { + "epoch": 0.37993799686914886, + "grad_norm": 0.7033821422129433, + "learning_rate": 1.4236191464085286e-05, + "loss": 0.8759, + "step": 6189 + }, + { + "epoch": 0.37999938610761536, + "grad_norm": 0.6940644805347812, + "learning_rate": 1.4234390252809356e-05, + "loss": 0.8628, + "step": 6190 + }, + { + "epoch": 0.38006077534608185, + "grad_norm": 0.655738094009293, + "learning_rate": 1.4232588874125335e-05, + "loss": 0.8234, + "step": 6191 + }, + { + "epoch": 0.38012216458454834, + "grad_norm": 0.7138260610939806, + "learning_rate": 1.4230787328104438e-05, + "loss": 0.905, + "step": 6192 + }, + { + "epoch": 0.38018355382301483, + "grad_norm": 0.7252996378576012, + "learning_rate": 1.422898561481789e-05, + "loss": 0.8644, + "step": 6193 + }, + { + "epoch": 0.3802449430614813, + "grad_norm": 0.6830425375073891, + "learning_rate": 1.4227183734336926e-05, + "loss": 0.9115, + "step": 6194 + }, + { + "epoch": 0.3803063322999478, + "grad_norm": 0.7501263760778099, + "learning_rate": 1.4225381686732776e-05, + "loss": 0.9177, + "step": 6195 + }, + { + "epoch": 0.3803677215384143, + "grad_norm": 0.7360158548442445, + "learning_rate": 1.4223579472076691e-05, + "loss": 0.9461, + "step": 6196 + }, + { + "epoch": 0.3804291107768808, + "grad_norm": 0.6692851113668545, + "learning_rate": 1.422177709043992e-05, + "loss": 0.8749, + "step": 6197 + }, + { + "epoch": 0.3804905000153473, + "grad_norm": 0.7694610418629739, + "learning_rate": 1.4219974541893722e-05, + "loss": 0.9141, + "step": 6198 + }, + { + "epoch": 0.3805518892538138, + "grad_norm": 0.7708660149193741, + "learning_rate": 1.4218171826509359e-05, + "loss": 0.9187, + "step": 6199 + }, + { + "epoch": 0.3806132784922803, + "grad_norm": 0.7363833189315268, + "learning_rate": 1.4216368944358103e-05, + "loss": 0.8982, + "step": 6200 + }, + { + "epoch": 0.3806746677307468, + "grad_norm": 0.6224367290258493, + "learning_rate": 1.4214565895511233e-05, + "loss": 0.8593, + "step": 6201 + }, + { + "epoch": 0.3807360569692133, + "grad_norm": 0.7222929240096345, + "learning_rate": 1.421276268004003e-05, + "loss": 0.8866, + "step": 6202 + }, + { + "epoch": 0.3807974462076798, + "grad_norm": 0.7807115875432581, + "learning_rate": 1.4210959298015789e-05, + "loss": 0.9235, + "step": 6203 + }, + { + "epoch": 0.3808588354461463, + "grad_norm": 0.6891884578583295, + "learning_rate": 1.4209155749509803e-05, + "loss": 0.8803, + "step": 6204 + }, + { + "epoch": 0.3809202246846128, + "grad_norm": 0.7289351506250088, + "learning_rate": 1.4207352034593382e-05, + "loss": 0.9076, + "step": 6205 + }, + { + "epoch": 0.3809816139230793, + "grad_norm": 0.761421314100504, + "learning_rate": 1.420554815333783e-05, + "loss": 0.9233, + "step": 6206 + }, + { + "epoch": 0.38104300316154577, + "grad_norm": 0.7367567877294976, + "learning_rate": 1.4203744105814467e-05, + "loss": 0.9376, + "step": 6207 + }, + { + "epoch": 0.38110439240001226, + "grad_norm": 0.6943056365178131, + "learning_rate": 1.4201939892094614e-05, + "loss": 0.9138, + "step": 6208 + }, + { + "epoch": 0.38116578163847875, + "grad_norm": 0.7589152196748316, + "learning_rate": 1.4200135512249606e-05, + "loss": 0.9622, + "step": 6209 + }, + { + "epoch": 0.3812271708769453, + "grad_norm": 0.709393479516626, + "learning_rate": 1.4198330966350777e-05, + "loss": 0.9403, + "step": 6210 + }, + { + "epoch": 0.3812885601154118, + "grad_norm": 0.6478408788292309, + "learning_rate": 1.4196526254469471e-05, + "loss": 0.9021, + "step": 6211 + }, + { + "epoch": 0.3813499493538783, + "grad_norm": 0.7263803391711722, + "learning_rate": 1.4194721376677038e-05, + "loss": 0.9051, + "step": 6212 + }, + { + "epoch": 0.3814113385923448, + "grad_norm": 0.653219816133273, + "learning_rate": 1.419291633304483e-05, + "loss": 0.8547, + "step": 6213 + }, + { + "epoch": 0.38147272783081126, + "grad_norm": 0.661071989765036, + "learning_rate": 1.419111112364422e-05, + "loss": 0.9046, + "step": 6214 + }, + { + "epoch": 0.38153411706927776, + "grad_norm": 0.8036992265696074, + "learning_rate": 1.4189305748546568e-05, + "loss": 0.9153, + "step": 6215 + }, + { + "epoch": 0.38159550630774425, + "grad_norm": 0.6842660665486067, + "learning_rate": 1.4187500207823255e-05, + "loss": 0.8799, + "step": 6216 + }, + { + "epoch": 0.38165689554621074, + "grad_norm": 0.6834044974363627, + "learning_rate": 1.4185694501545664e-05, + "loss": 0.9128, + "step": 6217 + }, + { + "epoch": 0.38171828478467723, + "grad_norm": 0.7085793600923775, + "learning_rate": 1.4183888629785178e-05, + "loss": 0.9113, + "step": 6218 + }, + { + "epoch": 0.3817796740231437, + "grad_norm": 0.6639452901479216, + "learning_rate": 1.4182082592613202e-05, + "loss": 0.827, + "step": 6219 + }, + { + "epoch": 0.3818410632616102, + "grad_norm": 0.6805793628613034, + "learning_rate": 1.418027639010113e-05, + "loss": 0.9188, + "step": 6220 + }, + { + "epoch": 0.38190245250007676, + "grad_norm": 0.7032408973895932, + "learning_rate": 1.4178470022320378e-05, + "loss": 0.9196, + "step": 6221 + }, + { + "epoch": 0.38196384173854325, + "grad_norm": 0.5688145739265743, + "learning_rate": 1.4176663489342356e-05, + "loss": 0.7066, + "step": 6222 + }, + { + "epoch": 0.38202523097700974, + "grad_norm": 0.6952180553279973, + "learning_rate": 1.4174856791238489e-05, + "loss": 0.8877, + "step": 6223 + }, + { + "epoch": 0.38208662021547624, + "grad_norm": 0.7572233462777178, + "learning_rate": 1.4173049928080204e-05, + "loss": 0.9636, + "step": 6224 + }, + { + "epoch": 0.3821480094539427, + "grad_norm": 0.7871674194121341, + "learning_rate": 1.4171242899938936e-05, + "loss": 0.8881, + "step": 6225 + }, + { + "epoch": 0.3822093986924092, + "grad_norm": 0.7462211979801764, + "learning_rate": 1.4169435706886128e-05, + "loss": 0.9276, + "step": 6226 + }, + { + "epoch": 0.3822707879308757, + "grad_norm": 0.7646100252066376, + "learning_rate": 1.4167628348993225e-05, + "loss": 0.9301, + "step": 6227 + }, + { + "epoch": 0.3823321771693422, + "grad_norm": 0.7613830629161888, + "learning_rate": 1.4165820826331684e-05, + "loss": 0.9558, + "step": 6228 + }, + { + "epoch": 0.3823935664078087, + "grad_norm": 0.6718177339076455, + "learning_rate": 1.4164013138972966e-05, + "loss": 0.903, + "step": 6229 + }, + { + "epoch": 0.3824549556462752, + "grad_norm": 0.7476475939445483, + "learning_rate": 1.4162205286988537e-05, + "loss": 0.926, + "step": 6230 + }, + { + "epoch": 0.38251634488474173, + "grad_norm": 0.7354987639372624, + "learning_rate": 1.4160397270449872e-05, + "loss": 0.9358, + "step": 6231 + }, + { + "epoch": 0.3825777341232082, + "grad_norm": 0.7150797612412199, + "learning_rate": 1.4158589089428451e-05, + "loss": 0.8899, + "step": 6232 + }, + { + "epoch": 0.3826391233616747, + "grad_norm": 0.6991833409343572, + "learning_rate": 1.4156780743995763e-05, + "loss": 0.8949, + "step": 6233 + }, + { + "epoch": 0.3827005126001412, + "grad_norm": 0.6945001880769631, + "learning_rate": 1.4154972234223298e-05, + "loss": 0.9713, + "step": 6234 + }, + { + "epoch": 0.3827619018386077, + "grad_norm": 0.6533198480271636, + "learning_rate": 1.415316356018256e-05, + "loss": 0.8666, + "step": 6235 + }, + { + "epoch": 0.3828232910770742, + "grad_norm": 0.7375063044906465, + "learning_rate": 1.4151354721945057e-05, + "loss": 0.9021, + "step": 6236 + }, + { + "epoch": 0.3828846803155407, + "grad_norm": 0.7808352179656393, + "learning_rate": 1.4149545719582294e-05, + "loss": 0.9393, + "step": 6237 + }, + { + "epoch": 0.3829460695540072, + "grad_norm": 0.664397765461106, + "learning_rate": 1.4147736553165797e-05, + "loss": 0.8992, + "step": 6238 + }, + { + "epoch": 0.38300745879247367, + "grad_norm": 0.7348873176950205, + "learning_rate": 1.414592722276709e-05, + "loss": 0.9204, + "step": 6239 + }, + { + "epoch": 0.38306884803094016, + "grad_norm": 0.7255121860633248, + "learning_rate": 1.4144117728457705e-05, + "loss": 0.9511, + "step": 6240 + }, + { + "epoch": 0.38313023726940665, + "grad_norm": 0.7515679743611088, + "learning_rate": 1.4142308070309183e-05, + "loss": 0.9368, + "step": 6241 + }, + { + "epoch": 0.3831916265078732, + "grad_norm": 0.7401270248495686, + "learning_rate": 1.4140498248393068e-05, + "loss": 0.939, + "step": 6242 + }, + { + "epoch": 0.3832530157463397, + "grad_norm": 0.6787447546908187, + "learning_rate": 1.4138688262780913e-05, + "loss": 0.9203, + "step": 6243 + }, + { + "epoch": 0.3833144049848062, + "grad_norm": 0.7385309036793699, + "learning_rate": 1.4136878113544277e-05, + "loss": 0.9437, + "step": 6244 + }, + { + "epoch": 0.38337579422327267, + "grad_norm": 0.7076300808051176, + "learning_rate": 1.413506780075472e-05, + "loss": 0.9086, + "step": 6245 + }, + { + "epoch": 0.38343718346173916, + "grad_norm": 0.721273113816995, + "learning_rate": 1.413325732448382e-05, + "loss": 0.8783, + "step": 6246 + }, + { + "epoch": 0.38349857270020565, + "grad_norm": 0.6998421636644716, + "learning_rate": 1.413144668480315e-05, + "loss": 0.8916, + "step": 6247 + }, + { + "epoch": 0.38355996193867214, + "grad_norm": 0.7625293929408948, + "learning_rate": 1.4129635881784297e-05, + "loss": 0.9283, + "step": 6248 + }, + { + "epoch": 0.38362135117713864, + "grad_norm": 0.6133678161071054, + "learning_rate": 1.4127824915498852e-05, + "loss": 0.8902, + "step": 6249 + }, + { + "epoch": 0.38368274041560513, + "grad_norm": 0.6992457108465453, + "learning_rate": 1.4126013786018407e-05, + "loss": 0.8619, + "step": 6250 + }, + { + "epoch": 0.3837441296540716, + "grad_norm": 0.7784079766832944, + "learning_rate": 1.4124202493414574e-05, + "loss": 0.8785, + "step": 6251 + }, + { + "epoch": 0.3838055188925381, + "grad_norm": 0.6987176383186043, + "learning_rate": 1.4122391037758956e-05, + "loss": 0.896, + "step": 6252 + }, + { + "epoch": 0.38386690813100466, + "grad_norm": 0.6737612309351215, + "learning_rate": 1.4120579419123175e-05, + "loss": 0.8328, + "step": 6253 + }, + { + "epoch": 0.38392829736947115, + "grad_norm": 0.7549140979516513, + "learning_rate": 1.4118767637578846e-05, + "loss": 0.9263, + "step": 6254 + }, + { + "epoch": 0.38398968660793764, + "grad_norm": 0.7540184942917765, + "learning_rate": 1.4116955693197607e-05, + "loss": 0.9057, + "step": 6255 + }, + { + "epoch": 0.38405107584640413, + "grad_norm": 0.6991064782293128, + "learning_rate": 1.411514358605109e-05, + "loss": 0.8728, + "step": 6256 + }, + { + "epoch": 0.3841124650848706, + "grad_norm": 0.7504624198571722, + "learning_rate": 1.4113331316210937e-05, + "loss": 0.8855, + "step": 6257 + }, + { + "epoch": 0.3841738543233371, + "grad_norm": 0.7261227964506469, + "learning_rate": 1.4111518883748798e-05, + "loss": 0.9021, + "step": 6258 + }, + { + "epoch": 0.3842352435618036, + "grad_norm": 0.7089905395612636, + "learning_rate": 1.4109706288736326e-05, + "loss": 0.9026, + "step": 6259 + }, + { + "epoch": 0.3842966328002701, + "grad_norm": 0.7402952629482461, + "learning_rate": 1.4107893531245187e-05, + "loss": 0.9196, + "step": 6260 + }, + { + "epoch": 0.3843580220387366, + "grad_norm": 0.8120240709931733, + "learning_rate": 1.4106080611347043e-05, + "loss": 0.9665, + "step": 6261 + }, + { + "epoch": 0.3844194112772031, + "grad_norm": 0.7467228775678546, + "learning_rate": 1.4104267529113575e-05, + "loss": 0.8877, + "step": 6262 + }, + { + "epoch": 0.38448080051566963, + "grad_norm": 0.6587518857443235, + "learning_rate": 1.410245428461646e-05, + "loss": 0.8814, + "step": 6263 + }, + { + "epoch": 0.3845421897541361, + "grad_norm": 0.7113420349944627, + "learning_rate": 1.4100640877927383e-05, + "loss": 0.966, + "step": 6264 + }, + { + "epoch": 0.3846035789926026, + "grad_norm": 0.7130937825869622, + "learning_rate": 1.4098827309118042e-05, + "loss": 0.923, + "step": 6265 + }, + { + "epoch": 0.3846649682310691, + "grad_norm": 0.7308205240550537, + "learning_rate": 1.4097013578260135e-05, + "loss": 0.8964, + "step": 6266 + }, + { + "epoch": 0.3847263574695356, + "grad_norm": 0.7008002422069046, + "learning_rate": 1.4095199685425369e-05, + "loss": 0.8615, + "step": 6267 + }, + { + "epoch": 0.3847877467080021, + "grad_norm": 0.7695265008144476, + "learning_rate": 1.4093385630685459e-05, + "loss": 0.958, + "step": 6268 + }, + { + "epoch": 0.3848491359464686, + "grad_norm": 0.7354121224838566, + "learning_rate": 1.4091571414112119e-05, + "loss": 0.8527, + "step": 6269 + }, + { + "epoch": 0.38491052518493507, + "grad_norm": 0.6730503575054037, + "learning_rate": 1.408975703577708e-05, + "loss": 0.8254, + "step": 6270 + }, + { + "epoch": 0.38497191442340156, + "grad_norm": 0.7236081292741805, + "learning_rate": 1.4087942495752068e-05, + "loss": 0.8854, + "step": 6271 + }, + { + "epoch": 0.38503330366186805, + "grad_norm": 0.7532536756882807, + "learning_rate": 1.4086127794108829e-05, + "loss": 0.916, + "step": 6272 + }, + { + "epoch": 0.38509469290033455, + "grad_norm": 0.7350069632085213, + "learning_rate": 1.4084312930919102e-05, + "loss": 0.8963, + "step": 6273 + }, + { + "epoch": 0.3851560821388011, + "grad_norm": 0.713836211827639, + "learning_rate": 1.4082497906254641e-05, + "loss": 0.9014, + "step": 6274 + }, + { + "epoch": 0.3852174713772676, + "grad_norm": 0.7388038743763667, + "learning_rate": 1.4080682720187207e-05, + "loss": 0.8726, + "step": 6275 + }, + { + "epoch": 0.3852788606157341, + "grad_norm": 0.7183379265662384, + "learning_rate": 1.4078867372788554e-05, + "loss": 0.9201, + "step": 6276 + }, + { + "epoch": 0.38534024985420057, + "grad_norm": 0.7220254408415455, + "learning_rate": 1.407705186413046e-05, + "loss": 0.8891, + "step": 6277 + }, + { + "epoch": 0.38540163909266706, + "grad_norm": 0.7166793277356376, + "learning_rate": 1.4075236194284703e-05, + "loss": 0.927, + "step": 6278 + }, + { + "epoch": 0.38546302833113355, + "grad_norm": 0.6734333135893374, + "learning_rate": 1.4073420363323061e-05, + "loss": 0.8652, + "step": 6279 + }, + { + "epoch": 0.38552441756960004, + "grad_norm": 0.6853739345543776, + "learning_rate": 1.4071604371317326e-05, + "loss": 0.9088, + "step": 6280 + }, + { + "epoch": 0.38558580680806653, + "grad_norm": 0.6753661821746696, + "learning_rate": 1.4069788218339296e-05, + "loss": 0.9038, + "step": 6281 + }, + { + "epoch": 0.385647196046533, + "grad_norm": 0.6740495688352813, + "learning_rate": 1.4067971904460765e-05, + "loss": 0.8948, + "step": 6282 + }, + { + "epoch": 0.3857085852849995, + "grad_norm": 0.6485511975513253, + "learning_rate": 1.4066155429753554e-05, + "loss": 0.8996, + "step": 6283 + }, + { + "epoch": 0.38576997452346606, + "grad_norm": 0.7336247155639447, + "learning_rate": 1.4064338794289467e-05, + "loss": 0.917, + "step": 6284 + }, + { + "epoch": 0.38583136376193256, + "grad_norm": 0.6761350953637971, + "learning_rate": 1.4062521998140336e-05, + "loss": 0.8227, + "step": 6285 + }, + { + "epoch": 0.38589275300039905, + "grad_norm": 0.7653288050400525, + "learning_rate": 1.4060705041377976e-05, + "loss": 0.9339, + "step": 6286 + }, + { + "epoch": 0.38595414223886554, + "grad_norm": 0.7113288328040761, + "learning_rate": 1.4058887924074229e-05, + "loss": 0.8957, + "step": 6287 + }, + { + "epoch": 0.38601553147733203, + "grad_norm": 0.7443874171360247, + "learning_rate": 1.4057070646300937e-05, + "loss": 0.905, + "step": 6288 + }, + { + "epoch": 0.3860769207157985, + "grad_norm": 0.7287495391470019, + "learning_rate": 1.405525320812994e-05, + "loss": 0.938, + "step": 6289 + }, + { + "epoch": 0.386138309954265, + "grad_norm": 0.7193872593705568, + "learning_rate": 1.4053435609633098e-05, + "loss": 0.9604, + "step": 6290 + }, + { + "epoch": 0.3861996991927315, + "grad_norm": 0.6889785323310207, + "learning_rate": 1.4051617850882262e-05, + "loss": 0.8647, + "step": 6291 + }, + { + "epoch": 0.386261088431198, + "grad_norm": 0.646596136860491, + "learning_rate": 1.4049799931949308e-05, + "loss": 0.8459, + "step": 6292 + }, + { + "epoch": 0.3863224776696645, + "grad_norm": 0.7350351433533617, + "learning_rate": 1.40479818529061e-05, + "loss": 0.9322, + "step": 6293 + }, + { + "epoch": 0.386383866908131, + "grad_norm": 0.6919504106743064, + "learning_rate": 1.404616361382452e-05, + "loss": 0.9156, + "step": 6294 + }, + { + "epoch": 0.3864452561465975, + "grad_norm": 0.6989839545185805, + "learning_rate": 1.4044345214776454e-05, + "loss": 0.9298, + "step": 6295 + }, + { + "epoch": 0.386506645385064, + "grad_norm": 0.6632901919042953, + "learning_rate": 1.4042526655833788e-05, + "loss": 0.9282, + "step": 6296 + }, + { + "epoch": 0.3865680346235305, + "grad_norm": 0.7059584825292073, + "learning_rate": 1.4040707937068423e-05, + "loss": 0.909, + "step": 6297 + }, + { + "epoch": 0.386629423861997, + "grad_norm": 0.7130438343118666, + "learning_rate": 1.4038889058552262e-05, + "loss": 0.9226, + "step": 6298 + }, + { + "epoch": 0.3866908131004635, + "grad_norm": 0.6760701185629375, + "learning_rate": 1.4037070020357215e-05, + "loss": 0.9045, + "step": 6299 + }, + { + "epoch": 0.38675220233893, + "grad_norm": 0.6966904639826175, + "learning_rate": 1.40352508225552e-05, + "loss": 0.903, + "step": 6300 + }, + { + "epoch": 0.3868135915773965, + "grad_norm": 0.6683400211433322, + "learning_rate": 1.4033431465218137e-05, + "loss": 0.9128, + "step": 6301 + }, + { + "epoch": 0.38687498081586297, + "grad_norm": 0.6909892057770725, + "learning_rate": 1.4031611948417956e-05, + "loss": 0.9305, + "step": 6302 + }, + { + "epoch": 0.38693637005432946, + "grad_norm": 0.6653426111197249, + "learning_rate": 1.402979227222659e-05, + "loss": 0.8847, + "step": 6303 + }, + { + "epoch": 0.38699775929279595, + "grad_norm": 0.6084193923419717, + "learning_rate": 1.4027972436715985e-05, + "loss": 0.7371, + "step": 6304 + }, + { + "epoch": 0.38705914853126244, + "grad_norm": 0.6490637017782402, + "learning_rate": 1.4026152441958085e-05, + "loss": 0.8821, + "step": 6305 + }, + { + "epoch": 0.387120537769729, + "grad_norm": 0.6528958353160917, + "learning_rate": 1.4024332288024846e-05, + "loss": 0.9184, + "step": 6306 + }, + { + "epoch": 0.3871819270081955, + "grad_norm": 0.6763357658552048, + "learning_rate": 1.402251197498823e-05, + "loss": 0.9029, + "step": 6307 + }, + { + "epoch": 0.387243316246662, + "grad_norm": 0.7487481183300408, + "learning_rate": 1.40206915029202e-05, + "loss": 0.8904, + "step": 6308 + }, + { + "epoch": 0.38730470548512846, + "grad_norm": 0.7471636446545102, + "learning_rate": 1.4018870871892729e-05, + "loss": 0.9063, + "step": 6309 + }, + { + "epoch": 0.38736609472359496, + "grad_norm": 0.7601021459686521, + "learning_rate": 1.4017050081977802e-05, + "loss": 0.9352, + "step": 6310 + }, + { + "epoch": 0.38742748396206145, + "grad_norm": 0.7176976672712093, + "learning_rate": 1.4015229133247397e-05, + "loss": 0.8972, + "step": 6311 + }, + { + "epoch": 0.38748887320052794, + "grad_norm": 0.6762791097377048, + "learning_rate": 1.4013408025773512e-05, + "loss": 0.9069, + "step": 6312 + }, + { + "epoch": 0.38755026243899443, + "grad_norm": 0.6907150844951582, + "learning_rate": 1.4011586759628139e-05, + "loss": 0.883, + "step": 6313 + }, + { + "epoch": 0.3876116516774609, + "grad_norm": 0.678081801165745, + "learning_rate": 1.4009765334883287e-05, + "loss": 0.8147, + "step": 6314 + }, + { + "epoch": 0.3876730409159274, + "grad_norm": 0.7876508833668787, + "learning_rate": 1.400794375161097e-05, + "loss": 0.9096, + "step": 6315 + }, + { + "epoch": 0.38773443015439396, + "grad_norm": 0.7523104581254048, + "learning_rate": 1.4006122009883195e-05, + "loss": 0.9524, + "step": 6316 + }, + { + "epoch": 0.38779581939286045, + "grad_norm": 0.6942915052625497, + "learning_rate": 1.4004300109771996e-05, + "loss": 0.8662, + "step": 6317 + }, + { + "epoch": 0.38785720863132694, + "grad_norm": 0.7893328912263913, + "learning_rate": 1.4002478051349394e-05, + "loss": 0.9367, + "step": 6318 + }, + { + "epoch": 0.38791859786979344, + "grad_norm": 0.7467336465560858, + "learning_rate": 1.4000655834687427e-05, + "loss": 0.9541, + "step": 6319 + }, + { + "epoch": 0.3879799871082599, + "grad_norm": 0.7305016689936994, + "learning_rate": 1.3998833459858138e-05, + "loss": 0.9118, + "step": 6320 + }, + { + "epoch": 0.3880413763467264, + "grad_norm": 0.739367233539273, + "learning_rate": 1.3997010926933574e-05, + "loss": 0.9234, + "step": 6321 + }, + { + "epoch": 0.3881027655851929, + "grad_norm": 0.7332605922442332, + "learning_rate": 1.3995188235985796e-05, + "loss": 0.9057, + "step": 6322 + }, + { + "epoch": 0.3881641548236594, + "grad_norm": 0.7358803267687198, + "learning_rate": 1.3993365387086852e-05, + "loss": 0.8936, + "step": 6323 + }, + { + "epoch": 0.3882255440621259, + "grad_norm": 0.6890936122998396, + "learning_rate": 1.3991542380308823e-05, + "loss": 0.85, + "step": 6324 + }, + { + "epoch": 0.3882869333005924, + "grad_norm": 0.7523035060609342, + "learning_rate": 1.3989719215723772e-05, + "loss": 0.9616, + "step": 6325 + }, + { + "epoch": 0.3883483225390589, + "grad_norm": 0.652194771421553, + "learning_rate": 1.3987895893403783e-05, + "loss": 0.908, + "step": 6326 + }, + { + "epoch": 0.3884097117775254, + "grad_norm": 0.6966831348810534, + "learning_rate": 1.3986072413420939e-05, + "loss": 0.8938, + "step": 6327 + }, + { + "epoch": 0.3884711010159919, + "grad_norm": 0.6961213417707114, + "learning_rate": 1.3984248775847333e-05, + "loss": 0.8647, + "step": 6328 + }, + { + "epoch": 0.3885324902544584, + "grad_norm": 0.7094013570218128, + "learning_rate": 1.3982424980755064e-05, + "loss": 0.9191, + "step": 6329 + }, + { + "epoch": 0.3885938794929249, + "grad_norm": 0.7272360532970529, + "learning_rate": 1.3980601028216239e-05, + "loss": 0.8852, + "step": 6330 + }, + { + "epoch": 0.3886552687313914, + "grad_norm": 0.7086333149505654, + "learning_rate": 1.3978776918302964e-05, + "loss": 0.8813, + "step": 6331 + }, + { + "epoch": 0.3887166579698579, + "grad_norm": 0.7035686445221249, + "learning_rate": 1.3976952651087356e-05, + "loss": 0.8704, + "step": 6332 + }, + { + "epoch": 0.3887780472083244, + "grad_norm": 0.6742370104783854, + "learning_rate": 1.3975128226641542e-05, + "loss": 0.8897, + "step": 6333 + }, + { + "epoch": 0.38883943644679086, + "grad_norm": 0.7590019778528624, + "learning_rate": 1.3973303645037648e-05, + "loss": 0.9035, + "step": 6334 + }, + { + "epoch": 0.38890082568525736, + "grad_norm": 0.9073919774811866, + "learning_rate": 1.3971478906347806e-05, + "loss": 0.9406, + "step": 6335 + }, + { + "epoch": 0.38896221492372385, + "grad_norm": 0.7145283014137427, + "learning_rate": 1.3969654010644167e-05, + "loss": 0.9027, + "step": 6336 + }, + { + "epoch": 0.3890236041621904, + "grad_norm": 0.6920604391843177, + "learning_rate": 1.3967828957998873e-05, + "loss": 0.8677, + "step": 6337 + }, + { + "epoch": 0.3890849934006569, + "grad_norm": 0.7522961373852809, + "learning_rate": 1.3966003748484079e-05, + "loss": 0.9578, + "step": 6338 + }, + { + "epoch": 0.3891463826391234, + "grad_norm": 0.7591833739181487, + "learning_rate": 1.3964178382171942e-05, + "loss": 0.8766, + "step": 6339 + }, + { + "epoch": 0.38920777187758987, + "grad_norm": 0.7337702608616751, + "learning_rate": 1.3962352859134633e-05, + "loss": 0.8921, + "step": 6340 + }, + { + "epoch": 0.38926916111605636, + "grad_norm": 0.6650627821617647, + "learning_rate": 1.3960527179444323e-05, + "loss": 0.7969, + "step": 6341 + }, + { + "epoch": 0.38933055035452285, + "grad_norm": 0.7391252565823091, + "learning_rate": 1.3958701343173193e-05, + "loss": 0.9196, + "step": 6342 + }, + { + "epoch": 0.38939193959298934, + "grad_norm": 0.6998963449518036, + "learning_rate": 1.3956875350393426e-05, + "loss": 0.8932, + "step": 6343 + }, + { + "epoch": 0.38945332883145584, + "grad_norm": 0.7208937442111157, + "learning_rate": 1.3955049201177213e-05, + "loss": 0.9063, + "step": 6344 + }, + { + "epoch": 0.3895147180699223, + "grad_norm": 0.7515837639231004, + "learning_rate": 1.3953222895596752e-05, + "loss": 0.8796, + "step": 6345 + }, + { + "epoch": 0.3895761073083888, + "grad_norm": 0.6823720138375453, + "learning_rate": 1.3951396433724245e-05, + "loss": 0.892, + "step": 6346 + }, + { + "epoch": 0.3896374965468553, + "grad_norm": 0.7399085085685922, + "learning_rate": 1.3949569815631907e-05, + "loss": 0.8868, + "step": 6347 + }, + { + "epoch": 0.38969888578532186, + "grad_norm": 0.6847373978656061, + "learning_rate": 1.3947743041391948e-05, + "loss": 0.874, + "step": 6348 + }, + { + "epoch": 0.38976027502378835, + "grad_norm": 0.7229120285226518, + "learning_rate": 1.3945916111076594e-05, + "loss": 0.8613, + "step": 6349 + }, + { + "epoch": 0.38982166426225484, + "grad_norm": 0.8627615361571089, + "learning_rate": 1.3944089024758069e-05, + "loss": 0.9586, + "step": 6350 + }, + { + "epoch": 0.38988305350072133, + "grad_norm": 0.5878295286738243, + "learning_rate": 1.3942261782508612e-05, + "loss": 0.6634, + "step": 6351 + }, + { + "epoch": 0.3899444427391878, + "grad_norm": 0.764476529746003, + "learning_rate": 1.3940434384400463e-05, + "loss": 0.9109, + "step": 6352 + }, + { + "epoch": 0.3900058319776543, + "grad_norm": 0.6654144778494433, + "learning_rate": 1.3938606830505864e-05, + "loss": 0.9026, + "step": 6353 + }, + { + "epoch": 0.3900672212161208, + "grad_norm": 0.7612226868149949, + "learning_rate": 1.393677912089708e-05, + "loss": 0.9141, + "step": 6354 + }, + { + "epoch": 0.3901286104545873, + "grad_norm": 0.7197376524538617, + "learning_rate": 1.3934951255646353e-05, + "loss": 0.8998, + "step": 6355 + }, + { + "epoch": 0.3901899996930538, + "grad_norm": 0.6914965712882389, + "learning_rate": 1.3933123234825963e-05, + "loss": 0.9153, + "step": 6356 + }, + { + "epoch": 0.3902513889315203, + "grad_norm": 0.7295237986895577, + "learning_rate": 1.3931295058508174e-05, + "loss": 0.9296, + "step": 6357 + }, + { + "epoch": 0.3903127781699868, + "grad_norm": 0.743508098283473, + "learning_rate": 1.3929466726765266e-05, + "loss": 0.9085, + "step": 6358 + }, + { + "epoch": 0.3903741674084533, + "grad_norm": 0.6521244804816786, + "learning_rate": 1.3927638239669522e-05, + "loss": 0.8573, + "step": 6359 + }, + { + "epoch": 0.3904355566469198, + "grad_norm": 0.6906733513115612, + "learning_rate": 1.3925809597293229e-05, + "loss": 0.896, + "step": 6360 + }, + { + "epoch": 0.3904969458853863, + "grad_norm": 0.7890018750837744, + "learning_rate": 1.3923980799708687e-05, + "loss": 0.9311, + "step": 6361 + }, + { + "epoch": 0.3905583351238528, + "grad_norm": 0.6732307355939937, + "learning_rate": 1.3922151846988201e-05, + "loss": 0.8926, + "step": 6362 + }, + { + "epoch": 0.3906197243623193, + "grad_norm": 0.7993360189247968, + "learning_rate": 1.3920322739204072e-05, + "loss": 0.8977, + "step": 6363 + }, + { + "epoch": 0.3906811136007858, + "grad_norm": 0.7033526982101538, + "learning_rate": 1.3918493476428618e-05, + "loss": 0.8994, + "step": 6364 + }, + { + "epoch": 0.39074250283925227, + "grad_norm": 0.77631927739213, + "learning_rate": 1.3916664058734159e-05, + "loss": 1.0087, + "step": 6365 + }, + { + "epoch": 0.39080389207771876, + "grad_norm": 0.6358598881984397, + "learning_rate": 1.3914834486193023e-05, + "loss": 0.8896, + "step": 6366 + }, + { + "epoch": 0.39086528131618525, + "grad_norm": 0.7913952565700367, + "learning_rate": 1.3913004758877539e-05, + "loss": 0.9046, + "step": 6367 + }, + { + "epoch": 0.39092667055465175, + "grad_norm": 0.7588665576525366, + "learning_rate": 1.3911174876860053e-05, + "loss": 0.8621, + "step": 6368 + }, + { + "epoch": 0.3909880597931183, + "grad_norm": 0.7002266587753575, + "learning_rate": 1.3909344840212903e-05, + "loss": 0.9463, + "step": 6369 + }, + { + "epoch": 0.3910494490315848, + "grad_norm": 0.6435478400312055, + "learning_rate": 1.3907514649008445e-05, + "loss": 0.8729, + "step": 6370 + }, + { + "epoch": 0.3911108382700513, + "grad_norm": 0.6178085596036775, + "learning_rate": 1.3905684303319032e-05, + "loss": 0.8815, + "step": 6371 + }, + { + "epoch": 0.39117222750851777, + "grad_norm": 0.7436980242971439, + "learning_rate": 1.390385380321703e-05, + "loss": 0.9478, + "step": 6372 + }, + { + "epoch": 0.39123361674698426, + "grad_norm": 0.6816254042916395, + "learning_rate": 1.3902023148774806e-05, + "loss": 0.8749, + "step": 6373 + }, + { + "epoch": 0.39129500598545075, + "grad_norm": 0.6698893368879354, + "learning_rate": 1.390019234006474e-05, + "loss": 0.9237, + "step": 6374 + }, + { + "epoch": 0.39135639522391724, + "grad_norm": 0.6859136122549653, + "learning_rate": 1.3898361377159211e-05, + "loss": 0.9094, + "step": 6375 + }, + { + "epoch": 0.39141778446238373, + "grad_norm": 0.676011505346491, + "learning_rate": 1.3896530260130608e-05, + "loss": 0.9135, + "step": 6376 + }, + { + "epoch": 0.3914791737008502, + "grad_norm": 0.6808235669020843, + "learning_rate": 1.3894698989051321e-05, + "loss": 0.8297, + "step": 6377 + }, + { + "epoch": 0.3915405629393167, + "grad_norm": 0.736069389826341, + "learning_rate": 1.389286756399375e-05, + "loss": 0.8986, + "step": 6378 + }, + { + "epoch": 0.3916019521777832, + "grad_norm": 0.6987770813666029, + "learning_rate": 1.389103598503031e-05, + "loss": 0.8901, + "step": 6379 + }, + { + "epoch": 0.39166334141624976, + "grad_norm": 0.7120921938697691, + "learning_rate": 1.3889204252233403e-05, + "loss": 0.8884, + "step": 6380 + }, + { + "epoch": 0.39172473065471625, + "grad_norm": 0.7502515188282156, + "learning_rate": 1.3887372365675452e-05, + "loss": 0.8978, + "step": 6381 + }, + { + "epoch": 0.39178611989318274, + "grad_norm": 0.6871436475680798, + "learning_rate": 1.3885540325428882e-05, + "loss": 0.8597, + "step": 6382 + }, + { + "epoch": 0.39184750913164923, + "grad_norm": 0.7797994692943101, + "learning_rate": 1.3883708131566118e-05, + "loss": 0.9536, + "step": 6383 + }, + { + "epoch": 0.3919088983701157, + "grad_norm": 0.7411100251880639, + "learning_rate": 1.3881875784159604e-05, + "loss": 0.9407, + "step": 6384 + }, + { + "epoch": 0.3919702876085822, + "grad_norm": 0.7326012107026063, + "learning_rate": 1.3880043283281774e-05, + "loss": 0.902, + "step": 6385 + }, + { + "epoch": 0.3920316768470487, + "grad_norm": 0.7421932965144598, + "learning_rate": 1.3878210629005087e-05, + "loss": 0.8892, + "step": 6386 + }, + { + "epoch": 0.3920930660855152, + "grad_norm": 0.6046806827080461, + "learning_rate": 1.3876377821401985e-05, + "loss": 0.8747, + "step": 6387 + }, + { + "epoch": 0.3921544553239817, + "grad_norm": 0.7380434074063813, + "learning_rate": 1.3874544860544938e-05, + "loss": 0.9534, + "step": 6388 + }, + { + "epoch": 0.3922158445624482, + "grad_norm": 0.7187608988609452, + "learning_rate": 1.3872711746506413e-05, + "loss": 0.9029, + "step": 6389 + }, + { + "epoch": 0.3922772338009147, + "grad_norm": 0.7540590663098897, + "learning_rate": 1.3870878479358875e-05, + "loss": 0.8818, + "step": 6390 + }, + { + "epoch": 0.3923386230393812, + "grad_norm": 0.7356512195236016, + "learning_rate": 1.3869045059174813e-05, + "loss": 0.8888, + "step": 6391 + }, + { + "epoch": 0.3924000122778477, + "grad_norm": 0.7224939655428555, + "learning_rate": 1.3867211486026702e-05, + "loss": 0.9086, + "step": 6392 + }, + { + "epoch": 0.3924614015163142, + "grad_norm": 0.6079454383281705, + "learning_rate": 1.386537775998704e-05, + "loss": 0.7731, + "step": 6393 + }, + { + "epoch": 0.3925227907547807, + "grad_norm": 0.7015352740812532, + "learning_rate": 1.3863543881128324e-05, + "loss": 0.9078, + "step": 6394 + }, + { + "epoch": 0.3925841799932472, + "grad_norm": 0.6927760769065133, + "learning_rate": 1.386170984952305e-05, + "loss": 0.8821, + "step": 6395 + }, + { + "epoch": 0.3926455692317137, + "grad_norm": 0.6062979361322963, + "learning_rate": 1.3859875665243733e-05, + "loss": 0.7924, + "step": 6396 + }, + { + "epoch": 0.39270695847018017, + "grad_norm": 0.6881493831437613, + "learning_rate": 1.385804132836289e-05, + "loss": 0.9673, + "step": 6397 + }, + { + "epoch": 0.39276834770864666, + "grad_norm": 0.773798631753506, + "learning_rate": 1.3856206838953037e-05, + "loss": 0.9565, + "step": 6398 + }, + { + "epoch": 0.39282973694711315, + "grad_norm": 0.6761392615776691, + "learning_rate": 1.38543721970867e-05, + "loss": 0.9152, + "step": 6399 + }, + { + "epoch": 0.39289112618557964, + "grad_norm": 0.5907683231657034, + "learning_rate": 1.3852537402836421e-05, + "loss": 0.8715, + "step": 6400 + }, + { + "epoch": 0.3929525154240462, + "grad_norm": 0.7570923981377338, + "learning_rate": 1.3850702456274732e-05, + "loss": 0.8729, + "step": 6401 + }, + { + "epoch": 0.3930139046625127, + "grad_norm": 0.6846865443603177, + "learning_rate": 1.3848867357474179e-05, + "loss": 0.8822, + "step": 6402 + }, + { + "epoch": 0.3930752939009792, + "grad_norm": 0.6846299673728901, + "learning_rate": 1.3847032106507314e-05, + "loss": 0.8807, + "step": 6403 + }, + { + "epoch": 0.39313668313944566, + "grad_norm": 0.6560946211594295, + "learning_rate": 1.3845196703446695e-05, + "loss": 0.9211, + "step": 6404 + }, + { + "epoch": 0.39319807237791216, + "grad_norm": 0.6362675474108264, + "learning_rate": 1.3843361148364882e-05, + "loss": 0.8981, + "step": 6405 + }, + { + "epoch": 0.39325946161637865, + "grad_norm": 0.6712766074264898, + "learning_rate": 1.384152544133445e-05, + "loss": 0.8814, + "step": 6406 + }, + { + "epoch": 0.39332085085484514, + "grad_norm": 0.717474312255344, + "learning_rate": 1.3839689582427971e-05, + "loss": 0.8963, + "step": 6407 + }, + { + "epoch": 0.39338224009331163, + "grad_norm": 0.7471033361605943, + "learning_rate": 1.3837853571718027e-05, + "loss": 0.8743, + "step": 6408 + }, + { + "epoch": 0.3934436293317781, + "grad_norm": 0.7445951043284554, + "learning_rate": 1.3836017409277205e-05, + "loss": 0.9189, + "step": 6409 + }, + { + "epoch": 0.3935050185702446, + "grad_norm": 0.6822895893580883, + "learning_rate": 1.3834181095178096e-05, + "loss": 0.814, + "step": 6410 + }, + { + "epoch": 0.39356640780871116, + "grad_norm": 0.6568902989355425, + "learning_rate": 1.3832344629493306e-05, + "loss": 0.885, + "step": 6411 + }, + { + "epoch": 0.39362779704717765, + "grad_norm": 0.7816869677255459, + "learning_rate": 1.3830508012295431e-05, + "loss": 0.9647, + "step": 6412 + }, + { + "epoch": 0.39368918628564414, + "grad_norm": 0.701083897453427, + "learning_rate": 1.382867124365709e-05, + "loss": 0.8857, + "step": 6413 + }, + { + "epoch": 0.39375057552411064, + "grad_norm": 0.7121479439177646, + "learning_rate": 1.3826834323650899e-05, + "loss": 0.8707, + "step": 6414 + }, + { + "epoch": 0.3938119647625771, + "grad_norm": 0.630352587837781, + "learning_rate": 1.382499725234948e-05, + "loss": 0.8599, + "step": 6415 + }, + { + "epoch": 0.3938733540010436, + "grad_norm": 0.7307851403582458, + "learning_rate": 1.382316002982546e-05, + "loss": 0.9439, + "step": 6416 + }, + { + "epoch": 0.3939347432395101, + "grad_norm": 0.7372516288447, + "learning_rate": 1.3821322656151475e-05, + "loss": 0.9049, + "step": 6417 + }, + { + "epoch": 0.3939961324779766, + "grad_norm": 0.6843436169081529, + "learning_rate": 1.3819485131400171e-05, + "loss": 0.8835, + "step": 6418 + }, + { + "epoch": 0.3940575217164431, + "grad_norm": 0.655469504273448, + "learning_rate": 1.3817647455644188e-05, + "loss": 0.8315, + "step": 6419 + }, + { + "epoch": 0.3941189109549096, + "grad_norm": 0.6738950935550211, + "learning_rate": 1.3815809628956186e-05, + "loss": 0.8787, + "step": 6420 + }, + { + "epoch": 0.3941803001933761, + "grad_norm": 0.6971387208954507, + "learning_rate": 1.3813971651408819e-05, + "loss": 0.9165, + "step": 6421 + }, + { + "epoch": 0.3942416894318426, + "grad_norm": 0.7163065726729073, + "learning_rate": 1.3812133523074756e-05, + "loss": 0.9226, + "step": 6422 + }, + { + "epoch": 0.3943030786703091, + "grad_norm": 0.7126070111555903, + "learning_rate": 1.3810295244026665e-05, + "loss": 0.9091, + "step": 6423 + }, + { + "epoch": 0.3943644679087756, + "grad_norm": 0.7218066036943422, + "learning_rate": 1.3808456814337223e-05, + "loss": 0.9307, + "step": 6424 + }, + { + "epoch": 0.3944258571472421, + "grad_norm": 0.6519155801237602, + "learning_rate": 1.3806618234079114e-05, + "loss": 0.8719, + "step": 6425 + }, + { + "epoch": 0.3944872463857086, + "grad_norm": 0.7323085556611884, + "learning_rate": 1.380477950332503e-05, + "loss": 0.9292, + "step": 6426 + }, + { + "epoch": 0.3945486356241751, + "grad_norm": 0.7995827069787534, + "learning_rate": 1.380294062214766e-05, + "loss": 0.9196, + "step": 6427 + }, + { + "epoch": 0.3946100248626416, + "grad_norm": 0.7071631486299571, + "learning_rate": 1.380110159061971e-05, + "loss": 0.9469, + "step": 6428 + }, + { + "epoch": 0.39467141410110806, + "grad_norm": 0.6878404366606038, + "learning_rate": 1.3799262408813882e-05, + "loss": 0.8769, + "step": 6429 + }, + { + "epoch": 0.39473280333957456, + "grad_norm": 0.7993673336987032, + "learning_rate": 1.3797423076802892e-05, + "loss": 0.9077, + "step": 6430 + }, + { + "epoch": 0.39479419257804105, + "grad_norm": 0.6472432905147529, + "learning_rate": 1.379558359465946e-05, + "loss": 0.9187, + "step": 6431 + }, + { + "epoch": 0.39485558181650754, + "grad_norm": 0.780700613416979, + "learning_rate": 1.3793743962456303e-05, + "loss": 0.9459, + "step": 6432 + }, + { + "epoch": 0.3949169710549741, + "grad_norm": 0.7156038448616444, + "learning_rate": 1.379190418026616e-05, + "loss": 0.8892, + "step": 6433 + }, + { + "epoch": 0.3949783602934406, + "grad_norm": 0.6246834687530856, + "learning_rate": 1.3790064248161765e-05, + "loss": 0.7671, + "step": 6434 + }, + { + "epoch": 0.39503974953190707, + "grad_norm": 0.7532652587773929, + "learning_rate": 1.378822416621586e-05, + "loss": 0.9294, + "step": 6435 + }, + { + "epoch": 0.39510113877037356, + "grad_norm": 0.6976793492919984, + "learning_rate": 1.378638393450119e-05, + "loss": 0.8785, + "step": 6436 + }, + { + "epoch": 0.39516252800884005, + "grad_norm": 0.7925744534930752, + "learning_rate": 1.3784543553090513e-05, + "loss": 0.8852, + "step": 6437 + }, + { + "epoch": 0.39522391724730654, + "grad_norm": 0.6948667633550791, + "learning_rate": 1.378270302205659e-05, + "loss": 0.9039, + "step": 6438 + }, + { + "epoch": 0.39528530648577304, + "grad_norm": 0.7402089071423877, + "learning_rate": 1.3780862341472183e-05, + "loss": 0.8996, + "step": 6439 + }, + { + "epoch": 0.3953466957242395, + "grad_norm": 0.6964204387789281, + "learning_rate": 1.377902151141007e-05, + "loss": 0.8832, + "step": 6440 + }, + { + "epoch": 0.395408084962706, + "grad_norm": 0.6672434535369178, + "learning_rate": 1.3777180531943021e-05, + "loss": 0.9032, + "step": 6441 + }, + { + "epoch": 0.3954694742011725, + "grad_norm": 0.7419582592414329, + "learning_rate": 1.3775339403143824e-05, + "loss": 0.8936, + "step": 6442 + }, + { + "epoch": 0.39553086343963906, + "grad_norm": 0.7533496764966995, + "learning_rate": 1.3773498125085271e-05, + "loss": 0.9279, + "step": 6443 + }, + { + "epoch": 0.39559225267810555, + "grad_norm": 0.7047008335618812, + "learning_rate": 1.3771656697840152e-05, + "loss": 0.9006, + "step": 6444 + }, + { + "epoch": 0.39565364191657204, + "grad_norm": 0.6955826357122666, + "learning_rate": 1.3769815121481273e-05, + "loss": 0.8786, + "step": 6445 + }, + { + "epoch": 0.39571503115503853, + "grad_norm": 0.7315153000268279, + "learning_rate": 1.376797339608144e-05, + "loss": 0.8907, + "step": 6446 + }, + { + "epoch": 0.395776420393505, + "grad_norm": 0.6756064558153843, + "learning_rate": 1.3766131521713466e-05, + "loss": 0.864, + "step": 6447 + }, + { + "epoch": 0.3958378096319715, + "grad_norm": 0.7444716779037667, + "learning_rate": 1.3764289498450171e-05, + "loss": 0.9179, + "step": 6448 + }, + { + "epoch": 0.395899198870438, + "grad_norm": 0.6957389783074375, + "learning_rate": 1.3762447326364377e-05, + "loss": 0.8917, + "step": 6449 + }, + { + "epoch": 0.3959605881089045, + "grad_norm": 0.767129574089132, + "learning_rate": 1.3760605005528922e-05, + "loss": 0.8555, + "step": 6450 + }, + { + "epoch": 0.396021977347371, + "grad_norm": 0.6676041761627673, + "learning_rate": 1.3758762536016632e-05, + "loss": 0.9083, + "step": 6451 + }, + { + "epoch": 0.3960833665858375, + "grad_norm": 0.684734448884255, + "learning_rate": 1.375691991790036e-05, + "loss": 0.8867, + "step": 6452 + }, + { + "epoch": 0.396144755824304, + "grad_norm": 0.6579355803602287, + "learning_rate": 1.3755077151252949e-05, + "loss": 0.8869, + "step": 6453 + }, + { + "epoch": 0.3962061450627705, + "grad_norm": 0.7113669270211374, + "learning_rate": 1.3753234236147255e-05, + "loss": 0.8562, + "step": 6454 + }, + { + "epoch": 0.396267534301237, + "grad_norm": 0.7308694656961022, + "learning_rate": 1.3751391172656137e-05, + "loss": 0.9179, + "step": 6455 + }, + { + "epoch": 0.3963289235397035, + "grad_norm": 0.7864832858058916, + "learning_rate": 1.374954796085246e-05, + "loss": 0.9434, + "step": 6456 + }, + { + "epoch": 0.39639031277817, + "grad_norm": 0.7455989253713065, + "learning_rate": 1.3747704600809102e-05, + "loss": 0.902, + "step": 6457 + }, + { + "epoch": 0.3964517020166365, + "grad_norm": 0.7027754769937067, + "learning_rate": 1.3745861092598936e-05, + "loss": 0.8537, + "step": 6458 + }, + { + "epoch": 0.396513091255103, + "grad_norm": 0.6601140434840419, + "learning_rate": 1.3744017436294846e-05, + "loss": 0.8846, + "step": 6459 + }, + { + "epoch": 0.39657448049356947, + "grad_norm": 0.765524152222088, + "learning_rate": 1.3742173631969722e-05, + "loss": 0.9341, + "step": 6460 + }, + { + "epoch": 0.39663586973203596, + "grad_norm": 0.7596898830366715, + "learning_rate": 1.374032967969646e-05, + "loss": 0.9317, + "step": 6461 + }, + { + "epoch": 0.39669725897050245, + "grad_norm": 0.7400182913221555, + "learning_rate": 1.373848557954796e-05, + "loss": 0.8931, + "step": 6462 + }, + { + "epoch": 0.39675864820896894, + "grad_norm": 0.7006803199752277, + "learning_rate": 1.3736641331597131e-05, + "loss": 0.903, + "step": 6463 + }, + { + "epoch": 0.3968200374474355, + "grad_norm": 0.6705103340374592, + "learning_rate": 1.3734796935916888e-05, + "loss": 0.8623, + "step": 6464 + }, + { + "epoch": 0.396881426685902, + "grad_norm": 0.7012264492505421, + "learning_rate": 1.3732952392580143e-05, + "loss": 0.899, + "step": 6465 + }, + { + "epoch": 0.3969428159243685, + "grad_norm": 0.7444028013811866, + "learning_rate": 1.3731107701659827e-05, + "loss": 0.8633, + "step": 6466 + }, + { + "epoch": 0.39700420516283497, + "grad_norm": 0.8339971174013687, + "learning_rate": 1.372926286322887e-05, + "loss": 1.0209, + "step": 6467 + }, + { + "epoch": 0.39706559440130146, + "grad_norm": 0.6757879463606512, + "learning_rate": 1.3727417877360203e-05, + "loss": 0.8541, + "step": 6468 + }, + { + "epoch": 0.39712698363976795, + "grad_norm": 0.6709591449242617, + "learning_rate": 1.3725572744126772e-05, + "loss": 0.888, + "step": 6469 + }, + { + "epoch": 0.39718837287823444, + "grad_norm": 0.7014086927091372, + "learning_rate": 1.3723727463601526e-05, + "loss": 0.8714, + "step": 6470 + }, + { + "epoch": 0.39724976211670093, + "grad_norm": 0.706100996769611, + "learning_rate": 1.3721882035857416e-05, + "loss": 0.8934, + "step": 6471 + }, + { + "epoch": 0.3973111513551674, + "grad_norm": 0.7450799797073905, + "learning_rate": 1.3720036460967404e-05, + "loss": 0.9034, + "step": 6472 + }, + { + "epoch": 0.3973725405936339, + "grad_norm": 0.7833323297964817, + "learning_rate": 1.3718190739004455e-05, + "loss": 0.9723, + "step": 6473 + }, + { + "epoch": 0.3974339298321004, + "grad_norm": 0.7036747146197364, + "learning_rate": 1.3716344870041538e-05, + "loss": 0.8831, + "step": 6474 + }, + { + "epoch": 0.39749531907056695, + "grad_norm": 0.7425207524955988, + "learning_rate": 1.3714498854151636e-05, + "loss": 0.8776, + "step": 6475 + }, + { + "epoch": 0.39755670830903345, + "grad_norm": 0.7706027369833736, + "learning_rate": 1.3712652691407725e-05, + "loss": 0.9895, + "step": 6476 + }, + { + "epoch": 0.39761809754749994, + "grad_norm": 0.7436060348813048, + "learning_rate": 1.3710806381882796e-05, + "loss": 0.8854, + "step": 6477 + }, + { + "epoch": 0.39767948678596643, + "grad_norm": 0.5854347654073231, + "learning_rate": 1.3708959925649846e-05, + "loss": 0.8783, + "step": 6478 + }, + { + "epoch": 0.3977408760244329, + "grad_norm": 0.7186298103569735, + "learning_rate": 1.370711332278187e-05, + "loss": 0.9187, + "step": 6479 + }, + { + "epoch": 0.3978022652628994, + "grad_norm": 0.6590299829624711, + "learning_rate": 1.370526657335188e-05, + "loss": 0.9165, + "step": 6480 + }, + { + "epoch": 0.3978636545013659, + "grad_norm": 0.7499556989628822, + "learning_rate": 1.3703419677432884e-05, + "loss": 0.9424, + "step": 6481 + }, + { + "epoch": 0.3979250437398324, + "grad_norm": 0.7087244386072238, + "learning_rate": 1.3701572635097902e-05, + "loss": 0.8607, + "step": 6482 + }, + { + "epoch": 0.3979864329782989, + "grad_norm": 0.7802065409309603, + "learning_rate": 1.3699725446419954e-05, + "loss": 0.9926, + "step": 6483 + }, + { + "epoch": 0.3980478222167654, + "grad_norm": 0.7298592376685344, + "learning_rate": 1.3697878111472073e-05, + "loss": 0.8973, + "step": 6484 + }, + { + "epoch": 0.39810921145523187, + "grad_norm": 0.7925507828885029, + "learning_rate": 1.3696030630327292e-05, + "loss": 0.8886, + "step": 6485 + }, + { + "epoch": 0.3981706006936984, + "grad_norm": 0.7056272754492883, + "learning_rate": 1.3694183003058655e-05, + "loss": 0.9229, + "step": 6486 + }, + { + "epoch": 0.3982319899321649, + "grad_norm": 0.7494583833657048, + "learning_rate": 1.3692335229739205e-05, + "loss": 0.9076, + "step": 6487 + }, + { + "epoch": 0.3982933791706314, + "grad_norm": 0.7145684466140274, + "learning_rate": 1.3690487310441991e-05, + "loss": 0.9258, + "step": 6488 + }, + { + "epoch": 0.3983547684090979, + "grad_norm": 0.7347848192748543, + "learning_rate": 1.3688639245240078e-05, + "loss": 0.8855, + "step": 6489 + }, + { + "epoch": 0.3984161576475644, + "grad_norm": 0.6365400315610336, + "learning_rate": 1.368679103420653e-05, + "loss": 0.8351, + "step": 6490 + }, + { + "epoch": 0.3984775468860309, + "grad_norm": 0.7636369666056325, + "learning_rate": 1.3684942677414411e-05, + "loss": 0.8952, + "step": 6491 + }, + { + "epoch": 0.39853893612449737, + "grad_norm": 0.6705945004984278, + "learning_rate": 1.3683094174936801e-05, + "loss": 0.8893, + "step": 6492 + }, + { + "epoch": 0.39860032536296386, + "grad_norm": 0.6273459721634878, + "learning_rate": 1.3681245526846782e-05, + "loss": 0.8422, + "step": 6493 + }, + { + "epoch": 0.39866171460143035, + "grad_norm": 0.7952360116951631, + "learning_rate": 1.3679396733217434e-05, + "loss": 0.9052, + "step": 6494 + }, + { + "epoch": 0.39872310383989684, + "grad_norm": 0.7231152364316902, + "learning_rate": 1.3677547794121858e-05, + "loss": 0.9221, + "step": 6495 + }, + { + "epoch": 0.3987844930783634, + "grad_norm": 0.7282557720668587, + "learning_rate": 1.3675698709633147e-05, + "loss": 0.8758, + "step": 6496 + }, + { + "epoch": 0.3988458823168299, + "grad_norm": 0.6834859710781138, + "learning_rate": 1.3673849479824409e-05, + "loss": 0.8818, + "step": 6497 + }, + { + "epoch": 0.39890727155529637, + "grad_norm": 0.7671392017897146, + "learning_rate": 1.367200010476875e-05, + "loss": 0.9172, + "step": 6498 + }, + { + "epoch": 0.39896866079376286, + "grad_norm": 0.747843974578958, + "learning_rate": 1.3670150584539288e-05, + "loss": 0.9193, + "step": 6499 + }, + { + "epoch": 0.39903005003222936, + "grad_norm": 0.6429206124164255, + "learning_rate": 1.3668300919209144e-05, + "loss": 0.8843, + "step": 6500 + }, + { + "epoch": 0.39909143927069585, + "grad_norm": 0.6906791230009949, + "learning_rate": 1.3666451108851445e-05, + "loss": 0.8735, + "step": 6501 + }, + { + "epoch": 0.39915282850916234, + "grad_norm": 0.6236761433005032, + "learning_rate": 1.3664601153539324e-05, + "loss": 0.8526, + "step": 6502 + }, + { + "epoch": 0.39921421774762883, + "grad_norm": 0.6585608761836333, + "learning_rate": 1.366275105334592e-05, + "loss": 0.8851, + "step": 6503 + }, + { + "epoch": 0.3992756069860953, + "grad_norm": 0.6867350912942332, + "learning_rate": 1.3660900808344377e-05, + "loss": 0.8996, + "step": 6504 + }, + { + "epoch": 0.3993369962245618, + "grad_norm": 0.7089042215144316, + "learning_rate": 1.3659050418607844e-05, + "loss": 0.859, + "step": 6505 + }, + { + "epoch": 0.3993983854630283, + "grad_norm": 0.7049679843698511, + "learning_rate": 1.3657199884209478e-05, + "loss": 0.8855, + "step": 6506 + }, + { + "epoch": 0.39945977470149485, + "grad_norm": 0.6353510141345302, + "learning_rate": 1.3655349205222446e-05, + "loss": 0.8361, + "step": 6507 + }, + { + "epoch": 0.39952116393996134, + "grad_norm": 0.7504909892935052, + "learning_rate": 1.3653498381719902e-05, + "loss": 0.8611, + "step": 6508 + }, + { + "epoch": 0.39958255317842784, + "grad_norm": 0.6655589853699011, + "learning_rate": 1.365164741377503e-05, + "loss": 0.9025, + "step": 6509 + }, + { + "epoch": 0.3996439424168943, + "grad_norm": 0.7366428055691621, + "learning_rate": 1.3649796301461006e-05, + "loss": 0.8312, + "step": 6510 + }, + { + "epoch": 0.3997053316553608, + "grad_norm": 0.6752957351413712, + "learning_rate": 1.3647945044851011e-05, + "loss": 0.9008, + "step": 6511 + }, + { + "epoch": 0.3997667208938273, + "grad_norm": 0.709696656300416, + "learning_rate": 1.3646093644018244e-05, + "loss": 0.8854, + "step": 6512 + }, + { + "epoch": 0.3998281101322938, + "grad_norm": 0.739474447732973, + "learning_rate": 1.3644242099035889e-05, + "loss": 0.893, + "step": 6513 + }, + { + "epoch": 0.3998894993707603, + "grad_norm": 0.7196680169705585, + "learning_rate": 1.3642390409977156e-05, + "loss": 0.9252, + "step": 6514 + }, + { + "epoch": 0.3999508886092268, + "grad_norm": 0.800882368976562, + "learning_rate": 1.3640538576915248e-05, + "loss": 0.8754, + "step": 6515 + }, + { + "epoch": 0.4000122778476933, + "grad_norm": 0.7240970054845978, + "learning_rate": 1.3638686599923379e-05, + "loss": 0.9029, + "step": 6516 + }, + { + "epoch": 0.4000736670861598, + "grad_norm": 0.7372962998549509, + "learning_rate": 1.3636834479074768e-05, + "loss": 0.9181, + "step": 6517 + }, + { + "epoch": 0.4001350563246263, + "grad_norm": 0.8982448858915363, + "learning_rate": 1.3634982214442637e-05, + "loss": 0.8556, + "step": 6518 + }, + { + "epoch": 0.4001964455630928, + "grad_norm": 0.7721606867869117, + "learning_rate": 1.363312980610022e-05, + "loss": 0.8632, + "step": 6519 + }, + { + "epoch": 0.4002578348015593, + "grad_norm": 0.6357676702173994, + "learning_rate": 1.363127725412075e-05, + "loss": 0.825, + "step": 6520 + }, + { + "epoch": 0.4003192240400258, + "grad_norm": 0.7890166560483681, + "learning_rate": 1.3629424558577467e-05, + "loss": 0.9188, + "step": 6521 + }, + { + "epoch": 0.4003806132784923, + "grad_norm": 0.7514100659131593, + "learning_rate": 1.3627571719543622e-05, + "loss": 0.9144, + "step": 6522 + }, + { + "epoch": 0.4004420025169588, + "grad_norm": 0.7601276566807381, + "learning_rate": 1.3625718737092463e-05, + "loss": 0.8943, + "step": 6523 + }, + { + "epoch": 0.40050339175542526, + "grad_norm": 0.8005206626631282, + "learning_rate": 1.3623865611297254e-05, + "loss": 0.8643, + "step": 6524 + }, + { + "epoch": 0.40056478099389176, + "grad_norm": 0.7351651877615208, + "learning_rate": 1.3622012342231252e-05, + "loss": 0.881, + "step": 6525 + }, + { + "epoch": 0.40062617023235825, + "grad_norm": 0.7458678929668912, + "learning_rate": 1.3620158929967731e-05, + "loss": 0.9084, + "step": 6526 + }, + { + "epoch": 0.40068755947082474, + "grad_norm": 0.7330907274191183, + "learning_rate": 1.3618305374579967e-05, + "loss": 0.8986, + "step": 6527 + }, + { + "epoch": 0.4007489487092913, + "grad_norm": 0.7022743396654888, + "learning_rate": 1.361645167614124e-05, + "loss": 0.9113, + "step": 6528 + }, + { + "epoch": 0.4008103379477578, + "grad_norm": 0.7019394758668188, + "learning_rate": 1.3614597834724834e-05, + "loss": 0.9288, + "step": 6529 + }, + { + "epoch": 0.40087172718622427, + "grad_norm": 0.6953162674359776, + "learning_rate": 1.3612743850404044e-05, + "loss": 0.8643, + "step": 6530 + }, + { + "epoch": 0.40093311642469076, + "grad_norm": 0.7738268519051404, + "learning_rate": 1.3610889723252169e-05, + "loss": 0.9003, + "step": 6531 + }, + { + "epoch": 0.40099450566315725, + "grad_norm": 0.6329028977193081, + "learning_rate": 1.360903545334251e-05, + "loss": 0.8668, + "step": 6532 + }, + { + "epoch": 0.40105589490162374, + "grad_norm": 0.735717053370241, + "learning_rate": 1.3607181040748375e-05, + "loss": 0.9457, + "step": 6533 + }, + { + "epoch": 0.40111728414009024, + "grad_norm": 0.7344750835001456, + "learning_rate": 1.3605326485543083e-05, + "loss": 0.8866, + "step": 6534 + }, + { + "epoch": 0.4011786733785567, + "grad_norm": 0.7418428807621741, + "learning_rate": 1.360347178779995e-05, + "loss": 0.886, + "step": 6535 + }, + { + "epoch": 0.4012400626170232, + "grad_norm": 0.7622670647525781, + "learning_rate": 1.3601616947592308e-05, + "loss": 0.9772, + "step": 6536 + }, + { + "epoch": 0.4013014518554897, + "grad_norm": 0.7263382943484027, + "learning_rate": 1.3599761964993486e-05, + "loss": 0.9357, + "step": 6537 + }, + { + "epoch": 0.4013628410939562, + "grad_norm": 0.7213346525784758, + "learning_rate": 1.3597906840076815e-05, + "loss": 0.9006, + "step": 6538 + }, + { + "epoch": 0.40142423033242275, + "grad_norm": 0.7348243792904073, + "learning_rate": 1.359605157291565e-05, + "loss": 0.9098, + "step": 6539 + }, + { + "epoch": 0.40148561957088924, + "grad_norm": 0.7064973427444675, + "learning_rate": 1.3594196163583326e-05, + "loss": 0.8896, + "step": 6540 + }, + { + "epoch": 0.40154700880935573, + "grad_norm": 0.7829005228834133, + "learning_rate": 1.359234061215321e-05, + "loss": 0.9039, + "step": 6541 + }, + { + "epoch": 0.4016083980478222, + "grad_norm": 0.7120368358890912, + "learning_rate": 1.3590484918698654e-05, + "loss": 0.9044, + "step": 6542 + }, + { + "epoch": 0.4016697872862887, + "grad_norm": 0.6891098167254532, + "learning_rate": 1.3588629083293027e-05, + "loss": 0.8662, + "step": 6543 + }, + { + "epoch": 0.4017311765247552, + "grad_norm": 0.6774038252837529, + "learning_rate": 1.35867731060097e-05, + "loss": 0.8566, + "step": 6544 + }, + { + "epoch": 0.4017925657632217, + "grad_norm": 0.7114047461340202, + "learning_rate": 1.3584916986922048e-05, + "loss": 0.9046, + "step": 6545 + }, + { + "epoch": 0.4018539550016882, + "grad_norm": 0.7317886981985235, + "learning_rate": 1.3583060726103457e-05, + "loss": 0.9063, + "step": 6546 + }, + { + "epoch": 0.4019153442401547, + "grad_norm": 0.7628039186209813, + "learning_rate": 1.3581204323627307e-05, + "loss": 0.8389, + "step": 6547 + }, + { + "epoch": 0.4019767334786212, + "grad_norm": 0.7414062756108121, + "learning_rate": 1.3579347779566996e-05, + "loss": 0.9146, + "step": 6548 + }, + { + "epoch": 0.4020381227170877, + "grad_norm": 0.7254328128909726, + "learning_rate": 1.3577491093995928e-05, + "loss": 0.8996, + "step": 6549 + }, + { + "epoch": 0.4020995119555542, + "grad_norm": 0.6379479625881919, + "learning_rate": 1.3575634266987498e-05, + "loss": 0.8644, + "step": 6550 + }, + { + "epoch": 0.4021609011940207, + "grad_norm": 0.7823857158111767, + "learning_rate": 1.3573777298615127e-05, + "loss": 0.7635, + "step": 6551 + }, + { + "epoch": 0.4022222904324872, + "grad_norm": 0.7095831549949707, + "learning_rate": 1.3571920188952221e-05, + "loss": 0.8958, + "step": 6552 + }, + { + "epoch": 0.4022836796709537, + "grad_norm": 0.6357343350390596, + "learning_rate": 1.3570062938072208e-05, + "loss": 0.8701, + "step": 6553 + }, + { + "epoch": 0.4023450689094202, + "grad_norm": 0.7512008778676114, + "learning_rate": 1.3568205546048514e-05, + "loss": 0.9239, + "step": 6554 + }, + { + "epoch": 0.40240645814788667, + "grad_norm": 0.7306305097972758, + "learning_rate": 1.3566348012954568e-05, + "loss": 0.9365, + "step": 6555 + }, + { + "epoch": 0.40246784738635316, + "grad_norm": 0.6808273716229475, + "learning_rate": 1.3564490338863814e-05, + "loss": 0.9078, + "step": 6556 + }, + { + "epoch": 0.40252923662481965, + "grad_norm": 0.7029440325078898, + "learning_rate": 1.3562632523849693e-05, + "loss": 0.8629, + "step": 6557 + }, + { + "epoch": 0.40259062586328614, + "grad_norm": 0.7869823919324379, + "learning_rate": 1.3560774567985649e-05, + "loss": 0.9171, + "step": 6558 + }, + { + "epoch": 0.40265201510175264, + "grad_norm": 0.693811210026565, + "learning_rate": 1.3558916471345146e-05, + "loss": 0.9103, + "step": 6559 + }, + { + "epoch": 0.4027134043402192, + "grad_norm": 0.7218292368390978, + "learning_rate": 1.3557058234001642e-05, + "loss": 0.8826, + "step": 6560 + }, + { + "epoch": 0.4027747935786857, + "grad_norm": 0.7334474074026631, + "learning_rate": 1.3555199856028597e-05, + "loss": 0.9228, + "step": 6561 + }, + { + "epoch": 0.40283618281715217, + "grad_norm": 0.705873266808856, + "learning_rate": 1.355334133749949e-05, + "loss": 0.8746, + "step": 6562 + }, + { + "epoch": 0.40289757205561866, + "grad_norm": 0.8158336627956454, + "learning_rate": 1.3551482678487795e-05, + "loss": 0.963, + "step": 6563 + }, + { + "epoch": 0.40295896129408515, + "grad_norm": 0.6742079850369366, + "learning_rate": 1.3549623879066996e-05, + "loss": 0.8807, + "step": 6564 + }, + { + "epoch": 0.40302035053255164, + "grad_norm": 0.813055737424207, + "learning_rate": 1.3547764939310577e-05, + "loss": 0.9223, + "step": 6565 + }, + { + "epoch": 0.40308173977101813, + "grad_norm": 0.694070745365636, + "learning_rate": 1.3545905859292039e-05, + "loss": 0.9093, + "step": 6566 + }, + { + "epoch": 0.4031431290094846, + "grad_norm": 0.801757668493198, + "learning_rate": 1.3544046639084875e-05, + "loss": 0.9155, + "step": 6567 + }, + { + "epoch": 0.4032045182479511, + "grad_norm": 0.7796448460920692, + "learning_rate": 1.3542187278762593e-05, + "loss": 0.9353, + "step": 6568 + }, + { + "epoch": 0.4032659074864176, + "grad_norm": 0.660706267480335, + "learning_rate": 1.3540327778398703e-05, + "loss": 0.8664, + "step": 6569 + }, + { + "epoch": 0.40332729672488415, + "grad_norm": 0.7088714409939118, + "learning_rate": 1.3538468138066721e-05, + "loss": 0.8793, + "step": 6570 + }, + { + "epoch": 0.40338868596335065, + "grad_norm": 0.7315727529608252, + "learning_rate": 1.353660835784017e-05, + "loss": 0.9364, + "step": 6571 + }, + { + "epoch": 0.40345007520181714, + "grad_norm": 0.7386565500229545, + "learning_rate": 1.3534748437792573e-05, + "loss": 0.9241, + "step": 6572 + }, + { + "epoch": 0.40351146444028363, + "grad_norm": 0.6802353640172283, + "learning_rate": 1.3532888377997466e-05, + "loss": 0.9009, + "step": 6573 + }, + { + "epoch": 0.4035728536787501, + "grad_norm": 0.7258689485732354, + "learning_rate": 1.3531028178528387e-05, + "loss": 0.9376, + "step": 6574 + }, + { + "epoch": 0.4036342429172166, + "grad_norm": 0.6846044857987242, + "learning_rate": 1.3529167839458876e-05, + "loss": 0.8408, + "step": 6575 + }, + { + "epoch": 0.4036956321556831, + "grad_norm": 0.6663614183321127, + "learning_rate": 1.352730736086249e-05, + "loss": 0.8759, + "step": 6576 + }, + { + "epoch": 0.4037570213941496, + "grad_norm": 0.7205653518620639, + "learning_rate": 1.3525446742812773e-05, + "loss": 0.9008, + "step": 6577 + }, + { + "epoch": 0.4038184106326161, + "grad_norm": 0.6847936123019062, + "learning_rate": 1.3523585985383297e-05, + "loss": 0.9344, + "step": 6578 + }, + { + "epoch": 0.4038797998710826, + "grad_norm": 0.822106511582108, + "learning_rate": 1.3521725088647615e-05, + "loss": 0.9413, + "step": 6579 + }, + { + "epoch": 0.40394118910954907, + "grad_norm": 0.7883239348060503, + "learning_rate": 1.351986405267931e-05, + "loss": 0.9158, + "step": 6580 + }, + { + "epoch": 0.4040025783480156, + "grad_norm": 0.7530131649192042, + "learning_rate": 1.3518002877551953e-05, + "loss": 0.894, + "step": 6581 + }, + { + "epoch": 0.4040639675864821, + "grad_norm": 0.7099361197757761, + "learning_rate": 1.3516141563339123e-05, + "loss": 0.9121, + "step": 6582 + }, + { + "epoch": 0.4041253568249486, + "grad_norm": 0.7000698909760125, + "learning_rate": 1.3514280110114414e-05, + "loss": 0.8913, + "step": 6583 + }, + { + "epoch": 0.4041867460634151, + "grad_norm": 0.7665445112433892, + "learning_rate": 1.3512418517951415e-05, + "loss": 0.9551, + "step": 6584 + }, + { + "epoch": 0.4042481353018816, + "grad_norm": 0.7508331329147521, + "learning_rate": 1.3510556786923727e-05, + "loss": 0.8872, + "step": 6585 + }, + { + "epoch": 0.4043095245403481, + "grad_norm": 0.7642893601014312, + "learning_rate": 1.3508694917104954e-05, + "loss": 0.9343, + "step": 6586 + }, + { + "epoch": 0.40437091377881457, + "grad_norm": 0.7910701966109858, + "learning_rate": 1.3506832908568705e-05, + "loss": 0.9455, + "step": 6587 + }, + { + "epoch": 0.40443230301728106, + "grad_norm": 0.7050528136374643, + "learning_rate": 1.3504970761388595e-05, + "loss": 0.8787, + "step": 6588 + }, + { + "epoch": 0.40449369225574755, + "grad_norm": 0.8108137294900646, + "learning_rate": 1.3503108475638244e-05, + "loss": 0.9053, + "step": 6589 + }, + { + "epoch": 0.40455508149421404, + "grad_norm": 0.7542382013472848, + "learning_rate": 1.3501246051391279e-05, + "loss": 0.9322, + "step": 6590 + }, + { + "epoch": 0.4046164707326806, + "grad_norm": 0.6906916672202411, + "learning_rate": 1.3499383488721334e-05, + "loss": 0.8658, + "step": 6591 + }, + { + "epoch": 0.4046778599711471, + "grad_norm": 0.7478500434543531, + "learning_rate": 1.3497520787702044e-05, + "loss": 0.933, + "step": 6592 + }, + { + "epoch": 0.40473924920961357, + "grad_norm": 0.6700185597481245, + "learning_rate": 1.3495657948407049e-05, + "loss": 0.8693, + "step": 6593 + }, + { + "epoch": 0.40480063844808006, + "grad_norm": 0.7192770853518266, + "learning_rate": 1.349379497091e-05, + "loss": 0.8625, + "step": 6594 + }, + { + "epoch": 0.40486202768654656, + "grad_norm": 0.7652291947707219, + "learning_rate": 1.3491931855284546e-05, + "loss": 0.9405, + "step": 6595 + }, + { + "epoch": 0.40492341692501305, + "grad_norm": 0.7010833453511848, + "learning_rate": 1.3490068601604355e-05, + "loss": 0.8835, + "step": 6596 + }, + { + "epoch": 0.40498480616347954, + "grad_norm": 0.7088625755426521, + "learning_rate": 1.3488205209943082e-05, + "loss": 0.8425, + "step": 6597 + }, + { + "epoch": 0.40504619540194603, + "grad_norm": 0.7391095708254158, + "learning_rate": 1.3486341680374404e-05, + "loss": 0.9165, + "step": 6598 + }, + { + "epoch": 0.4051075846404125, + "grad_norm": 0.7353577887595815, + "learning_rate": 1.348447801297199e-05, + "loss": 0.9655, + "step": 6599 + }, + { + "epoch": 0.405168973878879, + "grad_norm": 0.7560066236828282, + "learning_rate": 1.3482614207809529e-05, + "loss": 0.9257, + "step": 6600 + }, + { + "epoch": 0.4052303631173455, + "grad_norm": 0.7473226493442043, + "learning_rate": 1.3480750264960698e-05, + "loss": 0.9445, + "step": 6601 + }, + { + "epoch": 0.40529175235581205, + "grad_norm": 0.6881631825438831, + "learning_rate": 1.3478886184499191e-05, + "loss": 0.8644, + "step": 6602 + }, + { + "epoch": 0.40535314159427854, + "grad_norm": 0.8114164595652602, + "learning_rate": 1.3477021966498712e-05, + "loss": 0.9569, + "step": 6603 + }, + { + "epoch": 0.40541453083274503, + "grad_norm": 0.6515028334589487, + "learning_rate": 1.3475157611032951e-05, + "loss": 0.9051, + "step": 6604 + }, + { + "epoch": 0.4054759200712115, + "grad_norm": 0.7382191180728169, + "learning_rate": 1.347329311817563e-05, + "loss": 0.8769, + "step": 6605 + }, + { + "epoch": 0.405537309309678, + "grad_norm": 0.6645072039654794, + "learning_rate": 1.3471428488000453e-05, + "loss": 0.8421, + "step": 6606 + }, + { + "epoch": 0.4055986985481445, + "grad_norm": 0.7493892107193987, + "learning_rate": 1.346956372058114e-05, + "loss": 0.9095, + "step": 6607 + }, + { + "epoch": 0.405660087786611, + "grad_norm": 0.6783593455144136, + "learning_rate": 1.3467698815991418e-05, + "loss": 0.9054, + "step": 6608 + }, + { + "epoch": 0.4057214770250775, + "grad_norm": 0.6695289821205456, + "learning_rate": 1.3465833774305016e-05, + "loss": 0.8773, + "step": 6609 + }, + { + "epoch": 0.405782866263544, + "grad_norm": 0.6662493742493345, + "learning_rate": 1.3463968595595672e-05, + "loss": 0.8463, + "step": 6610 + }, + { + "epoch": 0.4058442555020105, + "grad_norm": 0.6952638771604676, + "learning_rate": 1.3462103279937116e-05, + "loss": 0.8836, + "step": 6611 + }, + { + "epoch": 0.40590564474047697, + "grad_norm": 0.7120861834090982, + "learning_rate": 1.3460237827403103e-05, + "loss": 0.9047, + "step": 6612 + }, + { + "epoch": 0.4059670339789435, + "grad_norm": 0.7109765813849729, + "learning_rate": 1.3458372238067382e-05, + "loss": 0.8308, + "step": 6613 + }, + { + "epoch": 0.40602842321741, + "grad_norm": 0.7427835389848206, + "learning_rate": 1.3456506512003707e-05, + "loss": 0.9114, + "step": 6614 + }, + { + "epoch": 0.4060898124558765, + "grad_norm": 0.8003877377654047, + "learning_rate": 1.3454640649285848e-05, + "loss": 0.9282, + "step": 6615 + }, + { + "epoch": 0.406151201694343, + "grad_norm": 0.8915913139203879, + "learning_rate": 1.3452774649987563e-05, + "loss": 0.8964, + "step": 6616 + }, + { + "epoch": 0.4062125909328095, + "grad_norm": 0.7224788165807674, + "learning_rate": 1.3450908514182632e-05, + "loss": 0.918, + "step": 6617 + }, + { + "epoch": 0.406273980171276, + "grad_norm": 0.7132419972056774, + "learning_rate": 1.3449042241944832e-05, + "loss": 0.9481, + "step": 6618 + }, + { + "epoch": 0.40633536940974246, + "grad_norm": 0.6850234900294578, + "learning_rate": 1.3447175833347943e-05, + "loss": 0.8932, + "step": 6619 + }, + { + "epoch": 0.40639675864820896, + "grad_norm": 0.7568256622998917, + "learning_rate": 1.3445309288465758e-05, + "loss": 0.8822, + "step": 6620 + }, + { + "epoch": 0.40645814788667545, + "grad_norm": 0.6562521366579545, + "learning_rate": 1.3443442607372069e-05, + "loss": 0.85, + "step": 6621 + }, + { + "epoch": 0.40651953712514194, + "grad_norm": 0.7374069496139053, + "learning_rate": 1.3441575790140675e-05, + "loss": 0.9134, + "step": 6622 + }, + { + "epoch": 0.4065809263636085, + "grad_norm": 0.7727973947791965, + "learning_rate": 1.3439708836845387e-05, + "loss": 0.8778, + "step": 6623 + }, + { + "epoch": 0.406642315602075, + "grad_norm": 0.7320091896790418, + "learning_rate": 1.343784174756001e-05, + "loss": 0.9074, + "step": 6624 + }, + { + "epoch": 0.40670370484054147, + "grad_norm": 0.780556444790022, + "learning_rate": 1.3435974522358361e-05, + "loss": 0.976, + "step": 6625 + }, + { + "epoch": 0.40676509407900796, + "grad_norm": 0.6990093683036336, + "learning_rate": 1.3434107161314265e-05, + "loss": 0.8391, + "step": 6626 + }, + { + "epoch": 0.40682648331747445, + "grad_norm": 0.6892333922093015, + "learning_rate": 1.3432239664501543e-05, + "loss": 0.8638, + "step": 6627 + }, + { + "epoch": 0.40688787255594094, + "grad_norm": 0.7090511845596197, + "learning_rate": 1.343037203199403e-05, + "loss": 0.8274, + "step": 6628 + }, + { + "epoch": 0.40694926179440744, + "grad_norm": 0.7517372140392385, + "learning_rate": 1.3428504263865565e-05, + "loss": 0.877, + "step": 6629 + }, + { + "epoch": 0.4070106510328739, + "grad_norm": 0.673063579251433, + "learning_rate": 1.3426636360189991e-05, + "loss": 0.6816, + "step": 6630 + }, + { + "epoch": 0.4070720402713404, + "grad_norm": 0.670547488189315, + "learning_rate": 1.3424768321041153e-05, + "loss": 0.8533, + "step": 6631 + }, + { + "epoch": 0.4071334295098069, + "grad_norm": 0.7142568283861203, + "learning_rate": 1.3422900146492908e-05, + "loss": 0.8726, + "step": 6632 + }, + { + "epoch": 0.4071948187482734, + "grad_norm": 0.8538442060802175, + "learning_rate": 1.3421031836619111e-05, + "loss": 0.8962, + "step": 6633 + }, + { + "epoch": 0.40725620798673995, + "grad_norm": 0.7437550306965195, + "learning_rate": 1.3419163391493628e-05, + "loss": 0.8928, + "step": 6634 + }, + { + "epoch": 0.40731759722520644, + "grad_norm": 0.740345534553036, + "learning_rate": 1.3417294811190333e-05, + "loss": 0.8809, + "step": 6635 + }, + { + "epoch": 0.40737898646367293, + "grad_norm": 0.7406610090495951, + "learning_rate": 1.3415426095783094e-05, + "loss": 0.9071, + "step": 6636 + }, + { + "epoch": 0.4074403757021394, + "grad_norm": 0.7336327855808389, + "learning_rate": 1.3413557245345794e-05, + "loss": 0.8745, + "step": 6637 + }, + { + "epoch": 0.4075017649406059, + "grad_norm": 0.7106467590584353, + "learning_rate": 1.341168825995232e-05, + "loss": 0.8762, + "step": 6638 + }, + { + "epoch": 0.4075631541790724, + "grad_norm": 0.7223873653831681, + "learning_rate": 1.3409819139676562e-05, + "loss": 0.9664, + "step": 6639 + }, + { + "epoch": 0.4076245434175389, + "grad_norm": 0.6143180310666878, + "learning_rate": 1.340794988459242e-05, + "loss": 0.8475, + "step": 6640 + }, + { + "epoch": 0.4076859326560054, + "grad_norm": 0.7159984800684439, + "learning_rate": 1.3406080494773785e-05, + "loss": 0.8624, + "step": 6641 + }, + { + "epoch": 0.4077473218944719, + "grad_norm": 0.7213106447837027, + "learning_rate": 1.3404210970294578e-05, + "loss": 0.8651, + "step": 6642 + }, + { + "epoch": 0.4078087111329384, + "grad_norm": 0.6913043867408867, + "learning_rate": 1.34023413112287e-05, + "loss": 0.9031, + "step": 6643 + }, + { + "epoch": 0.4078701003714049, + "grad_norm": 0.756218824942224, + "learning_rate": 1.3400471517650073e-05, + "loss": 0.8898, + "step": 6644 + }, + { + "epoch": 0.4079314896098714, + "grad_norm": 0.7732895862672776, + "learning_rate": 1.339860158963262e-05, + "loss": 0.9061, + "step": 6645 + }, + { + "epoch": 0.4079928788483379, + "grad_norm": 0.7643696100003194, + "learning_rate": 1.339673152725027e-05, + "loss": 0.9315, + "step": 6646 + }, + { + "epoch": 0.4080542680868044, + "grad_norm": 0.7374304637583403, + "learning_rate": 1.3394861330576959e-05, + "loss": 0.8931, + "step": 6647 + }, + { + "epoch": 0.4081156573252709, + "grad_norm": 0.7367936959039117, + "learning_rate": 1.3392990999686617e-05, + "loss": 0.8854, + "step": 6648 + }, + { + "epoch": 0.4081770465637374, + "grad_norm": 0.7311154614761208, + "learning_rate": 1.3391120534653198e-05, + "loss": 0.9381, + "step": 6649 + }, + { + "epoch": 0.40823843580220387, + "grad_norm": 0.7131581410054462, + "learning_rate": 1.3389249935550646e-05, + "loss": 0.8546, + "step": 6650 + }, + { + "epoch": 0.40829982504067036, + "grad_norm": 0.7191424739506659, + "learning_rate": 1.3387379202452917e-05, + "loss": 0.9221, + "step": 6651 + }, + { + "epoch": 0.40836121427913685, + "grad_norm": 0.7197306538317699, + "learning_rate": 1.3385508335433969e-05, + "loss": 0.8792, + "step": 6652 + }, + { + "epoch": 0.40842260351760334, + "grad_norm": 0.811523683314016, + "learning_rate": 1.338363733456777e-05, + "loss": 0.9286, + "step": 6653 + }, + { + "epoch": 0.40848399275606984, + "grad_norm": 0.7381307562772367, + "learning_rate": 1.3381766199928292e-05, + "loss": 0.9199, + "step": 6654 + }, + { + "epoch": 0.4085453819945364, + "grad_norm": 0.7544745453657904, + "learning_rate": 1.337989493158951e-05, + "loss": 0.892, + "step": 6655 + }, + { + "epoch": 0.4086067712330029, + "grad_norm": 0.7731969198728744, + "learning_rate": 1.3378023529625403e-05, + "loss": 0.8953, + "step": 6656 + }, + { + "epoch": 0.40866816047146937, + "grad_norm": 0.6864031197746421, + "learning_rate": 1.3376151994109958e-05, + "loss": 0.8905, + "step": 6657 + }, + { + "epoch": 0.40872954970993586, + "grad_norm": 0.7463778627954969, + "learning_rate": 1.337428032511717e-05, + "loss": 0.9361, + "step": 6658 + }, + { + "epoch": 0.40879093894840235, + "grad_norm": 0.6964526390565194, + "learning_rate": 1.3372408522721033e-05, + "loss": 0.8817, + "step": 6659 + }, + { + "epoch": 0.40885232818686884, + "grad_norm": 0.6972468035674436, + "learning_rate": 1.3370536586995549e-05, + "loss": 0.8941, + "step": 6660 + }, + { + "epoch": 0.40891371742533533, + "grad_norm": 0.6947053820284105, + "learning_rate": 1.3368664518014726e-05, + "loss": 0.9093, + "step": 6661 + }, + { + "epoch": 0.4089751066638018, + "grad_norm": 0.7385683004051844, + "learning_rate": 1.336679231585258e-05, + "loss": 0.8997, + "step": 6662 + }, + { + "epoch": 0.4090364959022683, + "grad_norm": 0.7609680738511233, + "learning_rate": 1.3364919980583126e-05, + "loss": 0.8639, + "step": 6663 + }, + { + "epoch": 0.4090978851407348, + "grad_norm": 0.7510443855488612, + "learning_rate": 1.3363047512280391e-05, + "loss": 0.9392, + "step": 6664 + }, + { + "epoch": 0.4091592743792013, + "grad_norm": 0.8039009060183926, + "learning_rate": 1.3361174911018398e-05, + "loss": 0.9026, + "step": 6665 + }, + { + "epoch": 0.40922066361766785, + "grad_norm": 0.7638141670159087, + "learning_rate": 1.3359302176871182e-05, + "loss": 0.9171, + "step": 6666 + }, + { + "epoch": 0.40928205285613434, + "grad_norm": 0.7301147940688111, + "learning_rate": 1.3357429309912789e-05, + "loss": 0.9245, + "step": 6667 + }, + { + "epoch": 0.40934344209460083, + "grad_norm": 0.7581056822283041, + "learning_rate": 1.3355556310217254e-05, + "loss": 0.9219, + "step": 6668 + }, + { + "epoch": 0.4094048313330673, + "grad_norm": 0.7254399097095102, + "learning_rate": 1.3353683177858634e-05, + "loss": 0.9024, + "step": 6669 + }, + { + "epoch": 0.4094662205715338, + "grad_norm": 0.6982725982495724, + "learning_rate": 1.3351809912910982e-05, + "loss": 0.9009, + "step": 6670 + }, + { + "epoch": 0.4095276098100003, + "grad_norm": 0.7016057318395235, + "learning_rate": 1.3349936515448353e-05, + "loss": 0.9028, + "step": 6671 + }, + { + "epoch": 0.4095889990484668, + "grad_norm": 0.5932964177626509, + "learning_rate": 1.3348062985544824e-05, + "loss": 0.8612, + "step": 6672 + }, + { + "epoch": 0.4096503882869333, + "grad_norm": 0.7337249538837539, + "learning_rate": 1.3346189323274452e-05, + "loss": 0.8807, + "step": 6673 + }, + { + "epoch": 0.4097117775253998, + "grad_norm": 0.7651532761742315, + "learning_rate": 1.3344315528711325e-05, + "loss": 0.971, + "step": 6674 + }, + { + "epoch": 0.40977316676386627, + "grad_norm": 0.818626014739798, + "learning_rate": 1.3342441601929514e-05, + "loss": 0.9282, + "step": 6675 + }, + { + "epoch": 0.4098345560023328, + "grad_norm": 0.7008796519650426, + "learning_rate": 1.334056754300311e-05, + "loss": 0.9181, + "step": 6676 + }, + { + "epoch": 0.4098959452407993, + "grad_norm": 0.6963760450333533, + "learning_rate": 1.3338693352006207e-05, + "loss": 0.8682, + "step": 6677 + }, + { + "epoch": 0.4099573344792658, + "grad_norm": 0.7442670429473647, + "learning_rate": 1.3336819029012895e-05, + "loss": 0.8648, + "step": 6678 + }, + { + "epoch": 0.4100187237177323, + "grad_norm": 0.6890117377599553, + "learning_rate": 1.3334944574097285e-05, + "loss": 0.9099, + "step": 6679 + }, + { + "epoch": 0.4100801129561988, + "grad_norm": 0.7808580139365263, + "learning_rate": 1.3333069987333475e-05, + "loss": 0.9348, + "step": 6680 + }, + { + "epoch": 0.4101415021946653, + "grad_norm": 0.7784127812532904, + "learning_rate": 1.3331195268795587e-05, + "loss": 0.877, + "step": 6681 + }, + { + "epoch": 0.41020289143313177, + "grad_norm": 0.7708518368176752, + "learning_rate": 1.332932041855773e-05, + "loss": 0.8698, + "step": 6682 + }, + { + "epoch": 0.41026428067159826, + "grad_norm": 0.730318262878578, + "learning_rate": 1.3327445436694033e-05, + "loss": 0.9277, + "step": 6683 + }, + { + "epoch": 0.41032566991006475, + "grad_norm": 0.7046293266748626, + "learning_rate": 1.3325570323278618e-05, + "loss": 0.8971, + "step": 6684 + }, + { + "epoch": 0.41038705914853124, + "grad_norm": 0.7262000640803532, + "learning_rate": 1.3323695078385624e-05, + "loss": 0.8621, + "step": 6685 + }, + { + "epoch": 0.41044844838699773, + "grad_norm": 0.7342648597821906, + "learning_rate": 1.3321819702089185e-05, + "loss": 0.8864, + "step": 6686 + }, + { + "epoch": 0.4105098376254643, + "grad_norm": 0.8178224965455211, + "learning_rate": 1.331994419446345e-05, + "loss": 0.6991, + "step": 6687 + }, + { + "epoch": 0.41057122686393077, + "grad_norm": 0.7996467600120704, + "learning_rate": 1.3318068555582562e-05, + "loss": 0.9628, + "step": 6688 + }, + { + "epoch": 0.41063261610239726, + "grad_norm": 0.7383870855612907, + "learning_rate": 1.331619278552068e-05, + "loss": 0.9362, + "step": 6689 + }, + { + "epoch": 0.41069400534086375, + "grad_norm": 0.6701824650083728, + "learning_rate": 1.331431688435196e-05, + "loss": 0.8603, + "step": 6690 + }, + { + "epoch": 0.41075539457933025, + "grad_norm": 0.6880664454637329, + "learning_rate": 1.3312440852150565e-05, + "loss": 0.8729, + "step": 6691 + }, + { + "epoch": 0.41081678381779674, + "grad_norm": 0.7188975689396971, + "learning_rate": 1.3310564688990671e-05, + "loss": 0.8967, + "step": 6692 + }, + { + "epoch": 0.41087817305626323, + "grad_norm": 0.7495392867404772, + "learning_rate": 1.3308688394946444e-05, + "loss": 0.8766, + "step": 6693 + }, + { + "epoch": 0.4109395622947297, + "grad_norm": 0.7127598477126038, + "learning_rate": 1.3306811970092074e-05, + "loss": 0.8863, + "step": 6694 + }, + { + "epoch": 0.4110009515331962, + "grad_norm": 0.7716915617040698, + "learning_rate": 1.3304935414501738e-05, + "loss": 0.8677, + "step": 6695 + }, + { + "epoch": 0.4110623407716627, + "grad_norm": 0.7613016887503734, + "learning_rate": 1.3303058728249629e-05, + "loss": 0.9019, + "step": 6696 + }, + { + "epoch": 0.41112373001012925, + "grad_norm": 0.7409569180790989, + "learning_rate": 1.3301181911409944e-05, + "loss": 0.8695, + "step": 6697 + }, + { + "epoch": 0.41118511924859574, + "grad_norm": 0.8065586094439622, + "learning_rate": 1.3299304964056879e-05, + "loss": 0.8833, + "step": 6698 + }, + { + "epoch": 0.41124650848706223, + "grad_norm": 0.7103119536326412, + "learning_rate": 1.3297427886264645e-05, + "loss": 0.8734, + "step": 6699 + }, + { + "epoch": 0.4113078977255287, + "grad_norm": 0.8361795228915709, + "learning_rate": 1.3295550678107449e-05, + "loss": 0.9338, + "step": 6700 + }, + { + "epoch": 0.4113692869639952, + "grad_norm": 0.7500406378117871, + "learning_rate": 1.3293673339659511e-05, + "loss": 0.9044, + "step": 6701 + }, + { + "epoch": 0.4114306762024617, + "grad_norm": 0.7359086322331737, + "learning_rate": 1.329179587099505e-05, + "loss": 0.8943, + "step": 6702 + }, + { + "epoch": 0.4114920654409282, + "grad_norm": 0.7652448519770194, + "learning_rate": 1.3289918272188288e-05, + "loss": 0.8672, + "step": 6703 + }, + { + "epoch": 0.4115534546793947, + "grad_norm": 0.6833318667188228, + "learning_rate": 1.328804054331347e-05, + "loss": 0.8941, + "step": 6704 + }, + { + "epoch": 0.4116148439178612, + "grad_norm": 0.6966623011015545, + "learning_rate": 1.3286162684444816e-05, + "loss": 0.8906, + "step": 6705 + }, + { + "epoch": 0.4116762331563277, + "grad_norm": 0.6614836235448261, + "learning_rate": 1.328428469565658e-05, + "loss": 0.8267, + "step": 6706 + }, + { + "epoch": 0.41173762239479417, + "grad_norm": 0.7441173382318206, + "learning_rate": 1.3282406577023e-05, + "loss": 0.9301, + "step": 6707 + }, + { + "epoch": 0.4117990116332607, + "grad_norm": 0.7589677410824682, + "learning_rate": 1.3280528328618337e-05, + "loss": 0.8896, + "step": 6708 + }, + { + "epoch": 0.4118604008717272, + "grad_norm": 0.7462213676757342, + "learning_rate": 1.327864995051684e-05, + "loss": 0.9258, + "step": 6709 + }, + { + "epoch": 0.4119217901101937, + "grad_norm": 0.7471485920992597, + "learning_rate": 1.3276771442792775e-05, + "loss": 0.8538, + "step": 6710 + }, + { + "epoch": 0.4119831793486602, + "grad_norm": 0.7470737630224352, + "learning_rate": 1.3274892805520412e-05, + "loss": 0.9217, + "step": 6711 + }, + { + "epoch": 0.4120445685871267, + "grad_norm": 0.7171808435188697, + "learning_rate": 1.3273014038774019e-05, + "loss": 0.8787, + "step": 6712 + }, + { + "epoch": 0.41210595782559317, + "grad_norm": 0.799027695030872, + "learning_rate": 1.3271135142627878e-05, + "loss": 0.9318, + "step": 6713 + }, + { + "epoch": 0.41216734706405966, + "grad_norm": 0.7509334540190252, + "learning_rate": 1.326925611715627e-05, + "loss": 0.8885, + "step": 6714 + }, + { + "epoch": 0.41222873630252616, + "grad_norm": 0.7538848726518245, + "learning_rate": 1.3267376962433479e-05, + "loss": 0.8844, + "step": 6715 + }, + { + "epoch": 0.41229012554099265, + "grad_norm": 0.6917157170929878, + "learning_rate": 1.3265497678533803e-05, + "loss": 0.8666, + "step": 6716 + }, + { + "epoch": 0.41235151477945914, + "grad_norm": 0.7364586454116263, + "learning_rate": 1.3263618265531538e-05, + "loss": 0.8936, + "step": 6717 + }, + { + "epoch": 0.41241290401792563, + "grad_norm": 0.6721744345754529, + "learning_rate": 1.3261738723500987e-05, + "loss": 0.8848, + "step": 6718 + }, + { + "epoch": 0.4124742932563922, + "grad_norm": 0.7495387513990884, + "learning_rate": 1.3259859052516462e-05, + "loss": 0.9018, + "step": 6719 + }, + { + "epoch": 0.41253568249485867, + "grad_norm": 0.6386632559278906, + "learning_rate": 1.3257979252652273e-05, + "loss": 0.831, + "step": 6720 + }, + { + "epoch": 0.41259707173332516, + "grad_norm": 0.7064460968259306, + "learning_rate": 1.3256099323982739e-05, + "loss": 0.8529, + "step": 6721 + }, + { + "epoch": 0.41265846097179165, + "grad_norm": 0.7375646708299601, + "learning_rate": 1.3254219266582185e-05, + "loss": 0.927, + "step": 6722 + }, + { + "epoch": 0.41271985021025814, + "grad_norm": 0.7602123189053438, + "learning_rate": 1.3252339080524934e-05, + "loss": 0.9119, + "step": 6723 + }, + { + "epoch": 0.41278123944872464, + "grad_norm": 0.7487437509523893, + "learning_rate": 1.3250458765885327e-05, + "loss": 0.8539, + "step": 6724 + }, + { + "epoch": 0.4128426286871911, + "grad_norm": 0.794646020296731, + "learning_rate": 1.3248578322737703e-05, + "loss": 0.9042, + "step": 6725 + }, + { + "epoch": 0.4129040179256576, + "grad_norm": 0.746043575094002, + "learning_rate": 1.3246697751156404e-05, + "loss": 0.9148, + "step": 6726 + }, + { + "epoch": 0.4129654071641241, + "grad_norm": 0.7297859676223757, + "learning_rate": 1.3244817051215775e-05, + "loss": 0.8721, + "step": 6727 + }, + { + "epoch": 0.4130267964025906, + "grad_norm": 0.7419093370959473, + "learning_rate": 1.3242936222990173e-05, + "loss": 0.9007, + "step": 6728 + }, + { + "epoch": 0.41308818564105715, + "grad_norm": 0.7582344959895004, + "learning_rate": 1.324105526655396e-05, + "loss": 0.9116, + "step": 6729 + }, + { + "epoch": 0.41314957487952364, + "grad_norm": 0.7681607526554824, + "learning_rate": 1.3239174181981496e-05, + "loss": 0.9116, + "step": 6730 + }, + { + "epoch": 0.41321096411799013, + "grad_norm": 0.7897338689264906, + "learning_rate": 1.3237292969347154e-05, + "loss": 0.8809, + "step": 6731 + }, + { + "epoch": 0.4132723533564566, + "grad_norm": 0.7321375493311103, + "learning_rate": 1.3235411628725303e-05, + "loss": 0.8624, + "step": 6732 + }, + { + "epoch": 0.4133337425949231, + "grad_norm": 0.7217332251748512, + "learning_rate": 1.323353016019033e-05, + "loss": 0.858, + "step": 6733 + }, + { + "epoch": 0.4133951318333896, + "grad_norm": 0.6968122037261255, + "learning_rate": 1.3231648563816614e-05, + "loss": 0.9032, + "step": 6734 + }, + { + "epoch": 0.4134565210718561, + "grad_norm": 0.7691372469789189, + "learning_rate": 1.3229766839678547e-05, + "loss": 0.9005, + "step": 6735 + }, + { + "epoch": 0.4135179103103226, + "grad_norm": 0.8003189653907937, + "learning_rate": 1.3227884987850523e-05, + "loss": 0.9382, + "step": 6736 + }, + { + "epoch": 0.4135792995487891, + "grad_norm": 0.6668727203422153, + "learning_rate": 1.3226003008406941e-05, + "loss": 0.9016, + "step": 6737 + }, + { + "epoch": 0.4136406887872556, + "grad_norm": 0.6658137534853367, + "learning_rate": 1.3224120901422206e-05, + "loss": 0.8532, + "step": 6738 + }, + { + "epoch": 0.41370207802572206, + "grad_norm": 0.666885082062017, + "learning_rate": 1.3222238666970728e-05, + "loss": 0.7402, + "step": 6739 + }, + { + "epoch": 0.4137634672641886, + "grad_norm": 0.7621710501258598, + "learning_rate": 1.3220356305126922e-05, + "loss": 0.8565, + "step": 6740 + }, + { + "epoch": 0.4138248565026551, + "grad_norm": 0.7053395559420663, + "learning_rate": 1.3218473815965207e-05, + "loss": 0.9264, + "step": 6741 + }, + { + "epoch": 0.4138862457411216, + "grad_norm": 0.7481014797630359, + "learning_rate": 1.3216591199560007e-05, + "loss": 0.9259, + "step": 6742 + }, + { + "epoch": 0.4139476349795881, + "grad_norm": 0.7200146178520296, + "learning_rate": 1.3214708455985758e-05, + "loss": 0.8702, + "step": 6743 + }, + { + "epoch": 0.4140090242180546, + "grad_norm": 0.7996614053862009, + "learning_rate": 1.3212825585316887e-05, + "loss": 0.9064, + "step": 6744 + }, + { + "epoch": 0.41407041345652107, + "grad_norm": 0.7065084311920249, + "learning_rate": 1.3210942587627837e-05, + "loss": 0.8897, + "step": 6745 + }, + { + "epoch": 0.41413180269498756, + "grad_norm": 0.6856365268918566, + "learning_rate": 1.3209059462993054e-05, + "loss": 0.836, + "step": 6746 + }, + { + "epoch": 0.41419319193345405, + "grad_norm": 0.6096500958684461, + "learning_rate": 1.320717621148699e-05, + "loss": 0.7347, + "step": 6747 + }, + { + "epoch": 0.41425458117192054, + "grad_norm": 0.7161154426438193, + "learning_rate": 1.3205292833184094e-05, + "loss": 0.887, + "step": 6748 + }, + { + "epoch": 0.41431597041038704, + "grad_norm": 0.7285208906118822, + "learning_rate": 1.3203409328158827e-05, + "loss": 0.9126, + "step": 6749 + }, + { + "epoch": 0.4143773596488536, + "grad_norm": 0.7015009447476773, + "learning_rate": 1.320152569648566e-05, + "loss": 0.8867, + "step": 6750 + }, + { + "epoch": 0.4144387488873201, + "grad_norm": 0.7326024518081132, + "learning_rate": 1.3199641938239057e-05, + "loss": 0.8865, + "step": 6751 + }, + { + "epoch": 0.41450013812578657, + "grad_norm": 0.7091441350761709, + "learning_rate": 1.3197758053493496e-05, + "loss": 0.8733, + "step": 6752 + }, + { + "epoch": 0.41456152736425306, + "grad_norm": 0.7052303490581, + "learning_rate": 1.3195874042323457e-05, + "loss": 0.9092, + "step": 6753 + }, + { + "epoch": 0.41462291660271955, + "grad_norm": 0.6524153447088522, + "learning_rate": 1.3193989904803424e-05, + "loss": 0.8788, + "step": 6754 + }, + { + "epoch": 0.41468430584118604, + "grad_norm": 0.7125756882998835, + "learning_rate": 1.3192105641007886e-05, + "loss": 0.9149, + "step": 6755 + }, + { + "epoch": 0.41474569507965253, + "grad_norm": 0.7870192568174318, + "learning_rate": 1.3190221251011341e-05, + "loss": 0.9803, + "step": 6756 + }, + { + "epoch": 0.414807084318119, + "grad_norm": 0.7145615636825341, + "learning_rate": 1.3188336734888288e-05, + "loss": 0.862, + "step": 6757 + }, + { + "epoch": 0.4148684735565855, + "grad_norm": 0.6870628208850874, + "learning_rate": 1.3186452092713232e-05, + "loss": 0.886, + "step": 6758 + }, + { + "epoch": 0.414929862795052, + "grad_norm": 0.7597315670483055, + "learning_rate": 1.318456732456068e-05, + "loss": 0.8833, + "step": 6759 + }, + { + "epoch": 0.4149912520335185, + "grad_norm": 0.7757987343954629, + "learning_rate": 1.3182682430505152e-05, + "loss": 0.8706, + "step": 6760 + }, + { + "epoch": 0.41505264127198505, + "grad_norm": 0.6607833499451208, + "learning_rate": 1.3180797410621162e-05, + "loss": 0.8068, + "step": 6761 + }, + { + "epoch": 0.41511403051045154, + "grad_norm": 0.7578960185577043, + "learning_rate": 1.3178912264983239e-05, + "loss": 0.8965, + "step": 6762 + }, + { + "epoch": 0.41517541974891803, + "grad_norm": 0.7100089239596835, + "learning_rate": 1.3177026993665913e-05, + "loss": 0.9078, + "step": 6763 + }, + { + "epoch": 0.4152368089873845, + "grad_norm": 0.8123614949921096, + "learning_rate": 1.317514159674372e-05, + "loss": 0.9017, + "step": 6764 + }, + { + "epoch": 0.415298198225851, + "grad_norm": 0.6979012912041094, + "learning_rate": 1.3173256074291196e-05, + "loss": 0.856, + "step": 6765 + }, + { + "epoch": 0.4153595874643175, + "grad_norm": 0.7577995448130741, + "learning_rate": 1.3171370426382888e-05, + "loss": 0.9129, + "step": 6766 + }, + { + "epoch": 0.415420976702784, + "grad_norm": 0.7438595418599622, + "learning_rate": 1.3169484653093342e-05, + "loss": 0.9286, + "step": 6767 + }, + { + "epoch": 0.4154823659412505, + "grad_norm": 0.6715542859563359, + "learning_rate": 1.3167598754497122e-05, + "loss": 0.8518, + "step": 6768 + }, + { + "epoch": 0.415543755179717, + "grad_norm": 0.7438480336937908, + "learning_rate": 1.3165712730668778e-05, + "loss": 0.8977, + "step": 6769 + }, + { + "epoch": 0.41560514441818347, + "grad_norm": 0.7737671522851562, + "learning_rate": 1.3163826581682879e-05, + "loss": 0.9181, + "step": 6770 + }, + { + "epoch": 0.41566653365665, + "grad_norm": 0.6963426470431101, + "learning_rate": 1.3161940307613994e-05, + "loss": 0.9194, + "step": 6771 + }, + { + "epoch": 0.4157279228951165, + "grad_norm": 0.727723875692271, + "learning_rate": 1.3160053908536698e-05, + "loss": 0.8973, + "step": 6772 + }, + { + "epoch": 0.415789312133583, + "grad_norm": 0.7854434637243347, + "learning_rate": 1.3158167384525569e-05, + "loss": 0.8758, + "step": 6773 + }, + { + "epoch": 0.4158507013720495, + "grad_norm": 0.7647261359792132, + "learning_rate": 1.315628073565519e-05, + "loss": 0.8677, + "step": 6774 + }, + { + "epoch": 0.415912090610516, + "grad_norm": 0.7864072088993782, + "learning_rate": 1.3154393962000158e-05, + "loss": 0.9192, + "step": 6775 + }, + { + "epoch": 0.4159734798489825, + "grad_norm": 0.7664577101030762, + "learning_rate": 1.3152507063635058e-05, + "loss": 0.9349, + "step": 6776 + }, + { + "epoch": 0.41603486908744897, + "grad_norm": 0.7085566946116673, + "learning_rate": 1.3150620040634494e-05, + "loss": 0.8226, + "step": 6777 + }, + { + "epoch": 0.41609625832591546, + "grad_norm": 0.7266772603068627, + "learning_rate": 1.314873289307307e-05, + "loss": 0.9182, + "step": 6778 + }, + { + "epoch": 0.41615764756438195, + "grad_norm": 0.7471730379460811, + "learning_rate": 1.3146845621025393e-05, + "loss": 0.9269, + "step": 6779 + }, + { + "epoch": 0.41621903680284844, + "grad_norm": 0.759589236189108, + "learning_rate": 1.3144958224566078e-05, + "loss": 0.9047, + "step": 6780 + }, + { + "epoch": 0.41628042604131493, + "grad_norm": 0.6651916674442783, + "learning_rate": 1.3143070703769743e-05, + "loss": 0.8182, + "step": 6781 + }, + { + "epoch": 0.4163418152797815, + "grad_norm": 0.7519958839612642, + "learning_rate": 1.3141183058711014e-05, + "loss": 0.8956, + "step": 6782 + }, + { + "epoch": 0.41640320451824797, + "grad_norm": 0.724564334604243, + "learning_rate": 1.313929528946452e-05, + "loss": 0.9117, + "step": 6783 + }, + { + "epoch": 0.41646459375671446, + "grad_norm": 0.7484561419357655, + "learning_rate": 1.3137407396104891e-05, + "loss": 0.8393, + "step": 6784 + }, + { + "epoch": 0.41652598299518095, + "grad_norm": 0.7224294087747932, + "learning_rate": 1.3135519378706767e-05, + "loss": 0.8865, + "step": 6785 + }, + { + "epoch": 0.41658737223364745, + "grad_norm": 0.7804491480927379, + "learning_rate": 1.3133631237344795e-05, + "loss": 0.9137, + "step": 6786 + }, + { + "epoch": 0.41664876147211394, + "grad_norm": 0.759463591898615, + "learning_rate": 1.3131742972093615e-05, + "loss": 0.8712, + "step": 6787 + }, + { + "epoch": 0.41671015071058043, + "grad_norm": 0.7693939881884865, + "learning_rate": 1.312985458302789e-05, + "loss": 0.8832, + "step": 6788 + }, + { + "epoch": 0.4167715399490469, + "grad_norm": 0.7770124116341866, + "learning_rate": 1.3127966070222273e-05, + "loss": 0.881, + "step": 6789 + }, + { + "epoch": 0.4168329291875134, + "grad_norm": 0.7544596037781882, + "learning_rate": 1.3126077433751427e-05, + "loss": 0.8957, + "step": 6790 + }, + { + "epoch": 0.4168943184259799, + "grad_norm": 0.6666835318432975, + "learning_rate": 1.3124188673690022e-05, + "loss": 0.8682, + "step": 6791 + }, + { + "epoch": 0.4169557076644464, + "grad_norm": 0.6370743727131307, + "learning_rate": 1.3122299790112727e-05, + "loss": 0.8727, + "step": 6792 + }, + { + "epoch": 0.41701709690291294, + "grad_norm": 0.6816676023777909, + "learning_rate": 1.3120410783094224e-05, + "loss": 0.8321, + "step": 6793 + }, + { + "epoch": 0.41707848614137943, + "grad_norm": 0.67016053590245, + "learning_rate": 1.3118521652709194e-05, + "loss": 0.8846, + "step": 6794 + }, + { + "epoch": 0.4171398753798459, + "grad_norm": 0.8087389793879692, + "learning_rate": 1.3116632399032322e-05, + "loss": 0.9267, + "step": 6795 + }, + { + "epoch": 0.4172012646183124, + "grad_norm": 0.7507295534893776, + "learning_rate": 1.3114743022138303e-05, + "loss": 0.8968, + "step": 6796 + }, + { + "epoch": 0.4172626538567789, + "grad_norm": 0.7410876571956496, + "learning_rate": 1.3112853522101836e-05, + "loss": 0.8815, + "step": 6797 + }, + { + "epoch": 0.4173240430952454, + "grad_norm": 0.7260377400831133, + "learning_rate": 1.3110963898997618e-05, + "loss": 0.8441, + "step": 6798 + }, + { + "epoch": 0.4173854323337119, + "grad_norm": 0.7504295695614651, + "learning_rate": 1.3109074152900357e-05, + "loss": 0.8911, + "step": 6799 + }, + { + "epoch": 0.4174468215721784, + "grad_norm": 0.7577434065060492, + "learning_rate": 1.3107184283884771e-05, + "loss": 0.9275, + "step": 6800 + }, + { + "epoch": 0.4175082108106449, + "grad_norm": 0.698838273435502, + "learning_rate": 1.3105294292025566e-05, + "loss": 0.8592, + "step": 6801 + }, + { + "epoch": 0.41756960004911137, + "grad_norm": 0.7733320468291371, + "learning_rate": 1.3103404177397474e-05, + "loss": 0.9407, + "step": 6802 + }, + { + "epoch": 0.4176309892875779, + "grad_norm": 0.7135145990871589, + "learning_rate": 1.3101513940075214e-05, + "loss": 0.8804, + "step": 6803 + }, + { + "epoch": 0.4176923785260444, + "grad_norm": 0.7570983769029404, + "learning_rate": 1.309962358013352e-05, + "loss": 0.8392, + "step": 6804 + }, + { + "epoch": 0.4177537677645109, + "grad_norm": 0.7103185405386937, + "learning_rate": 1.3097733097647132e-05, + "loss": 0.8974, + "step": 6805 + }, + { + "epoch": 0.4178151570029774, + "grad_norm": 0.6807616201746485, + "learning_rate": 1.309584249269078e-05, + "loss": 0.9018, + "step": 6806 + }, + { + "epoch": 0.4178765462414439, + "grad_norm": 0.5600118923509488, + "learning_rate": 1.3093951765339223e-05, + "loss": 0.6534, + "step": 6807 + }, + { + "epoch": 0.41793793547991037, + "grad_norm": 0.746403409807969, + "learning_rate": 1.3092060915667202e-05, + "loss": 0.8709, + "step": 6808 + }, + { + "epoch": 0.41799932471837686, + "grad_norm": 0.6642196212808547, + "learning_rate": 1.3090169943749475e-05, + "loss": 0.8782, + "step": 6809 + }, + { + "epoch": 0.41806071395684336, + "grad_norm": 0.7065427979864786, + "learning_rate": 1.3088278849660805e-05, + "loss": 0.8291, + "step": 6810 + }, + { + "epoch": 0.41812210319530985, + "grad_norm": 0.7868069872735738, + "learning_rate": 1.3086387633475951e-05, + "loss": 0.8457, + "step": 6811 + }, + { + "epoch": 0.41818349243377634, + "grad_norm": 0.7608000344047663, + "learning_rate": 1.3084496295269692e-05, + "loss": 0.8711, + "step": 6812 + }, + { + "epoch": 0.41824488167224283, + "grad_norm": 0.7382298594863855, + "learning_rate": 1.3082604835116793e-05, + "loss": 0.8827, + "step": 6813 + }, + { + "epoch": 0.4183062709107094, + "grad_norm": 0.6858864969393049, + "learning_rate": 1.3080713253092039e-05, + "loss": 0.9053, + "step": 6814 + }, + { + "epoch": 0.41836766014917587, + "grad_norm": 0.7692819979953784, + "learning_rate": 1.3078821549270214e-05, + "loss": 0.8763, + "step": 6815 + }, + { + "epoch": 0.41842904938764236, + "grad_norm": 0.7434497358192097, + "learning_rate": 1.3076929723726107e-05, + "loss": 0.8744, + "step": 6816 + }, + { + "epoch": 0.41849043862610885, + "grad_norm": 0.6488203765431628, + "learning_rate": 1.307503777653451e-05, + "loss": 0.8648, + "step": 6817 + }, + { + "epoch": 0.41855182786457534, + "grad_norm": 0.6743256457454139, + "learning_rate": 1.3073145707770226e-05, + "loss": 0.8668, + "step": 6818 + }, + { + "epoch": 0.41861321710304183, + "grad_norm": 0.6997833170836375, + "learning_rate": 1.3071253517508052e-05, + "loss": 0.8593, + "step": 6819 + }, + { + "epoch": 0.4186746063415083, + "grad_norm": 0.6335247183578425, + "learning_rate": 1.3069361205822801e-05, + "loss": 0.8896, + "step": 6820 + }, + { + "epoch": 0.4187359955799748, + "grad_norm": 0.8052660965861114, + "learning_rate": 1.3067468772789287e-05, + "loss": 0.9164, + "step": 6821 + }, + { + "epoch": 0.4187973848184413, + "grad_norm": 0.7541812269729556, + "learning_rate": 1.3065576218482325e-05, + "loss": 0.8961, + "step": 6822 + }, + { + "epoch": 0.4188587740569078, + "grad_norm": 0.713021818559163, + "learning_rate": 1.3063683542976742e-05, + "loss": 0.8937, + "step": 6823 + }, + { + "epoch": 0.41892016329537435, + "grad_norm": 0.7793973032980656, + "learning_rate": 1.3061790746347357e-05, + "loss": 0.9161, + "step": 6824 + }, + { + "epoch": 0.41898155253384084, + "grad_norm": 0.7321316373702501, + "learning_rate": 1.3059897828669014e-05, + "loss": 0.9085, + "step": 6825 + }, + { + "epoch": 0.41904294177230733, + "grad_norm": 0.6638799514614879, + "learning_rate": 1.3058004790016543e-05, + "loss": 0.8332, + "step": 6826 + }, + { + "epoch": 0.4191043310107738, + "grad_norm": 0.6980004241147238, + "learning_rate": 1.3056111630464787e-05, + "loss": 0.8808, + "step": 6827 + }, + { + "epoch": 0.4191657202492403, + "grad_norm": 0.7639612323992384, + "learning_rate": 1.3054218350088592e-05, + "loss": 0.8869, + "step": 6828 + }, + { + "epoch": 0.4192271094877068, + "grad_norm": 0.7239867882498904, + "learning_rate": 1.3052324948962811e-05, + "loss": 0.874, + "step": 6829 + }, + { + "epoch": 0.4192884987261733, + "grad_norm": 0.6792648005182211, + "learning_rate": 1.30504314271623e-05, + "loss": 0.868, + "step": 6830 + }, + { + "epoch": 0.4193498879646398, + "grad_norm": 0.6186196804272935, + "learning_rate": 1.304853778476192e-05, + "loss": 0.7422, + "step": 6831 + }, + { + "epoch": 0.4194112772031063, + "grad_norm": 0.7157229415570386, + "learning_rate": 1.3046644021836538e-05, + "loss": 0.9396, + "step": 6832 + }, + { + "epoch": 0.4194726664415728, + "grad_norm": 0.7012290310394789, + "learning_rate": 1.3044750138461019e-05, + "loss": 0.8558, + "step": 6833 + }, + { + "epoch": 0.41953405568003926, + "grad_norm": 0.762772215550506, + "learning_rate": 1.3042856134710246e-05, + "loss": 0.862, + "step": 6834 + }, + { + "epoch": 0.4195954449185058, + "grad_norm": 0.8243505019295263, + "learning_rate": 1.3040962010659095e-05, + "loss": 0.9208, + "step": 6835 + }, + { + "epoch": 0.4196568341569723, + "grad_norm": 0.7125467766812774, + "learning_rate": 1.303906776638245e-05, + "loss": 0.9128, + "step": 6836 + }, + { + "epoch": 0.4197182233954388, + "grad_norm": 0.7106597809932169, + "learning_rate": 1.3037173401955205e-05, + "loss": 0.8958, + "step": 6837 + }, + { + "epoch": 0.4197796126339053, + "grad_norm": 0.8421615661796019, + "learning_rate": 1.303527891745225e-05, + "loss": 0.9287, + "step": 6838 + }, + { + "epoch": 0.4198410018723718, + "grad_norm": 0.7076863893088831, + "learning_rate": 1.3033384312948487e-05, + "loss": 0.8214, + "step": 6839 + }, + { + "epoch": 0.41990239111083827, + "grad_norm": 0.7534700848434223, + "learning_rate": 1.3031489588518816e-05, + "loss": 0.9351, + "step": 6840 + }, + { + "epoch": 0.41996378034930476, + "grad_norm": 0.791470863687818, + "learning_rate": 1.302959474423815e-05, + "loss": 0.8744, + "step": 6841 + }, + { + "epoch": 0.42002516958777125, + "grad_norm": 0.7643452248194124, + "learning_rate": 1.30276997801814e-05, + "loss": 0.883, + "step": 6842 + }, + { + "epoch": 0.42008655882623774, + "grad_norm": 0.7535815735135666, + "learning_rate": 1.3025804696423483e-05, + "loss": 0.8961, + "step": 6843 + }, + { + "epoch": 0.42014794806470424, + "grad_norm": 0.803924930445977, + "learning_rate": 1.3023909493039324e-05, + "loss": 0.8551, + "step": 6844 + }, + { + "epoch": 0.4202093373031707, + "grad_norm": 0.7684138118947206, + "learning_rate": 1.3022014170103847e-05, + "loss": 0.8933, + "step": 6845 + }, + { + "epoch": 0.4202707265416373, + "grad_norm": 0.8100697038258778, + "learning_rate": 1.302011872769199e-05, + "loss": 0.8912, + "step": 6846 + }, + { + "epoch": 0.42033211578010377, + "grad_norm": 0.7167087510009139, + "learning_rate": 1.301822316587869e-05, + "loss": 0.9081, + "step": 6847 + }, + { + "epoch": 0.42039350501857026, + "grad_norm": 0.774053314462362, + "learning_rate": 1.301632748473888e-05, + "loss": 0.8846, + "step": 6848 + }, + { + "epoch": 0.42045489425703675, + "grad_norm": 0.7367371335845124, + "learning_rate": 1.3014431684347515e-05, + "loss": 0.9109, + "step": 6849 + }, + { + "epoch": 0.42051628349550324, + "grad_norm": 0.7530413563387576, + "learning_rate": 1.3012535764779543e-05, + "loss": 0.896, + "step": 6850 + }, + { + "epoch": 0.42057767273396973, + "grad_norm": 0.7277831922554662, + "learning_rate": 1.301063972610992e-05, + "loss": 0.8878, + "step": 6851 + }, + { + "epoch": 0.4206390619724362, + "grad_norm": 0.6604799198940835, + "learning_rate": 1.3008743568413605e-05, + "loss": 0.8162, + "step": 6852 + }, + { + "epoch": 0.4207004512109027, + "grad_norm": 0.7941984415287165, + "learning_rate": 1.3006847291765565e-05, + "loss": 0.9146, + "step": 6853 + }, + { + "epoch": 0.4207618404493692, + "grad_norm": 0.8502780010888141, + "learning_rate": 1.3004950896240774e-05, + "loss": 0.9569, + "step": 6854 + }, + { + "epoch": 0.4208232296878357, + "grad_norm": 0.8120292345232747, + "learning_rate": 1.30030543819142e-05, + "loss": 0.8774, + "step": 6855 + }, + { + "epoch": 0.42088461892630225, + "grad_norm": 0.6379838472530877, + "learning_rate": 1.300115774886082e-05, + "loss": 0.8157, + "step": 6856 + }, + { + "epoch": 0.42094600816476874, + "grad_norm": 0.7228349755925862, + "learning_rate": 1.2999260997155632e-05, + "loss": 0.8439, + "step": 6857 + }, + { + "epoch": 0.42100739740323523, + "grad_norm": 0.7254438882030932, + "learning_rate": 1.2997364126873606e-05, + "loss": 0.8555, + "step": 6858 + }, + { + "epoch": 0.4210687866417017, + "grad_norm": 0.6734239223642171, + "learning_rate": 1.299546713808975e-05, + "loss": 0.8138, + "step": 6859 + }, + { + "epoch": 0.4211301758801682, + "grad_norm": 0.6792588663402154, + "learning_rate": 1.2993570030879059e-05, + "loss": 0.8394, + "step": 6860 + }, + { + "epoch": 0.4211915651186347, + "grad_norm": 0.6807965760803734, + "learning_rate": 1.2991672805316534e-05, + "loss": 0.8747, + "step": 6861 + }, + { + "epoch": 0.4212529543571012, + "grad_norm": 0.7046062822542527, + "learning_rate": 1.2989775461477179e-05, + "loss": 0.8354, + "step": 6862 + }, + { + "epoch": 0.4213143435955677, + "grad_norm": 0.7590178494552615, + "learning_rate": 1.2987877999436008e-05, + "loss": 0.9099, + "step": 6863 + }, + { + "epoch": 0.4213757328340342, + "grad_norm": 0.7612468046928221, + "learning_rate": 1.2985980419268045e-05, + "loss": 0.9014, + "step": 6864 + }, + { + "epoch": 0.42143712207250067, + "grad_norm": 0.6793927569951058, + "learning_rate": 1.2984082721048301e-05, + "loss": 0.9114, + "step": 6865 + }, + { + "epoch": 0.42149851131096716, + "grad_norm": 0.7351344510487418, + "learning_rate": 1.298218490485181e-05, + "loss": 0.867, + "step": 6866 + }, + { + "epoch": 0.4215599005494337, + "grad_norm": 0.7234947125627132, + "learning_rate": 1.29802869707536e-05, + "loss": 0.827, + "step": 6867 + }, + { + "epoch": 0.4216212897879002, + "grad_norm": 0.693334456807308, + "learning_rate": 1.2978388918828701e-05, + "loss": 0.8684, + "step": 6868 + }, + { + "epoch": 0.4216826790263667, + "grad_norm": 0.7667915195268563, + "learning_rate": 1.2976490749152166e-05, + "loss": 0.899, + "step": 6869 + }, + { + "epoch": 0.4217440682648332, + "grad_norm": 0.6745306283892206, + "learning_rate": 1.2974592461799026e-05, + "loss": 0.8642, + "step": 6870 + }, + { + "epoch": 0.4218054575032997, + "grad_norm": 0.6954208890525152, + "learning_rate": 1.2972694056844344e-05, + "loss": 0.8907, + "step": 6871 + }, + { + "epoch": 0.42186684674176617, + "grad_norm": 0.717008568119723, + "learning_rate": 1.2970795534363162e-05, + "loss": 0.8765, + "step": 6872 + }, + { + "epoch": 0.42192823598023266, + "grad_norm": 0.7172869760389765, + "learning_rate": 1.2968896894430546e-05, + "loss": 0.8702, + "step": 6873 + }, + { + "epoch": 0.42198962521869915, + "grad_norm": 0.7370301755448446, + "learning_rate": 1.2966998137121553e-05, + "loss": 0.844, + "step": 6874 + }, + { + "epoch": 0.42205101445716564, + "grad_norm": 0.7662669055896454, + "learning_rate": 1.2965099262511256e-05, + "loss": 0.9084, + "step": 6875 + }, + { + "epoch": 0.42211240369563213, + "grad_norm": 0.7837317425840417, + "learning_rate": 1.296320027067473e-05, + "loss": 0.854, + "step": 6876 + }, + { + "epoch": 0.4221737929340987, + "grad_norm": 0.7213068873699019, + "learning_rate": 1.2961301161687045e-05, + "loss": 0.8598, + "step": 6877 + }, + { + "epoch": 0.42223518217256517, + "grad_norm": 0.7891980222895567, + "learning_rate": 1.295940193562329e-05, + "loss": 0.9109, + "step": 6878 + }, + { + "epoch": 0.42229657141103166, + "grad_norm": 0.7664976848441155, + "learning_rate": 1.2957502592558545e-05, + "loss": 0.8745, + "step": 6879 + }, + { + "epoch": 0.42235796064949815, + "grad_norm": 0.7755841986937987, + "learning_rate": 1.2955603132567909e-05, + "loss": 0.8724, + "step": 6880 + }, + { + "epoch": 0.42241934988796465, + "grad_norm": 0.7677003980783549, + "learning_rate": 1.2953703555726471e-05, + "loss": 0.8861, + "step": 6881 + }, + { + "epoch": 0.42248073912643114, + "grad_norm": 0.7050237212716622, + "learning_rate": 1.2951803862109336e-05, + "loss": 0.8583, + "step": 6882 + }, + { + "epoch": 0.42254212836489763, + "grad_norm": 0.7693221781231093, + "learning_rate": 1.2949904051791605e-05, + "loss": 0.8647, + "step": 6883 + }, + { + "epoch": 0.4226035176033641, + "grad_norm": 0.7987259836807022, + "learning_rate": 1.294800412484839e-05, + "loss": 0.916, + "step": 6884 + }, + { + "epoch": 0.4226649068418306, + "grad_norm": 0.7522453502166255, + "learning_rate": 1.2946104081354805e-05, + "loss": 0.9001, + "step": 6885 + }, + { + "epoch": 0.4227262960802971, + "grad_norm": 0.7837991646564572, + "learning_rate": 1.2944203921385969e-05, + "loss": 0.9006, + "step": 6886 + }, + { + "epoch": 0.4227876853187636, + "grad_norm": 0.6956295488792005, + "learning_rate": 1.2942303645017005e-05, + "loss": 0.8641, + "step": 6887 + }, + { + "epoch": 0.42284907455723014, + "grad_norm": 0.7109653423685577, + "learning_rate": 1.294040325232304e-05, + "loss": 0.882, + "step": 6888 + }, + { + "epoch": 0.42291046379569663, + "grad_norm": 0.7296958288842824, + "learning_rate": 1.2938502743379212e-05, + "loss": 0.9017, + "step": 6889 + }, + { + "epoch": 0.4229718530341631, + "grad_norm": 0.7048352147148353, + "learning_rate": 1.2936602118260651e-05, + "loss": 0.8675, + "step": 6890 + }, + { + "epoch": 0.4230332422726296, + "grad_norm": 0.6560434975257012, + "learning_rate": 1.2934701377042503e-05, + "loss": 0.8614, + "step": 6891 + }, + { + "epoch": 0.4230946315110961, + "grad_norm": 0.6950972308864855, + "learning_rate": 1.2932800519799912e-05, + "loss": 0.87, + "step": 6892 + }, + { + "epoch": 0.4231560207495626, + "grad_norm": 0.780228953139597, + "learning_rate": 1.2930899546608034e-05, + "loss": 0.9389, + "step": 6893 + }, + { + "epoch": 0.4232174099880291, + "grad_norm": 0.7186227434803536, + "learning_rate": 1.2928998457542021e-05, + "loss": 0.944, + "step": 6894 + }, + { + "epoch": 0.4232787992264956, + "grad_norm": 0.6561666556269993, + "learning_rate": 1.292709725267703e-05, + "loss": 0.863, + "step": 6895 + }, + { + "epoch": 0.4233401884649621, + "grad_norm": 0.6287271030973868, + "learning_rate": 1.2925195932088234e-05, + "loss": 0.8683, + "step": 6896 + }, + { + "epoch": 0.42340157770342857, + "grad_norm": 0.7596170833182553, + "learning_rate": 1.2923294495850793e-05, + "loss": 0.8681, + "step": 6897 + }, + { + "epoch": 0.42346296694189506, + "grad_norm": 0.662061315931439, + "learning_rate": 1.292139294403989e-05, + "loss": 0.8992, + "step": 6898 + }, + { + "epoch": 0.4235243561803616, + "grad_norm": 0.7206057969251097, + "learning_rate": 1.2919491276730698e-05, + "loss": 0.843, + "step": 6899 + }, + { + "epoch": 0.4235857454188281, + "grad_norm": 0.7211127470337078, + "learning_rate": 1.29175894939984e-05, + "loss": 0.8634, + "step": 6900 + }, + { + "epoch": 0.4236471346572946, + "grad_norm": 0.7268656910059414, + "learning_rate": 1.2915687595918187e-05, + "loss": 0.8892, + "step": 6901 + }, + { + "epoch": 0.4237085238957611, + "grad_norm": 0.7400675925070134, + "learning_rate": 1.2913785582565247e-05, + "loss": 0.9074, + "step": 6902 + }, + { + "epoch": 0.42376991313422757, + "grad_norm": 0.8007397803362816, + "learning_rate": 1.291188345401478e-05, + "loss": 0.8764, + "step": 6903 + }, + { + "epoch": 0.42383130237269406, + "grad_norm": 0.7544159254198469, + "learning_rate": 1.2909981210341984e-05, + "loss": 0.8997, + "step": 6904 + }, + { + "epoch": 0.42389269161116055, + "grad_norm": 0.7517292621150556, + "learning_rate": 1.2908078851622071e-05, + "loss": 0.8827, + "step": 6905 + }, + { + "epoch": 0.42395408084962705, + "grad_norm": 0.7545520769829628, + "learning_rate": 1.2906176377930244e-05, + "loss": 0.8717, + "step": 6906 + }, + { + "epoch": 0.42401547008809354, + "grad_norm": 0.7918023515901449, + "learning_rate": 1.2904273789341722e-05, + "loss": 0.8557, + "step": 6907 + }, + { + "epoch": 0.42407685932656003, + "grad_norm": 0.7506847793391703, + "learning_rate": 1.2902371085931726e-05, + "loss": 0.9205, + "step": 6908 + }, + { + "epoch": 0.4241382485650266, + "grad_norm": 0.7498662583595068, + "learning_rate": 1.2900468267775477e-05, + "loss": 0.8568, + "step": 6909 + }, + { + "epoch": 0.42419963780349307, + "grad_norm": 0.7273628422405594, + "learning_rate": 1.2898565334948203e-05, + "loss": 0.8935, + "step": 6910 + }, + { + "epoch": 0.42426102704195956, + "grad_norm": 0.7369378334246113, + "learning_rate": 1.2896662287525142e-05, + "loss": 0.8482, + "step": 6911 + }, + { + "epoch": 0.42432241628042605, + "grad_norm": 0.7710068257292298, + "learning_rate": 1.2894759125581527e-05, + "loss": 0.9325, + "step": 6912 + }, + { + "epoch": 0.42438380551889254, + "grad_norm": 0.8119867225058961, + "learning_rate": 1.2892855849192602e-05, + "loss": 0.8874, + "step": 6913 + }, + { + "epoch": 0.42444519475735903, + "grad_norm": 0.7933870092347993, + "learning_rate": 1.289095245843361e-05, + "loss": 0.8672, + "step": 6914 + }, + { + "epoch": 0.4245065839958255, + "grad_norm": 0.6900946468690968, + "learning_rate": 1.2889048953379808e-05, + "loss": 0.8665, + "step": 6915 + }, + { + "epoch": 0.424567973234292, + "grad_norm": 0.7129448761007182, + "learning_rate": 1.2887145334106448e-05, + "loss": 0.8861, + "step": 6916 + }, + { + "epoch": 0.4246293624727585, + "grad_norm": 0.714574939156331, + "learning_rate": 1.2885241600688794e-05, + "loss": 0.8874, + "step": 6917 + }, + { + "epoch": 0.424690751711225, + "grad_norm": 0.7273153060231902, + "learning_rate": 1.2883337753202105e-05, + "loss": 0.8509, + "step": 6918 + }, + { + "epoch": 0.4247521409496915, + "grad_norm": 0.7206465870337643, + "learning_rate": 1.2881433791721655e-05, + "loss": 0.9262, + "step": 6919 + }, + { + "epoch": 0.42481353018815804, + "grad_norm": 0.805283075867477, + "learning_rate": 1.2879529716322716e-05, + "loss": 0.8902, + "step": 6920 + }, + { + "epoch": 0.42487491942662453, + "grad_norm": 0.756101233698977, + "learning_rate": 1.2877625527080568e-05, + "loss": 0.9073, + "step": 6921 + }, + { + "epoch": 0.424936308665091, + "grad_norm": 0.6903881405579597, + "learning_rate": 1.287572122407049e-05, + "loss": 0.8267, + "step": 6922 + }, + { + "epoch": 0.4249976979035575, + "grad_norm": 0.7507964158386202, + "learning_rate": 1.2873816807367772e-05, + "loss": 0.8498, + "step": 6923 + }, + { + "epoch": 0.425059087142024, + "grad_norm": 0.7819468127842171, + "learning_rate": 1.2871912277047707e-05, + "loss": 0.9233, + "step": 6924 + }, + { + "epoch": 0.4251204763804905, + "grad_norm": 0.6734711317394033, + "learning_rate": 1.2870007633185588e-05, + "loss": 0.8597, + "step": 6925 + }, + { + "epoch": 0.425181865618957, + "grad_norm": 0.7236795423340407, + "learning_rate": 1.2868102875856718e-05, + "loss": 0.8518, + "step": 6926 + }, + { + "epoch": 0.4252432548574235, + "grad_norm": 0.7538837035216421, + "learning_rate": 1.28661980051364e-05, + "loss": 0.8898, + "step": 6927 + }, + { + "epoch": 0.42530464409588997, + "grad_norm": 0.788672734792815, + "learning_rate": 1.2864293021099949e-05, + "loss": 0.9114, + "step": 6928 + }, + { + "epoch": 0.42536603333435646, + "grad_norm": 0.7412460270703445, + "learning_rate": 1.2862387923822672e-05, + "loss": 0.8149, + "step": 6929 + }, + { + "epoch": 0.425427422572823, + "grad_norm": 0.7522056259403099, + "learning_rate": 1.2860482713379892e-05, + "loss": 0.8945, + "step": 6930 + }, + { + "epoch": 0.4254888118112895, + "grad_norm": 0.6319648168081701, + "learning_rate": 1.2858577389846934e-05, + "loss": 0.8353, + "step": 6931 + }, + { + "epoch": 0.425550201049756, + "grad_norm": 0.6812078679026039, + "learning_rate": 1.2856671953299118e-05, + "loss": 0.8535, + "step": 6932 + }, + { + "epoch": 0.4256115902882225, + "grad_norm": 0.7223004911105851, + "learning_rate": 1.2854766403811787e-05, + "loss": 0.8717, + "step": 6933 + }, + { + "epoch": 0.425672979526689, + "grad_norm": 0.7182643131102647, + "learning_rate": 1.2852860741460268e-05, + "loss": 0.8902, + "step": 6934 + }, + { + "epoch": 0.42573436876515547, + "grad_norm": 0.8071345296130894, + "learning_rate": 1.2850954966319908e-05, + "loss": 0.979, + "step": 6935 + }, + { + "epoch": 0.42579575800362196, + "grad_norm": 0.7136480068474798, + "learning_rate": 1.2849049078466047e-05, + "loss": 0.867, + "step": 6936 + }, + { + "epoch": 0.42585714724208845, + "grad_norm": 0.6838428494039079, + "learning_rate": 1.284714307797404e-05, + "loss": 0.8231, + "step": 6937 + }, + { + "epoch": 0.42591853648055494, + "grad_norm": 0.7133815901632751, + "learning_rate": 1.284523696491924e-05, + "loss": 0.9101, + "step": 6938 + }, + { + "epoch": 0.42597992571902143, + "grad_norm": 0.7481165852872917, + "learning_rate": 1.2843330739377003e-05, + "loss": 0.9284, + "step": 6939 + }, + { + "epoch": 0.4260413149574879, + "grad_norm": 0.7487876007649696, + "learning_rate": 1.28414244014227e-05, + "loss": 0.8752, + "step": 6940 + }, + { + "epoch": 0.4261027041959545, + "grad_norm": 0.7548838498274344, + "learning_rate": 1.2839517951131688e-05, + "loss": 0.9087, + "step": 6941 + }, + { + "epoch": 0.42616409343442097, + "grad_norm": 0.7323870879755603, + "learning_rate": 1.2837611388579345e-05, + "loss": 0.878, + "step": 6942 + }, + { + "epoch": 0.42622548267288746, + "grad_norm": 0.7799916812456139, + "learning_rate": 1.2835704713841049e-05, + "loss": 0.8652, + "step": 6943 + }, + { + "epoch": 0.42628687191135395, + "grad_norm": 0.7205156100765883, + "learning_rate": 1.2833797926992179e-05, + "loss": 0.8596, + "step": 6944 + }, + { + "epoch": 0.42634826114982044, + "grad_norm": 0.7097179830389012, + "learning_rate": 1.2831891028108121e-05, + "loss": 0.8816, + "step": 6945 + }, + { + "epoch": 0.42640965038828693, + "grad_norm": 0.8177000510796292, + "learning_rate": 1.2829984017264263e-05, + "loss": 0.9092, + "step": 6946 + }, + { + "epoch": 0.4264710396267534, + "grad_norm": 0.7706663291571034, + "learning_rate": 1.2828076894536003e-05, + "loss": 0.9236, + "step": 6947 + }, + { + "epoch": 0.4265324288652199, + "grad_norm": 0.7841891500153448, + "learning_rate": 1.2826169659998738e-05, + "loss": 0.9294, + "step": 6948 + }, + { + "epoch": 0.4265938181036864, + "grad_norm": 0.7296372186405177, + "learning_rate": 1.2824262313727869e-05, + "loss": 0.8915, + "step": 6949 + }, + { + "epoch": 0.4266552073421529, + "grad_norm": 0.7343972504024049, + "learning_rate": 1.2822354855798808e-05, + "loss": 0.9176, + "step": 6950 + }, + { + "epoch": 0.42671659658061944, + "grad_norm": 0.7794370966354385, + "learning_rate": 1.2820447286286964e-05, + "loss": 0.8899, + "step": 6951 + }, + { + "epoch": 0.42677798581908594, + "grad_norm": 0.7547838435435891, + "learning_rate": 1.281853960526775e-05, + "loss": 0.8509, + "step": 6952 + }, + { + "epoch": 0.42683937505755243, + "grad_norm": 0.8009915362270446, + "learning_rate": 1.2816631812816594e-05, + "loss": 0.8775, + "step": 6953 + }, + { + "epoch": 0.4269007642960189, + "grad_norm": 0.7635590264666224, + "learning_rate": 1.2814723909008917e-05, + "loss": 0.9082, + "step": 6954 + }, + { + "epoch": 0.4269621535344854, + "grad_norm": 0.7332586759142904, + "learning_rate": 1.2812815893920153e-05, + "loss": 0.8594, + "step": 6955 + }, + { + "epoch": 0.4270235427729519, + "grad_norm": 0.7836626944210632, + "learning_rate": 1.2810907767625728e-05, + "loss": 0.8702, + "step": 6956 + }, + { + "epoch": 0.4270849320114184, + "grad_norm": 0.7999883923647289, + "learning_rate": 1.2808999530201088e-05, + "loss": 0.9554, + "step": 6957 + }, + { + "epoch": 0.4271463212498849, + "grad_norm": 0.7641110787726864, + "learning_rate": 1.2807091181721674e-05, + "loss": 0.8651, + "step": 6958 + }, + { + "epoch": 0.4272077104883514, + "grad_norm": 0.7841103242612526, + "learning_rate": 1.2805182722262927e-05, + "loss": 0.8649, + "step": 6959 + }, + { + "epoch": 0.42726909972681787, + "grad_norm": 0.7519311778616102, + "learning_rate": 1.2803274151900311e-05, + "loss": 0.878, + "step": 6960 + }, + { + "epoch": 0.42733048896528436, + "grad_norm": 0.7651258933156463, + "learning_rate": 1.280136547070927e-05, + "loss": 0.8679, + "step": 6961 + }, + { + "epoch": 0.4273918782037509, + "grad_norm": 0.7550682624766207, + "learning_rate": 1.279945667876527e-05, + "loss": 0.9361, + "step": 6962 + }, + { + "epoch": 0.4274532674422174, + "grad_norm": 0.7094634816580495, + "learning_rate": 1.2797547776143775e-05, + "loss": 0.919, + "step": 6963 + }, + { + "epoch": 0.4275146566806839, + "grad_norm": 0.6923999174037232, + "learning_rate": 1.2795638762920254e-05, + "loss": 0.8496, + "step": 6964 + }, + { + "epoch": 0.4275760459191504, + "grad_norm": 0.6783770267166522, + "learning_rate": 1.2793729639170183e-05, + "loss": 0.8426, + "step": 6965 + }, + { + "epoch": 0.4276374351576169, + "grad_norm": 0.7724970346722843, + "learning_rate": 1.2791820404969034e-05, + "loss": 0.8806, + "step": 6966 + }, + { + "epoch": 0.42769882439608337, + "grad_norm": 0.7043274161677018, + "learning_rate": 1.2789911060392295e-05, + "loss": 0.9134, + "step": 6967 + }, + { + "epoch": 0.42776021363454986, + "grad_norm": 0.7606903700866241, + "learning_rate": 1.2788001605515448e-05, + "loss": 0.9354, + "step": 6968 + }, + { + "epoch": 0.42782160287301635, + "grad_norm": 0.7384869787201493, + "learning_rate": 1.278609204041399e-05, + "loss": 0.8062, + "step": 6969 + }, + { + "epoch": 0.42788299211148284, + "grad_norm": 0.7160895547199292, + "learning_rate": 1.278418236516341e-05, + "loss": 0.8855, + "step": 6970 + }, + { + "epoch": 0.42794438134994933, + "grad_norm": 0.7344821158308048, + "learning_rate": 1.2782272579839207e-05, + "loss": 0.8617, + "step": 6971 + }, + { + "epoch": 0.4280057705884158, + "grad_norm": 0.7237022227642786, + "learning_rate": 1.2780362684516894e-05, + "loss": 0.909, + "step": 6972 + }, + { + "epoch": 0.42806715982688237, + "grad_norm": 0.617448725282354, + "learning_rate": 1.2778452679271972e-05, + "loss": 0.7348, + "step": 6973 + }, + { + "epoch": 0.42812854906534886, + "grad_norm": 0.7783345618015062, + "learning_rate": 1.2776542564179952e-05, + "loss": 0.8844, + "step": 6974 + }, + { + "epoch": 0.42818993830381535, + "grad_norm": 0.7777808373691033, + "learning_rate": 1.277463233931636e-05, + "loss": 0.8851, + "step": 6975 + }, + { + "epoch": 0.42825132754228185, + "grad_norm": 0.7962605829670172, + "learning_rate": 1.2772722004756707e-05, + "loss": 0.8687, + "step": 6976 + }, + { + "epoch": 0.42831271678074834, + "grad_norm": 0.781319331880626, + "learning_rate": 1.2770811560576526e-05, + "loss": 0.8663, + "step": 6977 + }, + { + "epoch": 0.42837410601921483, + "grad_norm": 0.717243233281571, + "learning_rate": 1.2768901006851345e-05, + "loss": 0.8761, + "step": 6978 + }, + { + "epoch": 0.4284354952576813, + "grad_norm": 0.7471328225300604, + "learning_rate": 1.2766990343656695e-05, + "loss": 0.8645, + "step": 6979 + }, + { + "epoch": 0.4284968844961478, + "grad_norm": 0.7925417450058334, + "learning_rate": 1.2765079571068122e-05, + "loss": 0.8912, + "step": 6980 + }, + { + "epoch": 0.4285582737346143, + "grad_norm": 0.7130185417327267, + "learning_rate": 1.2763168689161164e-05, + "loss": 0.869, + "step": 6981 + }, + { + "epoch": 0.4286196629730808, + "grad_norm": 0.7654960123994887, + "learning_rate": 1.2761257698011366e-05, + "loss": 0.8516, + "step": 6982 + }, + { + "epoch": 0.42868105221154734, + "grad_norm": 0.6240852986687184, + "learning_rate": 1.2759346597694287e-05, + "loss": 0.7498, + "step": 6983 + }, + { + "epoch": 0.42874244145001383, + "grad_norm": 0.7643873878665185, + "learning_rate": 1.2757435388285475e-05, + "loss": 0.937, + "step": 6984 + }, + { + "epoch": 0.4288038306884803, + "grad_norm": 0.7776178675373264, + "learning_rate": 1.2755524069860497e-05, + "loss": 0.8703, + "step": 6985 + }, + { + "epoch": 0.4288652199269468, + "grad_norm": 0.8168437341208841, + "learning_rate": 1.2753612642494915e-05, + "loss": 0.9497, + "step": 6986 + }, + { + "epoch": 0.4289266091654133, + "grad_norm": 0.6937160904246051, + "learning_rate": 1.2751701106264298e-05, + "loss": 0.8097, + "step": 6987 + }, + { + "epoch": 0.4289879984038798, + "grad_norm": 0.6783492857204596, + "learning_rate": 1.274978946124422e-05, + "loss": 0.8812, + "step": 6988 + }, + { + "epoch": 0.4290493876423463, + "grad_norm": 0.7340400852771184, + "learning_rate": 1.2747877707510252e-05, + "loss": 0.9228, + "step": 6989 + }, + { + "epoch": 0.4291107768808128, + "grad_norm": 0.772914095078318, + "learning_rate": 1.274596584513799e-05, + "loss": 0.8666, + "step": 6990 + }, + { + "epoch": 0.4291721661192793, + "grad_norm": 0.7938295974776846, + "learning_rate": 1.2744053874203007e-05, + "loss": 0.9118, + "step": 6991 + }, + { + "epoch": 0.42923355535774577, + "grad_norm": 0.6956306870291815, + "learning_rate": 1.27421417947809e-05, + "loss": 0.8306, + "step": 6992 + }, + { + "epoch": 0.42929494459621226, + "grad_norm": 0.7224014244673409, + "learning_rate": 1.2740229606947257e-05, + "loss": 0.8542, + "step": 6993 + }, + { + "epoch": 0.4293563338346788, + "grad_norm": 0.7522014243688924, + "learning_rate": 1.2738317310777685e-05, + "loss": 0.937, + "step": 6994 + }, + { + "epoch": 0.4294177230731453, + "grad_norm": 0.7729404540756021, + "learning_rate": 1.2736404906347786e-05, + "loss": 0.8791, + "step": 6995 + }, + { + "epoch": 0.4294791123116118, + "grad_norm": 0.6755583450372863, + "learning_rate": 1.2734492393733162e-05, + "loss": 0.8366, + "step": 6996 + }, + { + "epoch": 0.4295405015500783, + "grad_norm": 0.7420817130930305, + "learning_rate": 1.2732579773009432e-05, + "loss": 0.8811, + "step": 6997 + }, + { + "epoch": 0.42960189078854477, + "grad_norm": 0.7787246774989737, + "learning_rate": 1.2730667044252208e-05, + "loss": 0.9062, + "step": 6998 + }, + { + "epoch": 0.42966328002701126, + "grad_norm": 0.7725826903458841, + "learning_rate": 1.272875420753711e-05, + "loss": 0.8754, + "step": 6999 + }, + { + "epoch": 0.42972466926547775, + "grad_norm": 0.8414781017954572, + "learning_rate": 1.2726841262939764e-05, + "loss": 0.8788, + "step": 7000 + }, + { + "epoch": 0.42978605850394425, + "grad_norm": 0.7520142848766087, + "learning_rate": 1.2724928210535801e-05, + "loss": 0.8872, + "step": 7001 + }, + { + "epoch": 0.42984744774241074, + "grad_norm": 0.813764944560775, + "learning_rate": 1.2723015050400848e-05, + "loss": 0.9334, + "step": 7002 + }, + { + "epoch": 0.42990883698087723, + "grad_norm": 0.7915290800795369, + "learning_rate": 1.2721101782610547e-05, + "loss": 0.9562, + "step": 7003 + }, + { + "epoch": 0.4299702262193438, + "grad_norm": 0.7024690166205453, + "learning_rate": 1.2719188407240543e-05, + "loss": 0.8933, + "step": 7004 + }, + { + "epoch": 0.43003161545781027, + "grad_norm": 0.7505933415308873, + "learning_rate": 1.2717274924366474e-05, + "loss": 0.863, + "step": 7005 + }, + { + "epoch": 0.43009300469627676, + "grad_norm": 0.6923842971248719, + "learning_rate": 1.2715361334063996e-05, + "loss": 0.847, + "step": 7006 + }, + { + "epoch": 0.43015439393474325, + "grad_norm": 0.7333900848611234, + "learning_rate": 1.271344763640876e-05, + "loss": 0.888, + "step": 7007 + }, + { + "epoch": 0.43021578317320974, + "grad_norm": 0.814771973959688, + "learning_rate": 1.2711533831476429e-05, + "loss": 0.7924, + "step": 7008 + }, + { + "epoch": 0.43027717241167623, + "grad_norm": 0.6865344685527571, + "learning_rate": 1.2709619919342662e-05, + "loss": 0.8983, + "step": 7009 + }, + { + "epoch": 0.4303385616501427, + "grad_norm": 0.7508163391974119, + "learning_rate": 1.2707705900083128e-05, + "loss": 0.8991, + "step": 7010 + }, + { + "epoch": 0.4303999508886092, + "grad_norm": 0.8528209447280927, + "learning_rate": 1.2705791773773494e-05, + "loss": 0.9214, + "step": 7011 + }, + { + "epoch": 0.4304613401270757, + "grad_norm": 0.7949164153493772, + "learning_rate": 1.2703877540489444e-05, + "loss": 0.893, + "step": 7012 + }, + { + "epoch": 0.4305227293655422, + "grad_norm": 0.7242919374390104, + "learning_rate": 1.2701963200306655e-05, + "loss": 0.8957, + "step": 7013 + }, + { + "epoch": 0.4305841186040087, + "grad_norm": 0.7424949244081036, + "learning_rate": 1.2700048753300806e-05, + "loss": 0.9126, + "step": 7014 + }, + { + "epoch": 0.43064550784247524, + "grad_norm": 0.7639924427849835, + "learning_rate": 1.2698134199547592e-05, + "loss": 0.8891, + "step": 7015 + }, + { + "epoch": 0.43070689708094173, + "grad_norm": 0.7725137152256494, + "learning_rate": 1.2696219539122696e-05, + "loss": 0.8794, + "step": 7016 + }, + { + "epoch": 0.4307682863194082, + "grad_norm": 0.7187227088846916, + "learning_rate": 1.2694304772101827e-05, + "loss": 0.8864, + "step": 7017 + }, + { + "epoch": 0.4308296755578747, + "grad_norm": 0.6759679083428459, + "learning_rate": 1.269238989856068e-05, + "loss": 0.8643, + "step": 7018 + }, + { + "epoch": 0.4308910647963412, + "grad_norm": 0.7486547784195171, + "learning_rate": 1.2690474918574958e-05, + "loss": 0.8474, + "step": 7019 + }, + { + "epoch": 0.4309524540348077, + "grad_norm": 0.7656289286699117, + "learning_rate": 1.2688559832220376e-05, + "loss": 0.9081, + "step": 7020 + }, + { + "epoch": 0.4310138432732742, + "grad_norm": 0.6622089617476199, + "learning_rate": 1.268664463957264e-05, + "loss": 0.8352, + "step": 7021 + }, + { + "epoch": 0.4310752325117407, + "grad_norm": 0.7590404209910463, + "learning_rate": 1.2684729340707475e-05, + "loss": 0.8552, + "step": 7022 + }, + { + "epoch": 0.43113662175020717, + "grad_norm": 0.6513481456558023, + "learning_rate": 1.2682813935700599e-05, + "loss": 0.856, + "step": 7023 + }, + { + "epoch": 0.43119801098867366, + "grad_norm": 0.6884288100396017, + "learning_rate": 1.268089842462774e-05, + "loss": 0.8442, + "step": 7024 + }, + { + "epoch": 0.43125940022714015, + "grad_norm": 0.6043235548940971, + "learning_rate": 1.267898280756463e-05, + "loss": 0.8431, + "step": 7025 + }, + { + "epoch": 0.4313207894656067, + "grad_norm": 0.8076664678069215, + "learning_rate": 1.2677067084587e-05, + "loss": 0.9316, + "step": 7026 + }, + { + "epoch": 0.4313821787040732, + "grad_norm": 0.6983269630197686, + "learning_rate": 1.267515125577059e-05, + "loss": 0.9233, + "step": 7027 + }, + { + "epoch": 0.4314435679425397, + "grad_norm": 0.7388426729655373, + "learning_rate": 1.2673235321191141e-05, + "loss": 0.8971, + "step": 7028 + }, + { + "epoch": 0.4315049571810062, + "grad_norm": 0.7724053619805166, + "learning_rate": 1.2671319280924408e-05, + "loss": 0.8415, + "step": 7029 + }, + { + "epoch": 0.43156634641947267, + "grad_norm": 0.74254892375114, + "learning_rate": 1.266940313504613e-05, + "loss": 0.8646, + "step": 7030 + }, + { + "epoch": 0.43162773565793916, + "grad_norm": 0.7278122062191779, + "learning_rate": 1.2667486883632074e-05, + "loss": 0.871, + "step": 7031 + }, + { + "epoch": 0.43168912489640565, + "grad_norm": 0.7181785521466315, + "learning_rate": 1.2665570526757992e-05, + "loss": 0.8785, + "step": 7032 + }, + { + "epoch": 0.43175051413487214, + "grad_norm": 0.7797181412913664, + "learning_rate": 1.2663654064499651e-05, + "loss": 0.8798, + "step": 7033 + }, + { + "epoch": 0.43181190337333863, + "grad_norm": 0.7366403848281455, + "learning_rate": 1.266173749693282e-05, + "loss": 0.851, + "step": 7034 + }, + { + "epoch": 0.4318732926118051, + "grad_norm": 0.7080950181748235, + "learning_rate": 1.2659820824133266e-05, + "loss": 0.8555, + "step": 7035 + }, + { + "epoch": 0.4319346818502717, + "grad_norm": 0.6654237867262723, + "learning_rate": 1.2657904046176774e-05, + "loss": 0.8352, + "step": 7036 + }, + { + "epoch": 0.43199607108873816, + "grad_norm": 0.8286391284626569, + "learning_rate": 1.2655987163139116e-05, + "loss": 0.9058, + "step": 7037 + }, + { + "epoch": 0.43205746032720466, + "grad_norm": 0.71567759622674, + "learning_rate": 1.265407017509608e-05, + "loss": 0.8585, + "step": 7038 + }, + { + "epoch": 0.43211884956567115, + "grad_norm": 0.7504411842834302, + "learning_rate": 1.2652153082123458e-05, + "loss": 0.8512, + "step": 7039 + }, + { + "epoch": 0.43218023880413764, + "grad_norm": 0.7135827652957929, + "learning_rate": 1.2650235884297039e-05, + "loss": 0.9183, + "step": 7040 + }, + { + "epoch": 0.43224162804260413, + "grad_norm": 0.7057405260422122, + "learning_rate": 1.264831858169262e-05, + "loss": 0.9043, + "step": 7041 + }, + { + "epoch": 0.4323030172810706, + "grad_norm": 0.7773601371288775, + "learning_rate": 1.2646401174386002e-05, + "loss": 0.8941, + "step": 7042 + }, + { + "epoch": 0.4323644065195371, + "grad_norm": 0.7557613073344289, + "learning_rate": 1.2644483662452993e-05, + "loss": 0.8623, + "step": 7043 + }, + { + "epoch": 0.4324257957580036, + "grad_norm": 0.721650556292204, + "learning_rate": 1.2642566045969402e-05, + "loss": 0.8777, + "step": 7044 + }, + { + "epoch": 0.4324871849964701, + "grad_norm": 0.7622624277052922, + "learning_rate": 1.2640648325011042e-05, + "loss": 0.935, + "step": 7045 + }, + { + "epoch": 0.4325485742349366, + "grad_norm": 0.7811072825687659, + "learning_rate": 1.2638730499653731e-05, + "loss": 0.9322, + "step": 7046 + }, + { + "epoch": 0.43260996347340314, + "grad_norm": 0.7043856172142853, + "learning_rate": 1.2636812569973288e-05, + "loss": 0.8388, + "step": 7047 + }, + { + "epoch": 0.43267135271186963, + "grad_norm": 0.6643955256454636, + "learning_rate": 1.2634894536045543e-05, + "loss": 0.8501, + "step": 7048 + }, + { + "epoch": 0.4327327419503361, + "grad_norm": 0.7292327798103845, + "learning_rate": 1.2632976397946325e-05, + "loss": 0.9149, + "step": 7049 + }, + { + "epoch": 0.4327941311888026, + "grad_norm": 0.7142886001930181, + "learning_rate": 1.2631058155751465e-05, + "loss": 0.8625, + "step": 7050 + }, + { + "epoch": 0.4328555204272691, + "grad_norm": 0.7601743108302872, + "learning_rate": 1.2629139809536809e-05, + "loss": 0.8876, + "step": 7051 + }, + { + "epoch": 0.4329169096657356, + "grad_norm": 0.7563692703682953, + "learning_rate": 1.2627221359378193e-05, + "loss": 0.8834, + "step": 7052 + }, + { + "epoch": 0.4329782989042021, + "grad_norm": 0.751150099288631, + "learning_rate": 1.262530280535146e-05, + "loss": 0.8579, + "step": 7053 + }, + { + "epoch": 0.4330396881426686, + "grad_norm": 0.7676733660586631, + "learning_rate": 1.2623384147532473e-05, + "loss": 0.8665, + "step": 7054 + }, + { + "epoch": 0.43310107738113507, + "grad_norm": 0.7661225841149719, + "learning_rate": 1.2621465385997077e-05, + "loss": 0.9112, + "step": 7055 + }, + { + "epoch": 0.43316246661960156, + "grad_norm": 0.7149488316548618, + "learning_rate": 1.2619546520821133e-05, + "loss": 0.899, + "step": 7056 + }, + { + "epoch": 0.4332238558580681, + "grad_norm": 0.7993074245457422, + "learning_rate": 1.2617627552080506e-05, + "loss": 0.921, + "step": 7057 + }, + { + "epoch": 0.4332852450965346, + "grad_norm": 0.689196244359375, + "learning_rate": 1.2615708479851062e-05, + "loss": 0.8439, + "step": 7058 + }, + { + "epoch": 0.4333466343350011, + "grad_norm": 0.7894244167760037, + "learning_rate": 1.2613789304208672e-05, + "loss": 0.8644, + "step": 7059 + }, + { + "epoch": 0.4334080235734676, + "grad_norm": 0.7560466648458651, + "learning_rate": 1.261187002522921e-05, + "loss": 0.8823, + "step": 7060 + }, + { + "epoch": 0.4334694128119341, + "grad_norm": 0.7008735924810273, + "learning_rate": 1.2609950642988558e-05, + "loss": 0.8318, + "step": 7061 + }, + { + "epoch": 0.43353080205040057, + "grad_norm": 0.7434764424239898, + "learning_rate": 1.2608031157562594e-05, + "loss": 0.8461, + "step": 7062 + }, + { + "epoch": 0.43359219128886706, + "grad_norm": 0.744888103579301, + "learning_rate": 1.2606111569027215e-05, + "loss": 0.8845, + "step": 7063 + }, + { + "epoch": 0.43365358052733355, + "grad_norm": 0.596401577284888, + "learning_rate": 1.2604191877458307e-05, + "loss": 0.7944, + "step": 7064 + }, + { + "epoch": 0.43371496976580004, + "grad_norm": 0.6460495810917938, + "learning_rate": 1.2602272082931764e-05, + "loss": 0.8405, + "step": 7065 + }, + { + "epoch": 0.43377635900426653, + "grad_norm": 0.7083104267137342, + "learning_rate": 1.2600352185523488e-05, + "loss": 0.8315, + "step": 7066 + }, + { + "epoch": 0.433837748242733, + "grad_norm": 0.8238598720687513, + "learning_rate": 1.259843218530938e-05, + "loss": 0.8835, + "step": 7067 + }, + { + "epoch": 0.43389913748119957, + "grad_norm": 0.735579747229532, + "learning_rate": 1.2596512082365355e-05, + "loss": 0.9043, + "step": 7068 + }, + { + "epoch": 0.43396052671966606, + "grad_norm": 0.7106428560649191, + "learning_rate": 1.2594591876767317e-05, + "loss": 0.8653, + "step": 7069 + }, + { + "epoch": 0.43402191595813255, + "grad_norm": 0.69708364727953, + "learning_rate": 1.2592671568591186e-05, + "loss": 0.8588, + "step": 7070 + }, + { + "epoch": 0.43408330519659905, + "grad_norm": 0.7502894147932939, + "learning_rate": 1.259075115791288e-05, + "loss": 0.9214, + "step": 7071 + }, + { + "epoch": 0.43414469443506554, + "grad_norm": 0.8131626472177729, + "learning_rate": 1.2588830644808328e-05, + "loss": 0.8797, + "step": 7072 + }, + { + "epoch": 0.43420608367353203, + "grad_norm": 0.7433024325118234, + "learning_rate": 1.2586910029353451e-05, + "loss": 0.869, + "step": 7073 + }, + { + "epoch": 0.4342674729119985, + "grad_norm": 0.7413039238253887, + "learning_rate": 1.2584989311624186e-05, + "loss": 0.8879, + "step": 7074 + }, + { + "epoch": 0.434328862150465, + "grad_norm": 0.6883465685150817, + "learning_rate": 1.2583068491696467e-05, + "loss": 0.8423, + "step": 7075 + }, + { + "epoch": 0.4343902513889315, + "grad_norm": 0.6907636825566899, + "learning_rate": 1.2581147569646238e-05, + "loss": 0.8948, + "step": 7076 + }, + { + "epoch": 0.434451640627398, + "grad_norm": 0.751909895863401, + "learning_rate": 1.257922654554944e-05, + "loss": 0.897, + "step": 7077 + }, + { + "epoch": 0.4345130298658645, + "grad_norm": 0.7241080510755477, + "learning_rate": 1.257730541948202e-05, + "loss": 0.9094, + "step": 7078 + }, + { + "epoch": 0.43457441910433103, + "grad_norm": 0.7292833492423187, + "learning_rate": 1.2575384191519932e-05, + "loss": 0.8626, + "step": 7079 + }, + { + "epoch": 0.4346358083427975, + "grad_norm": 0.6606395541618684, + "learning_rate": 1.2573462861739133e-05, + "loss": 0.9126, + "step": 7080 + }, + { + "epoch": 0.434697197581264, + "grad_norm": 0.6671188687657598, + "learning_rate": 1.2571541430215586e-05, + "loss": 0.8547, + "step": 7081 + }, + { + "epoch": 0.4347585868197305, + "grad_norm": 0.7265290631866569, + "learning_rate": 1.2569619897025251e-05, + "loss": 0.8798, + "step": 7082 + }, + { + "epoch": 0.434819976058197, + "grad_norm": 0.760862796284897, + "learning_rate": 1.2567698262244099e-05, + "loss": 0.9138, + "step": 7083 + }, + { + "epoch": 0.4348813652966635, + "grad_norm": 0.823856267446226, + "learning_rate": 1.2565776525948102e-05, + "loss": 0.8893, + "step": 7084 + }, + { + "epoch": 0.43494275453513, + "grad_norm": 0.7430359933487332, + "learning_rate": 1.256385468821323e-05, + "loss": 0.8868, + "step": 7085 + }, + { + "epoch": 0.4350041437735965, + "grad_norm": 0.8537206948118895, + "learning_rate": 1.256193274911548e-05, + "loss": 0.9013, + "step": 7086 + }, + { + "epoch": 0.43506553301206297, + "grad_norm": 0.799373527853148, + "learning_rate": 1.256001070873082e-05, + "loss": 0.8526, + "step": 7087 + }, + { + "epoch": 0.43512692225052946, + "grad_norm": 0.7928219879718162, + "learning_rate": 1.2558088567135245e-05, + "loss": 0.8692, + "step": 7088 + }, + { + "epoch": 0.435188311488996, + "grad_norm": 0.6663563532122118, + "learning_rate": 1.2556166324404747e-05, + "loss": 0.8598, + "step": 7089 + }, + { + "epoch": 0.4352497007274625, + "grad_norm": 0.7446184993574544, + "learning_rate": 1.2554243980615325e-05, + "loss": 0.8764, + "step": 7090 + }, + { + "epoch": 0.435311089965929, + "grad_norm": 0.8105528877398489, + "learning_rate": 1.2552321535842977e-05, + "loss": 0.8726, + "step": 7091 + }, + { + "epoch": 0.4353724792043955, + "grad_norm": 0.6948242673716675, + "learning_rate": 1.2550398990163706e-05, + "loss": 0.9181, + "step": 7092 + }, + { + "epoch": 0.43543386844286197, + "grad_norm": 0.7482026265478466, + "learning_rate": 1.2548476343653526e-05, + "loss": 0.8621, + "step": 7093 + }, + { + "epoch": 0.43549525768132846, + "grad_norm": 0.7327176427290756, + "learning_rate": 1.2546553596388442e-05, + "loss": 0.8742, + "step": 7094 + }, + { + "epoch": 0.43555664691979495, + "grad_norm": 0.7532406663374968, + "learning_rate": 1.2544630748444477e-05, + "loss": 0.8665, + "step": 7095 + }, + { + "epoch": 0.43561803615826145, + "grad_norm": 0.7066448722236255, + "learning_rate": 1.254270779989765e-05, + "loss": 0.8747, + "step": 7096 + }, + { + "epoch": 0.43567942539672794, + "grad_norm": 0.7321481188569058, + "learning_rate": 1.254078475082398e-05, + "loss": 0.8529, + "step": 7097 + }, + { + "epoch": 0.43574081463519443, + "grad_norm": 0.7823522345790692, + "learning_rate": 1.2538861601299504e-05, + "loss": 0.8463, + "step": 7098 + }, + { + "epoch": 0.4358022038736609, + "grad_norm": 0.8042768174425668, + "learning_rate": 1.2536938351400245e-05, + "loss": 0.8473, + "step": 7099 + }, + { + "epoch": 0.43586359311212747, + "grad_norm": 0.7010012187658159, + "learning_rate": 1.253501500120225e-05, + "loss": 0.8443, + "step": 7100 + }, + { + "epoch": 0.43592498235059396, + "grad_norm": 0.6946798435540271, + "learning_rate": 1.2533091550781552e-05, + "loss": 0.8422, + "step": 7101 + }, + { + "epoch": 0.43598637158906045, + "grad_norm": 0.7231391180765371, + "learning_rate": 1.2531168000214196e-05, + "loss": 0.8642, + "step": 7102 + }, + { + "epoch": 0.43604776082752694, + "grad_norm": 0.706626301110484, + "learning_rate": 1.252924434957623e-05, + "loss": 0.8311, + "step": 7103 + }, + { + "epoch": 0.43610915006599343, + "grad_norm": 0.7680234005439023, + "learning_rate": 1.2527320598943711e-05, + "loss": 0.9065, + "step": 7104 + }, + { + "epoch": 0.4361705393044599, + "grad_norm": 0.7728836238022415, + "learning_rate": 1.252539674839269e-05, + "loss": 0.9185, + "step": 7105 + }, + { + "epoch": 0.4362319285429264, + "grad_norm": 0.7814875461008807, + "learning_rate": 1.2523472797999228e-05, + "loss": 0.885, + "step": 7106 + }, + { + "epoch": 0.4362933177813929, + "grad_norm": 0.762702345028829, + "learning_rate": 1.2521548747839389e-05, + "loss": 0.9076, + "step": 7107 + }, + { + "epoch": 0.4363547070198594, + "grad_norm": 0.7697502398329993, + "learning_rate": 1.2519624597989244e-05, + "loss": 0.887, + "step": 7108 + }, + { + "epoch": 0.4364160962583259, + "grad_norm": 0.7620930441477574, + "learning_rate": 1.2517700348524864e-05, + "loss": 0.8476, + "step": 7109 + }, + { + "epoch": 0.43647748549679244, + "grad_norm": 0.7424078636182292, + "learning_rate": 1.2515775999522322e-05, + "loss": 0.8733, + "step": 7110 + }, + { + "epoch": 0.43653887473525893, + "grad_norm": 0.7806408280165005, + "learning_rate": 1.2513851551057699e-05, + "loss": 0.9258, + "step": 7111 + }, + { + "epoch": 0.4366002639737254, + "grad_norm": 0.8372638302638252, + "learning_rate": 1.2511927003207077e-05, + "loss": 0.9477, + "step": 7112 + }, + { + "epoch": 0.4366616532121919, + "grad_norm": 0.7017332035542189, + "learning_rate": 1.251000235604655e-05, + "loss": 0.8709, + "step": 7113 + }, + { + "epoch": 0.4367230424506584, + "grad_norm": 0.669626831434765, + "learning_rate": 1.2508077609652203e-05, + "loss": 0.8688, + "step": 7114 + }, + { + "epoch": 0.4367844316891249, + "grad_norm": 0.7058551102545461, + "learning_rate": 1.2506152764100135e-05, + "loss": 0.8641, + "step": 7115 + }, + { + "epoch": 0.4368458209275914, + "grad_norm": 0.7655945683640483, + "learning_rate": 1.2504227819466443e-05, + "loss": 0.8903, + "step": 7116 + }, + { + "epoch": 0.4369072101660579, + "grad_norm": 0.6980046631030729, + "learning_rate": 1.250230277582723e-05, + "loss": 0.8949, + "step": 7117 + }, + { + "epoch": 0.43696859940452437, + "grad_norm": 0.6809341787201874, + "learning_rate": 1.2500377633258611e-05, + "loss": 0.8288, + "step": 7118 + }, + { + "epoch": 0.43702998864299086, + "grad_norm": 0.6433846567227434, + "learning_rate": 1.2498452391836687e-05, + "loss": 0.8193, + "step": 7119 + }, + { + "epoch": 0.43709137788145735, + "grad_norm": 0.5942326209685385, + "learning_rate": 1.2496527051637577e-05, + "loss": 0.6878, + "step": 7120 + }, + { + "epoch": 0.4371527671199239, + "grad_norm": 0.7784615034630232, + "learning_rate": 1.2494601612737403e-05, + "loss": 0.8739, + "step": 7121 + }, + { + "epoch": 0.4372141563583904, + "grad_norm": 0.8072965598725953, + "learning_rate": 1.2492676075212283e-05, + "loss": 0.9182, + "step": 7122 + }, + { + "epoch": 0.4372755455968569, + "grad_norm": 0.7331918011487564, + "learning_rate": 1.2490750439138349e-05, + "loss": 0.8961, + "step": 7123 + }, + { + "epoch": 0.4373369348353234, + "grad_norm": 0.7029922976889681, + "learning_rate": 1.2488824704591722e-05, + "loss": 0.9159, + "step": 7124 + }, + { + "epoch": 0.43739832407378987, + "grad_norm": 0.754968960900464, + "learning_rate": 1.2486898871648552e-05, + "loss": 0.8691, + "step": 7125 + }, + { + "epoch": 0.43745971331225636, + "grad_norm": 0.6743907383248375, + "learning_rate": 1.248497294038496e-05, + "loss": 0.8798, + "step": 7126 + }, + { + "epoch": 0.43752110255072285, + "grad_norm": 0.7377291568503432, + "learning_rate": 1.2483046910877103e-05, + "loss": 0.8849, + "step": 7127 + }, + { + "epoch": 0.43758249178918934, + "grad_norm": 0.7202967124293125, + "learning_rate": 1.248112078320112e-05, + "loss": 0.8735, + "step": 7128 + }, + { + "epoch": 0.43764388102765583, + "grad_norm": 0.7210468445215449, + "learning_rate": 1.2479194557433163e-05, + "loss": 0.8484, + "step": 7129 + }, + { + "epoch": 0.4377052702661223, + "grad_norm": 0.6777811958882898, + "learning_rate": 1.2477268233649384e-05, + "loss": 0.8549, + "step": 7130 + }, + { + "epoch": 0.4377666595045889, + "grad_norm": 0.8027714984072168, + "learning_rate": 1.247534181192594e-05, + "loss": 0.8874, + "step": 7131 + }, + { + "epoch": 0.43782804874305536, + "grad_norm": 0.727122421090166, + "learning_rate": 1.2473415292339001e-05, + "loss": 0.878, + "step": 7132 + }, + { + "epoch": 0.43788943798152186, + "grad_norm": 0.832825286071436, + "learning_rate": 1.2471488674964722e-05, + "loss": 0.9063, + "step": 7133 + }, + { + "epoch": 0.43795082721998835, + "grad_norm": 0.7267698050380212, + "learning_rate": 1.2469561959879281e-05, + "loss": 0.8965, + "step": 7134 + }, + { + "epoch": 0.43801221645845484, + "grad_norm": 0.7753642641610713, + "learning_rate": 1.2467635147158845e-05, + "loss": 0.8837, + "step": 7135 + }, + { + "epoch": 0.43807360569692133, + "grad_norm": 0.7450903596816867, + "learning_rate": 1.2465708236879594e-05, + "loss": 0.8616, + "step": 7136 + }, + { + "epoch": 0.4381349949353878, + "grad_norm": 0.7287592460624347, + "learning_rate": 1.246378122911771e-05, + "loss": 0.8344, + "step": 7137 + }, + { + "epoch": 0.4381963841738543, + "grad_norm": 0.7351331506014034, + "learning_rate": 1.2461854123949375e-05, + "loss": 0.8981, + "step": 7138 + }, + { + "epoch": 0.4382577734123208, + "grad_norm": 0.7255724776780086, + "learning_rate": 1.245992692145078e-05, + "loss": 0.8547, + "step": 7139 + }, + { + "epoch": 0.4383191626507873, + "grad_norm": 0.7910951534075246, + "learning_rate": 1.245799962169812e-05, + "loss": 0.8827, + "step": 7140 + }, + { + "epoch": 0.4383805518892538, + "grad_norm": 0.6931980594977897, + "learning_rate": 1.2456072224767586e-05, + "loss": 0.8142, + "step": 7141 + }, + { + "epoch": 0.43844194112772034, + "grad_norm": 0.8612058312483086, + "learning_rate": 1.2454144730735383e-05, + "loss": 0.9072, + "step": 7142 + }, + { + "epoch": 0.4385033303661868, + "grad_norm": 0.8067747474477329, + "learning_rate": 1.245221713967771e-05, + "loss": 0.8875, + "step": 7143 + }, + { + "epoch": 0.4385647196046533, + "grad_norm": 0.6826291264139298, + "learning_rate": 1.2450289451670778e-05, + "loss": 0.8488, + "step": 7144 + }, + { + "epoch": 0.4386261088431198, + "grad_norm": 0.6321151275124007, + "learning_rate": 1.2448361666790803e-05, + "loss": 0.7561, + "step": 7145 + }, + { + "epoch": 0.4386874980815863, + "grad_norm": 0.75626495750955, + "learning_rate": 1.2446433785113994e-05, + "loss": 0.892, + "step": 7146 + }, + { + "epoch": 0.4387488873200528, + "grad_norm": 0.8688004445488469, + "learning_rate": 1.2444505806716572e-05, + "loss": 0.9752, + "step": 7147 + }, + { + "epoch": 0.4388102765585193, + "grad_norm": 0.6813723993014315, + "learning_rate": 1.2442577731674763e-05, + "loss": 0.8543, + "step": 7148 + }, + { + "epoch": 0.4388716657969858, + "grad_norm": 0.7695556036734797, + "learning_rate": 1.244064956006479e-05, + "loss": 0.8963, + "step": 7149 + }, + { + "epoch": 0.43893305503545227, + "grad_norm": 0.7809455745016682, + "learning_rate": 1.2438721291962891e-05, + "loss": 0.9056, + "step": 7150 + }, + { + "epoch": 0.43899444427391876, + "grad_norm": 0.785090175787295, + "learning_rate": 1.243679292744529e-05, + "loss": 0.9592, + "step": 7151 + }, + { + "epoch": 0.43905583351238525, + "grad_norm": 0.7681560117142373, + "learning_rate": 1.2434864466588236e-05, + "loss": 0.885, + "step": 7152 + }, + { + "epoch": 0.4391172227508518, + "grad_norm": 0.7403584776620048, + "learning_rate": 1.2432935909467968e-05, + "loss": 0.866, + "step": 7153 + }, + { + "epoch": 0.4391786119893183, + "grad_norm": 0.587864219472523, + "learning_rate": 1.2431007256160728e-05, + "loss": 0.7117, + "step": 7154 + }, + { + "epoch": 0.4392400012277848, + "grad_norm": 0.7502974362661877, + "learning_rate": 1.2429078506742774e-05, + "loss": 0.923, + "step": 7155 + }, + { + "epoch": 0.4393013904662513, + "grad_norm": 0.7360889073138663, + "learning_rate": 1.2427149661290347e-05, + "loss": 0.8657, + "step": 7156 + }, + { + "epoch": 0.43936277970471777, + "grad_norm": 0.8302419694032771, + "learning_rate": 1.2425220719879721e-05, + "loss": 0.9028, + "step": 7157 + }, + { + "epoch": 0.43942416894318426, + "grad_norm": 0.8285419222628422, + "learning_rate": 1.2423291682587144e-05, + "loss": 0.8866, + "step": 7158 + }, + { + "epoch": 0.43948555818165075, + "grad_norm": 0.7844012295468583, + "learning_rate": 1.2421362549488886e-05, + "loss": 0.8592, + "step": 7159 + }, + { + "epoch": 0.43954694742011724, + "grad_norm": 0.7956984998105747, + "learning_rate": 1.2419433320661219e-05, + "loss": 0.8664, + "step": 7160 + }, + { + "epoch": 0.43960833665858373, + "grad_norm": 0.7123017092040306, + "learning_rate": 1.2417503996180408e-05, + "loss": 0.883, + "step": 7161 + }, + { + "epoch": 0.4396697258970502, + "grad_norm": 0.7329748717127945, + "learning_rate": 1.2415574576122741e-05, + "loss": 0.8598, + "step": 7162 + }, + { + "epoch": 0.43973111513551677, + "grad_norm": 0.6498649334804207, + "learning_rate": 1.2413645060564486e-05, + "loss": 0.8329, + "step": 7163 + }, + { + "epoch": 0.43979250437398326, + "grad_norm": 0.7205012223479846, + "learning_rate": 1.2411715449581938e-05, + "loss": 0.8621, + "step": 7164 + }, + { + "epoch": 0.43985389361244975, + "grad_norm": 0.7929419771191936, + "learning_rate": 1.2409785743251375e-05, + "loss": 0.8767, + "step": 7165 + }, + { + "epoch": 0.43991528285091624, + "grad_norm": 0.648762232603684, + "learning_rate": 1.2407855941649094e-05, + "loss": 0.8552, + "step": 7166 + }, + { + "epoch": 0.43997667208938274, + "grad_norm": 0.7077741284884224, + "learning_rate": 1.240592604485139e-05, + "loss": 0.851, + "step": 7167 + }, + { + "epoch": 0.44003806132784923, + "grad_norm": 0.7537260617963666, + "learning_rate": 1.2403996052934561e-05, + "loss": 0.8341, + "step": 7168 + }, + { + "epoch": 0.4400994505663157, + "grad_norm": 0.7467360983461735, + "learning_rate": 1.2402065965974912e-05, + "loss": 0.8268, + "step": 7169 + }, + { + "epoch": 0.4401608398047822, + "grad_norm": 0.8135294741636848, + "learning_rate": 1.2400135784048745e-05, + "loss": 0.8889, + "step": 7170 + }, + { + "epoch": 0.4402222290432487, + "grad_norm": 0.7024659104471609, + "learning_rate": 1.2398205507232377e-05, + "loss": 0.8317, + "step": 7171 + }, + { + "epoch": 0.4402836182817152, + "grad_norm": 0.6957414305679327, + "learning_rate": 1.2396275135602118e-05, + "loss": 0.9114, + "step": 7172 + }, + { + "epoch": 0.4403450075201817, + "grad_norm": 0.7658682444563928, + "learning_rate": 1.2394344669234285e-05, + "loss": 0.8902, + "step": 7173 + }, + { + "epoch": 0.44040639675864823, + "grad_norm": 0.7383497323837578, + "learning_rate": 1.2392414108205205e-05, + "loss": 0.8824, + "step": 7174 + }, + { + "epoch": 0.4404677859971147, + "grad_norm": 0.8363422492028175, + "learning_rate": 1.2390483452591198e-05, + "loss": 0.9084, + "step": 7175 + }, + { + "epoch": 0.4405291752355812, + "grad_norm": 0.7018195741161494, + "learning_rate": 1.2388552702468593e-05, + "loss": 0.8356, + "step": 7176 + }, + { + "epoch": 0.4405905644740477, + "grad_norm": 0.6989461963844914, + "learning_rate": 1.2386621857913726e-05, + "loss": 0.8497, + "step": 7177 + }, + { + "epoch": 0.4406519537125142, + "grad_norm": 0.7810820755279798, + "learning_rate": 1.2384690919002932e-05, + "loss": 0.8578, + "step": 7178 + }, + { + "epoch": 0.4407133429509807, + "grad_norm": 0.7452866376742006, + "learning_rate": 1.2382759885812554e-05, + "loss": 0.9079, + "step": 7179 + }, + { + "epoch": 0.4407747321894472, + "grad_norm": 0.72446862072953, + "learning_rate": 1.2380828758418932e-05, + "loss": 0.888, + "step": 7180 + }, + { + "epoch": 0.4408361214279137, + "grad_norm": 0.7814835581516577, + "learning_rate": 1.2378897536898413e-05, + "loss": 0.8391, + "step": 7181 + }, + { + "epoch": 0.44089751066638017, + "grad_norm": 0.7112945554893757, + "learning_rate": 1.2376966221327358e-05, + "loss": 0.8838, + "step": 7182 + }, + { + "epoch": 0.44095889990484666, + "grad_norm": 0.7286917875505694, + "learning_rate": 1.237503481178211e-05, + "loss": 0.9136, + "step": 7183 + }, + { + "epoch": 0.4410202891433132, + "grad_norm": 0.5876600743043724, + "learning_rate": 1.2373103308339034e-05, + "loss": 0.6587, + "step": 7184 + }, + { + "epoch": 0.4410816783817797, + "grad_norm": 0.6667535364982818, + "learning_rate": 1.2371171711074493e-05, + "loss": 0.8245, + "step": 7185 + }, + { + "epoch": 0.4411430676202462, + "grad_norm": 0.7756440083802867, + "learning_rate": 1.236924002006485e-05, + "loss": 0.8481, + "step": 7186 + }, + { + "epoch": 0.4412044568587127, + "grad_norm": 0.7883743240639698, + "learning_rate": 1.2367308235386481e-05, + "loss": 0.885, + "step": 7187 + }, + { + "epoch": 0.44126584609717917, + "grad_norm": 0.7295652274077656, + "learning_rate": 1.2365376357115755e-05, + "loss": 0.877, + "step": 7188 + }, + { + "epoch": 0.44132723533564566, + "grad_norm": 0.7129717717914477, + "learning_rate": 1.2363444385329052e-05, + "loss": 0.8554, + "step": 7189 + }, + { + "epoch": 0.44138862457411215, + "grad_norm": 0.7702469415660076, + "learning_rate": 1.236151232010275e-05, + "loss": 0.9182, + "step": 7190 + }, + { + "epoch": 0.44145001381257865, + "grad_norm": 0.7011781070563985, + "learning_rate": 1.2359580161513233e-05, + "loss": 0.8901, + "step": 7191 + }, + { + "epoch": 0.44151140305104514, + "grad_norm": 0.6949155761188086, + "learning_rate": 1.2357647909636897e-05, + "loss": 0.8601, + "step": 7192 + }, + { + "epoch": 0.44157279228951163, + "grad_norm": 0.7260651090555179, + "learning_rate": 1.2355715564550126e-05, + "loss": 0.8755, + "step": 7193 + }, + { + "epoch": 0.4416341815279781, + "grad_norm": 0.7151041552763693, + "learning_rate": 1.2353783126329323e-05, + "loss": 0.8187, + "step": 7194 + }, + { + "epoch": 0.44169557076644467, + "grad_norm": 0.7008914946687914, + "learning_rate": 1.235185059505088e-05, + "loss": 0.8411, + "step": 7195 + }, + { + "epoch": 0.44175696000491116, + "grad_norm": 0.7835140341309524, + "learning_rate": 1.234991797079121e-05, + "loss": 0.9178, + "step": 7196 + }, + { + "epoch": 0.44181834924337765, + "grad_norm": 0.7624475783633716, + "learning_rate": 1.234798525362671e-05, + "loss": 0.8419, + "step": 7197 + }, + { + "epoch": 0.44187973848184414, + "grad_norm": 0.7000217061401589, + "learning_rate": 1.2346052443633796e-05, + "loss": 0.845, + "step": 7198 + }, + { + "epoch": 0.44194112772031063, + "grad_norm": 0.8688353846855391, + "learning_rate": 1.2344119540888882e-05, + "loss": 0.9826, + "step": 7199 + }, + { + "epoch": 0.4420025169587771, + "grad_norm": 0.8369825114552648, + "learning_rate": 1.2342186545468381e-05, + "loss": 0.9432, + "step": 7200 + }, + { + "epoch": 0.4420639061972436, + "grad_norm": 0.7459473644124043, + "learning_rate": 1.2340253457448728e-05, + "loss": 0.8692, + "step": 7201 + }, + { + "epoch": 0.4421252954357101, + "grad_norm": 0.6878720035103274, + "learning_rate": 1.233832027690633e-05, + "loss": 0.9429, + "step": 7202 + }, + { + "epoch": 0.4421866846741766, + "grad_norm": 0.6953420066516424, + "learning_rate": 1.233638700391763e-05, + "loss": 0.8184, + "step": 7203 + }, + { + "epoch": 0.4422480739126431, + "grad_norm": 0.7734483062083244, + "learning_rate": 1.2334453638559057e-05, + "loss": 0.8382, + "step": 7204 + }, + { + "epoch": 0.4423094631511096, + "grad_norm": 0.7471582942536507, + "learning_rate": 1.2332520180907044e-05, + "loss": 0.8886, + "step": 7205 + }, + { + "epoch": 0.44237085238957613, + "grad_norm": 0.7706808139393146, + "learning_rate": 1.2330586631038033e-05, + "loss": 0.8561, + "step": 7206 + }, + { + "epoch": 0.4424322416280426, + "grad_norm": 0.7115748400009173, + "learning_rate": 1.232865298902847e-05, + "loss": 0.8764, + "step": 7207 + }, + { + "epoch": 0.4424936308665091, + "grad_norm": 0.69917955636151, + "learning_rate": 1.2326719254954793e-05, + "loss": 0.8799, + "step": 7208 + }, + { + "epoch": 0.4425550201049756, + "grad_norm": 0.7785611349338688, + "learning_rate": 1.2324785428893464e-05, + "loss": 0.9193, + "step": 7209 + }, + { + "epoch": 0.4426164093434421, + "grad_norm": 0.7574946258906834, + "learning_rate": 1.2322851510920934e-05, + "loss": 0.8647, + "step": 7210 + }, + { + "epoch": 0.4426777985819086, + "grad_norm": 0.7245980991250848, + "learning_rate": 1.232091750111366e-05, + "loss": 0.898, + "step": 7211 + }, + { + "epoch": 0.4427391878203751, + "grad_norm": 0.6885801763167982, + "learning_rate": 1.2318983399548106e-05, + "loss": 0.8236, + "step": 7212 + }, + { + "epoch": 0.44280057705884157, + "grad_norm": 0.7614063500150293, + "learning_rate": 1.231704920630073e-05, + "loss": 0.8849, + "step": 7213 + }, + { + "epoch": 0.44286196629730806, + "grad_norm": 0.7694256774740758, + "learning_rate": 1.2315114921448012e-05, + "loss": 0.92, + "step": 7214 + }, + { + "epoch": 0.44292335553577455, + "grad_norm": 0.7459065875558415, + "learning_rate": 1.2313180545066416e-05, + "loss": 0.8583, + "step": 7215 + }, + { + "epoch": 0.4429847447742411, + "grad_norm": 0.8376907967203352, + "learning_rate": 1.2311246077232424e-05, + "loss": 0.8876, + "step": 7216 + }, + { + "epoch": 0.4430461340127076, + "grad_norm": 0.8014412375617596, + "learning_rate": 1.230931151802251e-05, + "loss": 0.9111, + "step": 7217 + }, + { + "epoch": 0.4431075232511741, + "grad_norm": 0.7716683992762373, + "learning_rate": 1.2307376867513162e-05, + "loss": 0.8851, + "step": 7218 + }, + { + "epoch": 0.4431689124896406, + "grad_norm": 0.7691054836740947, + "learning_rate": 1.2305442125780866e-05, + "loss": 0.8988, + "step": 7219 + }, + { + "epoch": 0.44323030172810707, + "grad_norm": 0.7695190003812812, + "learning_rate": 1.230350729290211e-05, + "loss": 0.8766, + "step": 7220 + }, + { + "epoch": 0.44329169096657356, + "grad_norm": 0.685314103970917, + "learning_rate": 1.2301572368953396e-05, + "loss": 0.8752, + "step": 7221 + }, + { + "epoch": 0.44335308020504005, + "grad_norm": 0.828123286329754, + "learning_rate": 1.2299637354011211e-05, + "loss": 0.9904, + "step": 7222 + }, + { + "epoch": 0.44341446944350654, + "grad_norm": 0.7817214227993718, + "learning_rate": 1.2297702248152064e-05, + "loss": 0.8547, + "step": 7223 + }, + { + "epoch": 0.44347585868197303, + "grad_norm": 0.756993669014807, + "learning_rate": 1.229576705145246e-05, + "loss": 0.8289, + "step": 7224 + }, + { + "epoch": 0.4435372479204395, + "grad_norm": 0.6844381621333487, + "learning_rate": 1.2293831763988901e-05, + "loss": 0.8632, + "step": 7225 + }, + { + "epoch": 0.443598637158906, + "grad_norm": 0.7491924332422447, + "learning_rate": 1.2291896385837911e-05, + "loss": 0.8851, + "step": 7226 + }, + { + "epoch": 0.44366002639737256, + "grad_norm": 0.7978163583668842, + "learning_rate": 1.2289960917075994e-05, + "loss": 0.8958, + "step": 7227 + }, + { + "epoch": 0.44372141563583906, + "grad_norm": 0.7046708304144557, + "learning_rate": 1.2288025357779678e-05, + "loss": 0.8671, + "step": 7228 + }, + { + "epoch": 0.44378280487430555, + "grad_norm": 0.6873769563100212, + "learning_rate": 1.2286089708025477e-05, + "loss": 0.8671, + "step": 7229 + }, + { + "epoch": 0.44384419411277204, + "grad_norm": 2.0832672605298854, + "learning_rate": 1.2284153967889927e-05, + "loss": 0.8638, + "step": 7230 + }, + { + "epoch": 0.44390558335123853, + "grad_norm": 0.7125813323628886, + "learning_rate": 1.2282218137449553e-05, + "loss": 0.8968, + "step": 7231 + }, + { + "epoch": 0.443966972589705, + "grad_norm": 0.9147341328498059, + "learning_rate": 1.228028221678089e-05, + "loss": 0.9001, + "step": 7232 + }, + { + "epoch": 0.4440283618281715, + "grad_norm": 0.7843188839536799, + "learning_rate": 1.2278346205960476e-05, + "loss": 0.9256, + "step": 7233 + }, + { + "epoch": 0.444089751066638, + "grad_norm": 0.7505113320527141, + "learning_rate": 1.227641010506485e-05, + "loss": 0.8774, + "step": 7234 + }, + { + "epoch": 0.4441511403051045, + "grad_norm": 0.7301254935768228, + "learning_rate": 1.2274473914170558e-05, + "loss": 0.8801, + "step": 7235 + }, + { + "epoch": 0.444212529543571, + "grad_norm": 0.7173710024424615, + "learning_rate": 1.2272537633354147e-05, + "loss": 0.874, + "step": 7236 + }, + { + "epoch": 0.44427391878203754, + "grad_norm": 0.7542649933876907, + "learning_rate": 1.227060126269217e-05, + "loss": 0.8675, + "step": 7237 + }, + { + "epoch": 0.444335308020504, + "grad_norm": 0.8081549978045275, + "learning_rate": 1.226866480226118e-05, + "loss": 0.9188, + "step": 7238 + }, + { + "epoch": 0.4443966972589705, + "grad_norm": 0.793263698407924, + "learning_rate": 1.2266728252137735e-05, + "loss": 0.8702, + "step": 7239 + }, + { + "epoch": 0.444458086497437, + "grad_norm": 0.734186377742119, + "learning_rate": 1.22647916123984e-05, + "loss": 0.868, + "step": 7240 + }, + { + "epoch": 0.4445194757359035, + "grad_norm": 0.8276227247972316, + "learning_rate": 1.226285488311974e-05, + "loss": 0.8492, + "step": 7241 + }, + { + "epoch": 0.44458086497437, + "grad_norm": 0.7038134312103841, + "learning_rate": 1.2260918064378327e-05, + "loss": 0.8834, + "step": 7242 + }, + { + "epoch": 0.4446422542128365, + "grad_norm": 0.7622033992013184, + "learning_rate": 1.2258981156250727e-05, + "loss": 0.8965, + "step": 7243 + }, + { + "epoch": 0.444703643451303, + "grad_norm": 0.7169212083907709, + "learning_rate": 1.2257044158813521e-05, + "loss": 0.8563, + "step": 7244 + }, + { + "epoch": 0.44476503268976947, + "grad_norm": 0.7762406522894462, + "learning_rate": 1.2255107072143287e-05, + "loss": 0.807, + "step": 7245 + }, + { + "epoch": 0.44482642192823596, + "grad_norm": 0.697936431727569, + "learning_rate": 1.2253169896316612e-05, + "loss": 0.8501, + "step": 7246 + }, + { + "epoch": 0.44488781116670245, + "grad_norm": 0.7136776521815267, + "learning_rate": 1.2251232631410077e-05, + "loss": 0.8976, + "step": 7247 + }, + { + "epoch": 0.444949200405169, + "grad_norm": 0.7462988289386475, + "learning_rate": 1.2249295277500277e-05, + "loss": 0.8797, + "step": 7248 + }, + { + "epoch": 0.4450105896436355, + "grad_norm": 0.7781267550394011, + "learning_rate": 1.2247357834663804e-05, + "loss": 0.8615, + "step": 7249 + }, + { + "epoch": 0.445071978882102, + "grad_norm": 0.8130606294248128, + "learning_rate": 1.2245420302977256e-05, + "loss": 0.9321, + "step": 7250 + }, + { + "epoch": 0.4451333681205685, + "grad_norm": 0.7534244168414894, + "learning_rate": 1.2243482682517236e-05, + "loss": 0.9011, + "step": 7251 + }, + { + "epoch": 0.44519475735903496, + "grad_norm": 0.67879811781979, + "learning_rate": 1.2241544973360344e-05, + "loss": 0.8483, + "step": 7252 + }, + { + "epoch": 0.44525614659750146, + "grad_norm": 0.7904934567491797, + "learning_rate": 1.2239607175583194e-05, + "loss": 0.9002, + "step": 7253 + }, + { + "epoch": 0.44531753583596795, + "grad_norm": 0.8048499769298262, + "learning_rate": 1.223766928926239e-05, + "loss": 0.8992, + "step": 7254 + }, + { + "epoch": 0.44537892507443444, + "grad_norm": 0.6994599889929659, + "learning_rate": 1.2235731314474553e-05, + "loss": 0.8954, + "step": 7255 + }, + { + "epoch": 0.44544031431290093, + "grad_norm": 0.7098430337147434, + "learning_rate": 1.22337932512963e-05, + "loss": 0.8655, + "step": 7256 + }, + { + "epoch": 0.4455017035513674, + "grad_norm": 0.7344156978019121, + "learning_rate": 1.2231855099804251e-05, + "loss": 0.8378, + "step": 7257 + }, + { + "epoch": 0.4455630927898339, + "grad_norm": 0.7218143707448198, + "learning_rate": 1.2229916860075037e-05, + "loss": 0.8858, + "step": 7258 + }, + { + "epoch": 0.44562448202830046, + "grad_norm": 0.7656452232637656, + "learning_rate": 1.2227978532185278e-05, + "loss": 0.8391, + "step": 7259 + }, + { + "epoch": 0.44568587126676695, + "grad_norm": 0.6839135701249983, + "learning_rate": 1.2226040116211617e-05, + "loss": 0.8389, + "step": 7260 + }, + { + "epoch": 0.44574726050523344, + "grad_norm": 0.7936820361491219, + "learning_rate": 1.222410161223068e-05, + "loss": 0.8862, + "step": 7261 + }, + { + "epoch": 0.44580864974369994, + "grad_norm": 0.7458086578400699, + "learning_rate": 1.2222163020319111e-05, + "loss": 0.8101, + "step": 7262 + }, + { + "epoch": 0.44587003898216643, + "grad_norm": 0.8126793221481905, + "learning_rate": 1.2220224340553555e-05, + "loss": 0.8743, + "step": 7263 + }, + { + "epoch": 0.4459314282206329, + "grad_norm": 0.7588492379290965, + "learning_rate": 1.2218285573010654e-05, + "loss": 0.8507, + "step": 7264 + }, + { + "epoch": 0.4459928174590994, + "grad_norm": 0.817912925477819, + "learning_rate": 1.2216346717767064e-05, + "loss": 0.9052, + "step": 7265 + }, + { + "epoch": 0.4460542066975659, + "grad_norm": 0.7721784891703527, + "learning_rate": 1.221440777489943e-05, + "loss": 0.8206, + "step": 7266 + }, + { + "epoch": 0.4461155959360324, + "grad_norm": 0.8778921246547975, + "learning_rate": 1.2212468744484416e-05, + "loss": 0.9121, + "step": 7267 + }, + { + "epoch": 0.4461769851744989, + "grad_norm": 0.7216651733944311, + "learning_rate": 1.2210529626598678e-05, + "loss": 0.824, + "step": 7268 + }, + { + "epoch": 0.44623837441296543, + "grad_norm": 0.7710437521266873, + "learning_rate": 1.2208590421318882e-05, + "loss": 0.8708, + "step": 7269 + }, + { + "epoch": 0.4462997636514319, + "grad_norm": 0.7414396960278367, + "learning_rate": 1.2206651128721693e-05, + "loss": 0.8564, + "step": 7270 + }, + { + "epoch": 0.4463611528898984, + "grad_norm": 0.7505685599697809, + "learning_rate": 1.2204711748883784e-05, + "loss": 0.8547, + "step": 7271 + }, + { + "epoch": 0.4464225421283649, + "grad_norm": 0.7537061222018435, + "learning_rate": 1.2202772281881827e-05, + "loss": 0.8565, + "step": 7272 + }, + { + "epoch": 0.4464839313668314, + "grad_norm": 0.7855738372088571, + "learning_rate": 1.2200832727792502e-05, + "loss": 0.9146, + "step": 7273 + }, + { + "epoch": 0.4465453206052979, + "grad_norm": 0.7743298516451467, + "learning_rate": 1.2198893086692487e-05, + "loss": 0.8836, + "step": 7274 + }, + { + "epoch": 0.4466067098437644, + "grad_norm": 0.6891888487889725, + "learning_rate": 1.219695335865847e-05, + "loss": 0.8817, + "step": 7275 + }, + { + "epoch": 0.4466680990822309, + "grad_norm": 0.7459146249228235, + "learning_rate": 1.2195013543767136e-05, + "loss": 0.8602, + "step": 7276 + }, + { + "epoch": 0.44672948832069737, + "grad_norm": 0.687885715908745, + "learning_rate": 1.2193073642095172e-05, + "loss": 0.8732, + "step": 7277 + }, + { + "epoch": 0.44679087755916386, + "grad_norm": 0.780454436149515, + "learning_rate": 1.2191133653719284e-05, + "loss": 0.9352, + "step": 7278 + }, + { + "epoch": 0.44685226679763035, + "grad_norm": 0.7872707331222623, + "learning_rate": 1.2189193578716162e-05, + "loss": 0.8452, + "step": 7279 + }, + { + "epoch": 0.4469136560360969, + "grad_norm": 0.7040759708050057, + "learning_rate": 1.2187253417162506e-05, + "loss": 0.8658, + "step": 7280 + }, + { + "epoch": 0.4469750452745634, + "grad_norm": 0.727403791027151, + "learning_rate": 1.2185313169135026e-05, + "loss": 0.8732, + "step": 7281 + }, + { + "epoch": 0.4470364345130299, + "grad_norm": 0.7528684047179086, + "learning_rate": 1.2183372834710428e-05, + "loss": 0.8712, + "step": 7282 + }, + { + "epoch": 0.44709782375149637, + "grad_norm": 0.7234197204669482, + "learning_rate": 1.2181432413965428e-05, + "loss": 0.8344, + "step": 7283 + }, + { + "epoch": 0.44715921298996286, + "grad_norm": 0.7024296874703397, + "learning_rate": 1.2179491906976733e-05, + "loss": 0.8557, + "step": 7284 + }, + { + "epoch": 0.44722060222842935, + "grad_norm": 0.7517633167605948, + "learning_rate": 1.217755131382107e-05, + "loss": 0.8538, + "step": 7285 + }, + { + "epoch": 0.44728199146689585, + "grad_norm": 0.7221722663403528, + "learning_rate": 1.2175610634575154e-05, + "loss": 0.911, + "step": 7286 + }, + { + "epoch": 0.44734338070536234, + "grad_norm": 0.7431970621459002, + "learning_rate": 1.2173669869315714e-05, + "loss": 0.8909, + "step": 7287 + }, + { + "epoch": 0.44740476994382883, + "grad_norm": 0.6780086172136003, + "learning_rate": 1.217172901811948e-05, + "loss": 0.8332, + "step": 7288 + }, + { + "epoch": 0.4474661591822953, + "grad_norm": 0.709002043197676, + "learning_rate": 1.2169788081063181e-05, + "loss": 0.8635, + "step": 7289 + }, + { + "epoch": 0.44752754842076187, + "grad_norm": 0.6751341139891114, + "learning_rate": 1.2167847058223558e-05, + "loss": 0.8535, + "step": 7290 + }, + { + "epoch": 0.44758893765922836, + "grad_norm": 0.7166273311481309, + "learning_rate": 1.2165905949677342e-05, + "loss": 0.8535, + "step": 7291 + }, + { + "epoch": 0.44765032689769485, + "grad_norm": 0.7932434648611886, + "learning_rate": 1.2163964755501283e-05, + "loss": 0.9127, + "step": 7292 + }, + { + "epoch": 0.44771171613616134, + "grad_norm": 0.8398668616781813, + "learning_rate": 1.216202347577212e-05, + "loss": 0.9205, + "step": 7293 + }, + { + "epoch": 0.44777310537462783, + "grad_norm": 0.7371583467037729, + "learning_rate": 1.2160082110566609e-05, + "loss": 0.9038, + "step": 7294 + }, + { + "epoch": 0.4478344946130943, + "grad_norm": 0.7331725846596907, + "learning_rate": 1.2158140659961497e-05, + "loss": 0.8507, + "step": 7295 + }, + { + "epoch": 0.4478958838515608, + "grad_norm": 0.7027585447787545, + "learning_rate": 1.2156199124033541e-05, + "loss": 0.8712, + "step": 7296 + }, + { + "epoch": 0.4479572730900273, + "grad_norm": 0.6981028175835591, + "learning_rate": 1.2154257502859506e-05, + "loss": 0.8885, + "step": 7297 + }, + { + "epoch": 0.4480186623284938, + "grad_norm": 0.7732258194174607, + "learning_rate": 1.2152315796516146e-05, + "loss": 0.9041, + "step": 7298 + }, + { + "epoch": 0.4480800515669603, + "grad_norm": 0.7652105248713701, + "learning_rate": 1.2150374005080233e-05, + "loss": 0.9033, + "step": 7299 + }, + { + "epoch": 0.4481414408054268, + "grad_norm": 0.7378964234416181, + "learning_rate": 1.2148432128628534e-05, + "loss": 0.8691, + "step": 7300 + }, + { + "epoch": 0.44820283004389333, + "grad_norm": 0.721927183750301, + "learning_rate": 1.2146490167237823e-05, + "loss": 0.8673, + "step": 7301 + }, + { + "epoch": 0.4482642192823598, + "grad_norm": 0.7484050948918928, + "learning_rate": 1.2144548120984875e-05, + "loss": 0.9129, + "step": 7302 + }, + { + "epoch": 0.4483256085208263, + "grad_norm": 0.6660081411826884, + "learning_rate": 1.214260598994647e-05, + "loss": 0.8573, + "step": 7303 + }, + { + "epoch": 0.4483869977592928, + "grad_norm": 0.7410539332182493, + "learning_rate": 1.214066377419939e-05, + "loss": 0.8335, + "step": 7304 + }, + { + "epoch": 0.4484483869977593, + "grad_norm": 0.7365992719666467, + "learning_rate": 1.2138721473820422e-05, + "loss": 0.8441, + "step": 7305 + }, + { + "epoch": 0.4485097762362258, + "grad_norm": 0.6767447507436791, + "learning_rate": 1.2136779088886356e-05, + "loss": 0.8675, + "step": 7306 + }, + { + "epoch": 0.4485711654746923, + "grad_norm": 0.718799853844429, + "learning_rate": 1.2134836619473986e-05, + "loss": 0.7945, + "step": 7307 + }, + { + "epoch": 0.44863255471315877, + "grad_norm": 1.0552888963306308, + "learning_rate": 1.2132894065660106e-05, + "loss": 0.8725, + "step": 7308 + }, + { + "epoch": 0.44869394395162526, + "grad_norm": 0.8087804793162393, + "learning_rate": 1.2130951427521514e-05, + "loss": 0.9035, + "step": 7309 + }, + { + "epoch": 0.44875533319009175, + "grad_norm": 0.7049879196682278, + "learning_rate": 1.2129008705135015e-05, + "loss": 0.8241, + "step": 7310 + }, + { + "epoch": 0.4488167224285583, + "grad_norm": 0.7944153329214506, + "learning_rate": 1.2127065898577417e-05, + "loss": 0.8976, + "step": 7311 + }, + { + "epoch": 0.4488781116670248, + "grad_norm": 0.7743215806740881, + "learning_rate": 1.2125123007925528e-05, + "loss": 0.8684, + "step": 7312 + }, + { + "epoch": 0.4489395009054913, + "grad_norm": 0.7297171378056367, + "learning_rate": 1.2123180033256158e-05, + "loss": 0.8748, + "step": 7313 + }, + { + "epoch": 0.4490008901439578, + "grad_norm": 0.7487491043343101, + "learning_rate": 1.2121236974646127e-05, + "loss": 0.8694, + "step": 7314 + }, + { + "epoch": 0.44906227938242427, + "grad_norm": 0.745199748416326, + "learning_rate": 1.2119293832172254e-05, + "loss": 0.8737, + "step": 7315 + }, + { + "epoch": 0.44912366862089076, + "grad_norm": 0.7255499168989521, + "learning_rate": 1.211735060591136e-05, + "loss": 0.9053, + "step": 7316 + }, + { + "epoch": 0.44918505785935725, + "grad_norm": 0.6981325351507315, + "learning_rate": 1.2115407295940274e-05, + "loss": 0.8802, + "step": 7317 + }, + { + "epoch": 0.44924644709782374, + "grad_norm": 0.7486879046791166, + "learning_rate": 1.211346390233582e-05, + "loss": 0.8908, + "step": 7318 + }, + { + "epoch": 0.44930783633629023, + "grad_norm": 0.7837114849327826, + "learning_rate": 1.2111520425174836e-05, + "loss": 0.8969, + "step": 7319 + }, + { + "epoch": 0.4493692255747567, + "grad_norm": 0.6401020771696362, + "learning_rate": 1.2109576864534158e-05, + "loss": 0.8739, + "step": 7320 + }, + { + "epoch": 0.4494306148132232, + "grad_norm": 0.7006513800436682, + "learning_rate": 1.2107633220490622e-05, + "loss": 0.8722, + "step": 7321 + }, + { + "epoch": 0.44949200405168976, + "grad_norm": 0.7635881366106206, + "learning_rate": 1.2105689493121076e-05, + "loss": 0.9327, + "step": 7322 + }, + { + "epoch": 0.44955339329015626, + "grad_norm": 0.7274125633330125, + "learning_rate": 1.2103745682502358e-05, + "loss": 0.8352, + "step": 7323 + }, + { + "epoch": 0.44961478252862275, + "grad_norm": 0.7877423127616625, + "learning_rate": 1.2101801788711323e-05, + "loss": 0.8914, + "step": 7324 + }, + { + "epoch": 0.44967617176708924, + "grad_norm": 0.7341703334266355, + "learning_rate": 1.209985781182482e-05, + "loss": 0.8946, + "step": 7325 + }, + { + "epoch": 0.44973756100555573, + "grad_norm": 0.6766951067033857, + "learning_rate": 1.209791375191971e-05, + "loss": 0.8294, + "step": 7326 + }, + { + "epoch": 0.4497989502440222, + "grad_norm": 0.8330258851663457, + "learning_rate": 1.2095969609072848e-05, + "loss": 0.9682, + "step": 7327 + }, + { + "epoch": 0.4498603394824887, + "grad_norm": 0.7456039423556093, + "learning_rate": 1.2094025383361094e-05, + "loss": 0.8625, + "step": 7328 + }, + { + "epoch": 0.4499217287209552, + "grad_norm": 0.6284727685795061, + "learning_rate": 1.2092081074861324e-05, + "loss": 0.7528, + "step": 7329 + }, + { + "epoch": 0.4499831179594217, + "grad_norm": 0.7339318637486635, + "learning_rate": 1.2090136683650393e-05, + "loss": 0.8362, + "step": 7330 + }, + { + "epoch": 0.4500445071978882, + "grad_norm": 0.7919131978114163, + "learning_rate": 1.2088192209805182e-05, + "loss": 0.8932, + "step": 7331 + }, + { + "epoch": 0.4501058964363547, + "grad_norm": 0.6920709691117244, + "learning_rate": 1.2086247653402567e-05, + "loss": 0.8566, + "step": 7332 + }, + { + "epoch": 0.4501672856748212, + "grad_norm": 0.7168648078857652, + "learning_rate": 1.2084303014519422e-05, + "loss": 0.8834, + "step": 7333 + }, + { + "epoch": 0.4502286749132877, + "grad_norm": 0.701558637498405, + "learning_rate": 1.2082358293232632e-05, + "loss": 0.8719, + "step": 7334 + }, + { + "epoch": 0.4502900641517542, + "grad_norm": 0.7424067343509742, + "learning_rate": 1.208041348961908e-05, + "loss": 0.8426, + "step": 7335 + }, + { + "epoch": 0.4503514533902207, + "grad_norm": 0.7309640141286023, + "learning_rate": 1.2078468603755658e-05, + "loss": 0.8856, + "step": 7336 + }, + { + "epoch": 0.4504128426286872, + "grad_norm": 0.7603660874969934, + "learning_rate": 1.2076523635719255e-05, + "loss": 0.8665, + "step": 7337 + }, + { + "epoch": 0.4504742318671537, + "grad_norm": 0.8022588764828753, + "learning_rate": 1.2074578585586768e-05, + "loss": 0.8726, + "step": 7338 + }, + { + "epoch": 0.4505356211056202, + "grad_norm": 0.6506833013140809, + "learning_rate": 1.2072633453435092e-05, + "loss": 0.8445, + "step": 7339 + }, + { + "epoch": 0.45059701034408667, + "grad_norm": 0.768260919248274, + "learning_rate": 1.2070688239341131e-05, + "loss": 0.8742, + "step": 7340 + }, + { + "epoch": 0.45065839958255316, + "grad_norm": 0.7471685394589167, + "learning_rate": 1.2068742943381788e-05, + "loss": 0.8841, + "step": 7341 + }, + { + "epoch": 0.45071978882101965, + "grad_norm": 0.7453312617370749, + "learning_rate": 1.2066797565633972e-05, + "loss": 0.9026, + "step": 7342 + }, + { + "epoch": 0.4507811780594862, + "grad_norm": 0.7529417761143827, + "learning_rate": 1.2064852106174596e-05, + "loss": 0.8499, + "step": 7343 + }, + { + "epoch": 0.4508425672979527, + "grad_norm": 0.7570180875782484, + "learning_rate": 1.2062906565080572e-05, + "loss": 0.8432, + "step": 7344 + }, + { + "epoch": 0.4509039565364192, + "grad_norm": 0.7321825116349748, + "learning_rate": 1.2060960942428819e-05, + "loss": 0.8777, + "step": 7345 + }, + { + "epoch": 0.4509653457748857, + "grad_norm": 0.7780724300673342, + "learning_rate": 1.2059015238296254e-05, + "loss": 0.8859, + "step": 7346 + }, + { + "epoch": 0.45102673501335216, + "grad_norm": 0.8147375848813219, + "learning_rate": 1.2057069452759809e-05, + "loss": 0.9167, + "step": 7347 + }, + { + "epoch": 0.45108812425181866, + "grad_norm": 0.7516703763144825, + "learning_rate": 1.2055123585896402e-05, + "loss": 0.8378, + "step": 7348 + }, + { + "epoch": 0.45114951349028515, + "grad_norm": 0.778032505317255, + "learning_rate": 1.2053177637782969e-05, + "loss": 0.8829, + "step": 7349 + }, + { + "epoch": 0.45121090272875164, + "grad_norm": 0.6718192264852519, + "learning_rate": 1.2051231608496445e-05, + "loss": 0.8712, + "step": 7350 + }, + { + "epoch": 0.45127229196721813, + "grad_norm": 0.7437376195224566, + "learning_rate": 1.2049285498113763e-05, + "loss": 0.8948, + "step": 7351 + }, + { + "epoch": 0.4513336812056846, + "grad_norm": 0.8027233404320576, + "learning_rate": 1.2047339306711868e-05, + "loss": 0.9178, + "step": 7352 + }, + { + "epoch": 0.4513950704441511, + "grad_norm": 0.8018468673413757, + "learning_rate": 1.2045393034367693e-05, + "loss": 0.9126, + "step": 7353 + }, + { + "epoch": 0.45145645968261766, + "grad_norm": 0.7266516457210339, + "learning_rate": 1.2043446681158202e-05, + "loss": 0.8523, + "step": 7354 + }, + { + "epoch": 0.45151784892108415, + "grad_norm": 0.7410892422535673, + "learning_rate": 1.2041500247160328e-05, + "loss": 0.8725, + "step": 7355 + }, + { + "epoch": 0.45157923815955064, + "grad_norm": 0.7593688867600791, + "learning_rate": 1.2039553732451033e-05, + "loss": 0.8535, + "step": 7356 + }, + { + "epoch": 0.45164062739801714, + "grad_norm": 0.7345464557844409, + "learning_rate": 1.2037607137107267e-05, + "loss": 0.9041, + "step": 7357 + }, + { + "epoch": 0.4517020166364836, + "grad_norm": 0.7725298350173156, + "learning_rate": 1.2035660461205995e-05, + "loss": 0.8633, + "step": 7358 + }, + { + "epoch": 0.4517634058749501, + "grad_norm": 0.8159382321928189, + "learning_rate": 1.203371370482418e-05, + "loss": 0.8698, + "step": 7359 + }, + { + "epoch": 0.4518247951134166, + "grad_norm": 0.8360637406274379, + "learning_rate": 1.2031766868038779e-05, + "loss": 0.8835, + "step": 7360 + }, + { + "epoch": 0.4518861843518831, + "grad_norm": 0.7099077790828325, + "learning_rate": 1.2029819950926776e-05, + "loss": 0.894, + "step": 7361 + }, + { + "epoch": 0.4519475735903496, + "grad_norm": 0.7459610253492421, + "learning_rate": 1.2027872953565125e-05, + "loss": 0.8993, + "step": 7362 + }, + { + "epoch": 0.4520089628288161, + "grad_norm": 0.6840792979642936, + "learning_rate": 1.2025925876030815e-05, + "loss": 0.8296, + "step": 7363 + }, + { + "epoch": 0.45207035206728263, + "grad_norm": 0.840344550526272, + "learning_rate": 1.202397871840082e-05, + "loss": 0.839, + "step": 7364 + }, + { + "epoch": 0.4521317413057491, + "grad_norm": 0.7310971904021457, + "learning_rate": 1.202203148075212e-05, + "loss": 0.8569, + "step": 7365 + }, + { + "epoch": 0.4521931305442156, + "grad_norm": 0.8442289108499383, + "learning_rate": 1.2020084163161703e-05, + "loss": 0.8892, + "step": 7366 + }, + { + "epoch": 0.4522545197826821, + "grad_norm": 0.6844135183163493, + "learning_rate": 1.2018136765706552e-05, + "loss": 0.8097, + "step": 7367 + }, + { + "epoch": 0.4523159090211486, + "grad_norm": 0.7471762063496923, + "learning_rate": 1.2016189288463662e-05, + "loss": 0.811, + "step": 7368 + }, + { + "epoch": 0.4523772982596151, + "grad_norm": 0.7368880041511242, + "learning_rate": 1.2014241731510026e-05, + "loss": 0.8685, + "step": 7369 + }, + { + "epoch": 0.4524386874980816, + "grad_norm": 0.8258066191022471, + "learning_rate": 1.2012294094922643e-05, + "loss": 0.8858, + "step": 7370 + }, + { + "epoch": 0.4525000767365481, + "grad_norm": 0.7544450222725013, + "learning_rate": 1.2010346378778511e-05, + "loss": 0.7629, + "step": 7371 + }, + { + "epoch": 0.45256146597501457, + "grad_norm": 0.8563335821940817, + "learning_rate": 1.2008398583154635e-05, + "loss": 0.926, + "step": 7372 + }, + { + "epoch": 0.45262285521348106, + "grad_norm": 0.755608952972336, + "learning_rate": 1.2006450708128017e-05, + "loss": 0.8872, + "step": 7373 + }, + { + "epoch": 0.45268424445194755, + "grad_norm": 0.7288379626328435, + "learning_rate": 1.2004502753775676e-05, + "loss": 0.867, + "step": 7374 + }, + { + "epoch": 0.4527456336904141, + "grad_norm": 0.7828719461088163, + "learning_rate": 1.200255472017462e-05, + "loss": 0.8849, + "step": 7375 + }, + { + "epoch": 0.4528070229288806, + "grad_norm": 0.7632536718175924, + "learning_rate": 1.2000606607401863e-05, + "loss": 0.8931, + "step": 7376 + }, + { + "epoch": 0.4528684121673471, + "grad_norm": 0.7453301164872753, + "learning_rate": 1.1998658415534429e-05, + "loss": 0.9309, + "step": 7377 + }, + { + "epoch": 0.45292980140581357, + "grad_norm": 0.6037471084330922, + "learning_rate": 1.1996710144649337e-05, + "loss": 0.7441, + "step": 7378 + }, + { + "epoch": 0.45299119064428006, + "grad_norm": 0.7418116339110686, + "learning_rate": 1.1994761794823618e-05, + "loss": 0.8452, + "step": 7379 + }, + { + "epoch": 0.45305257988274655, + "grad_norm": 0.8816517699374138, + "learning_rate": 1.1992813366134291e-05, + "loss": 0.9071, + "step": 7380 + }, + { + "epoch": 0.45311396912121304, + "grad_norm": 0.6908724832527277, + "learning_rate": 1.1990864858658395e-05, + "loss": 0.8426, + "step": 7381 + }, + { + "epoch": 0.45317535835967954, + "grad_norm": 0.73801435777344, + "learning_rate": 1.1988916272472964e-05, + "loss": 0.8853, + "step": 7382 + }, + { + "epoch": 0.45323674759814603, + "grad_norm": 0.732056138783571, + "learning_rate": 1.1986967607655035e-05, + "loss": 0.8505, + "step": 7383 + }, + { + "epoch": 0.4532981368366125, + "grad_norm": 0.6726630025530982, + "learning_rate": 1.198501886428165e-05, + "loss": 0.8437, + "step": 7384 + }, + { + "epoch": 0.453359526075079, + "grad_norm": 0.7781085713029493, + "learning_rate": 1.1983070042429849e-05, + "loss": 0.8655, + "step": 7385 + }, + { + "epoch": 0.45342091531354556, + "grad_norm": 0.825699610630709, + "learning_rate": 1.1981121142176688e-05, + "loss": 0.9075, + "step": 7386 + }, + { + "epoch": 0.45348230455201205, + "grad_norm": 0.7407443021572948, + "learning_rate": 1.1979172163599208e-05, + "loss": 0.8743, + "step": 7387 + }, + { + "epoch": 0.45354369379047854, + "grad_norm": 0.7461422384666904, + "learning_rate": 1.1977223106774472e-05, + "loss": 0.8409, + "step": 7388 + }, + { + "epoch": 0.45360508302894503, + "grad_norm": 0.7149058433375913, + "learning_rate": 1.1975273971779528e-05, + "loss": 0.8713, + "step": 7389 + }, + { + "epoch": 0.4536664722674115, + "grad_norm": 0.7471816945951181, + "learning_rate": 1.1973324758691441e-05, + "loss": 0.8865, + "step": 7390 + }, + { + "epoch": 0.453727861505878, + "grad_norm": 0.8064478950135833, + "learning_rate": 1.1971375467587271e-05, + "loss": 0.9199, + "step": 7391 + }, + { + "epoch": 0.4537892507443445, + "grad_norm": 0.8109833343150581, + "learning_rate": 1.1969426098544086e-05, + "loss": 0.8147, + "step": 7392 + }, + { + "epoch": 0.453850639982811, + "grad_norm": 0.7487526151437628, + "learning_rate": 1.1967476651638956e-05, + "loss": 0.8859, + "step": 7393 + }, + { + "epoch": 0.4539120292212775, + "grad_norm": 0.7613138482053569, + "learning_rate": 1.1965527126948946e-05, + "loss": 0.8381, + "step": 7394 + }, + { + "epoch": 0.453973418459744, + "grad_norm": 0.7776888907894072, + "learning_rate": 1.196357752455114e-05, + "loss": 0.8971, + "step": 7395 + }, + { + "epoch": 0.45403480769821053, + "grad_norm": 0.7845058986852267, + "learning_rate": 1.1961627844522612e-05, + "loss": 0.8831, + "step": 7396 + }, + { + "epoch": 0.454096196936677, + "grad_norm": 0.719814728318968, + "learning_rate": 1.1959678086940446e-05, + "loss": 0.9077, + "step": 7397 + }, + { + "epoch": 0.4541575861751435, + "grad_norm": 0.8367809829319924, + "learning_rate": 1.1957728251881719e-05, + "loss": 0.8983, + "step": 7398 + }, + { + "epoch": 0.45421897541361, + "grad_norm": 0.8247622162711573, + "learning_rate": 1.1955778339423527e-05, + "loss": 0.9562, + "step": 7399 + }, + { + "epoch": 0.4542803646520765, + "grad_norm": 0.7191046266413202, + "learning_rate": 1.1953828349642955e-05, + "loss": 0.854, + "step": 7400 + }, + { + "epoch": 0.454341753890543, + "grad_norm": 0.6857479637984261, + "learning_rate": 1.19518782826171e-05, + "loss": 0.8448, + "step": 7401 + }, + { + "epoch": 0.4544031431290095, + "grad_norm": 0.7338445446728252, + "learning_rate": 1.1949928138423056e-05, + "loss": 0.8631, + "step": 7402 + }, + { + "epoch": 0.45446453236747597, + "grad_norm": 0.7932340647506808, + "learning_rate": 1.1947977917137927e-05, + "loss": 0.8234, + "step": 7403 + }, + { + "epoch": 0.45452592160594246, + "grad_norm": 0.790452582565786, + "learning_rate": 1.1946027618838811e-05, + "loss": 0.8757, + "step": 7404 + }, + { + "epoch": 0.45458731084440895, + "grad_norm": 0.7497396617204141, + "learning_rate": 1.1944077243602812e-05, + "loss": 0.8992, + "step": 7405 + }, + { + "epoch": 0.45464870008287545, + "grad_norm": 0.8021721422691697, + "learning_rate": 1.1942126791507046e-05, + "loss": 0.8431, + "step": 7406 + }, + { + "epoch": 0.454710089321342, + "grad_norm": 0.7419495396280199, + "learning_rate": 1.1940176262628617e-05, + "loss": 0.8859, + "step": 7407 + }, + { + "epoch": 0.4547714785598085, + "grad_norm": 0.701871991884302, + "learning_rate": 1.1938225657044647e-05, + "loss": 0.8588, + "step": 7408 + }, + { + "epoch": 0.454832867798275, + "grad_norm": 0.7255908548111876, + "learning_rate": 1.1936274974832247e-05, + "loss": 0.8617, + "step": 7409 + }, + { + "epoch": 0.45489425703674147, + "grad_norm": 0.8439691754639018, + "learning_rate": 1.1934324216068543e-05, + "loss": 0.9321, + "step": 7410 + }, + { + "epoch": 0.45495564627520796, + "grad_norm": 0.7930206925561436, + "learning_rate": 1.1932373380830659e-05, + "loss": 0.8371, + "step": 7411 + }, + { + "epoch": 0.45501703551367445, + "grad_norm": 0.7593931961712993, + "learning_rate": 1.1930422469195717e-05, + "loss": 0.9003, + "step": 7412 + }, + { + "epoch": 0.45507842475214094, + "grad_norm": 0.8007483180621678, + "learning_rate": 1.1928471481240853e-05, + "loss": 0.945, + "step": 7413 + }, + { + "epoch": 0.45513981399060743, + "grad_norm": 0.7115764189997594, + "learning_rate": 1.1926520417043195e-05, + "loss": 0.9064, + "step": 7414 + }, + { + "epoch": 0.4552012032290739, + "grad_norm": 0.7434150807047266, + "learning_rate": 1.1924569276679883e-05, + "loss": 0.8906, + "step": 7415 + }, + { + "epoch": 0.4552625924675404, + "grad_norm": 0.817873986176734, + "learning_rate": 1.1922618060228053e-05, + "loss": 0.8562, + "step": 7416 + }, + { + "epoch": 0.45532398170600696, + "grad_norm": 0.8179053607812036, + "learning_rate": 1.1920666767764847e-05, + "loss": 0.8799, + "step": 7417 + }, + { + "epoch": 0.45538537094447346, + "grad_norm": 0.7669667270583106, + "learning_rate": 1.1918715399367416e-05, + "loss": 0.8111, + "step": 7418 + }, + { + "epoch": 0.45544676018293995, + "grad_norm": 0.7968021797577066, + "learning_rate": 1.1916763955112897e-05, + "loss": 0.8887, + "step": 7419 + }, + { + "epoch": 0.45550814942140644, + "grad_norm": 0.7320281400386911, + "learning_rate": 1.191481243507845e-05, + "loss": 0.9324, + "step": 7420 + }, + { + "epoch": 0.45556953865987293, + "grad_norm": 0.7654975230533633, + "learning_rate": 1.1912860839341227e-05, + "loss": 0.8743, + "step": 7421 + }, + { + "epoch": 0.4556309278983394, + "grad_norm": 0.7523781552875107, + "learning_rate": 1.1910909167978385e-05, + "loss": 0.9281, + "step": 7422 + }, + { + "epoch": 0.4556923171368059, + "grad_norm": 0.7997763035564646, + "learning_rate": 1.1908957421067083e-05, + "loss": 0.8623, + "step": 7423 + }, + { + "epoch": 0.4557537063752724, + "grad_norm": 0.8615240505207704, + "learning_rate": 1.190700559868448e-05, + "loss": 0.9359, + "step": 7424 + }, + { + "epoch": 0.4558150956137389, + "grad_norm": 0.7367632537269879, + "learning_rate": 1.1905053700907753e-05, + "loss": 0.8687, + "step": 7425 + }, + { + "epoch": 0.4558764848522054, + "grad_norm": 0.8495925139101096, + "learning_rate": 1.190310172781406e-05, + "loss": 0.9199, + "step": 7426 + }, + { + "epoch": 0.4559378740906719, + "grad_norm": 0.7500602777413913, + "learning_rate": 1.1901149679480577e-05, + "loss": 0.8666, + "step": 7427 + }, + { + "epoch": 0.4559992633291384, + "grad_norm": 0.7710627383562358, + "learning_rate": 1.1899197555984481e-05, + "loss": 0.8271, + "step": 7428 + }, + { + "epoch": 0.4560606525676049, + "grad_norm": 0.7244033052388931, + "learning_rate": 1.1897245357402948e-05, + "loss": 0.8487, + "step": 7429 + }, + { + "epoch": 0.4561220418060714, + "grad_norm": 0.8457377549476415, + "learning_rate": 1.1895293083813158e-05, + "loss": 0.8358, + "step": 7430 + }, + { + "epoch": 0.4561834310445379, + "grad_norm": 0.7965534400951179, + "learning_rate": 1.1893340735292294e-05, + "loss": 0.8817, + "step": 7431 + }, + { + "epoch": 0.4562448202830044, + "grad_norm": 0.8258256923108649, + "learning_rate": 1.1891388311917547e-05, + "loss": 0.8948, + "step": 7432 + }, + { + "epoch": 0.4563062095214709, + "grad_norm": 0.8321807879560406, + "learning_rate": 1.1889435813766103e-05, + "loss": 0.8573, + "step": 7433 + }, + { + "epoch": 0.4563675987599374, + "grad_norm": 0.7386854220869278, + "learning_rate": 1.1887483240915157e-05, + "loss": 0.8782, + "step": 7434 + }, + { + "epoch": 0.45642898799840387, + "grad_norm": 0.7909774939038571, + "learning_rate": 1.1885530593441903e-05, + "loss": 0.8877, + "step": 7435 + }, + { + "epoch": 0.45649037723687036, + "grad_norm": 0.7537640067465793, + "learning_rate": 1.188357787142354e-05, + "loss": 0.838, + "step": 7436 + }, + { + "epoch": 0.45655176647533685, + "grad_norm": 0.705495037810192, + "learning_rate": 1.1881625074937269e-05, + "loss": 0.8663, + "step": 7437 + }, + { + "epoch": 0.45661315571380334, + "grad_norm": 0.8329704321186486, + "learning_rate": 1.1879672204060296e-05, + "loss": 0.88, + "step": 7438 + }, + { + "epoch": 0.4566745449522699, + "grad_norm": 0.748463464373828, + "learning_rate": 1.1877719258869827e-05, + "loss": 0.8678, + "step": 7439 + }, + { + "epoch": 0.4567359341907364, + "grad_norm": 0.7827003518277059, + "learning_rate": 1.1875766239443074e-05, + "loss": 0.8981, + "step": 7440 + }, + { + "epoch": 0.4567973234292029, + "grad_norm": 0.6969900955577505, + "learning_rate": 1.187381314585725e-05, + "loss": 0.841, + "step": 7441 + }, + { + "epoch": 0.45685871266766936, + "grad_norm": 0.8341244924480272, + "learning_rate": 1.1871859978189565e-05, + "loss": 0.897, + "step": 7442 + }, + { + "epoch": 0.45692010190613586, + "grad_norm": 0.7341150946366856, + "learning_rate": 1.186990673651725e-05, + "loss": 0.8586, + "step": 7443 + }, + { + "epoch": 0.45698149114460235, + "grad_norm": 0.7687496255179971, + "learning_rate": 1.1867953420917518e-05, + "loss": 0.8909, + "step": 7444 + }, + { + "epoch": 0.45704288038306884, + "grad_norm": 0.8372471841476365, + "learning_rate": 1.1866000031467597e-05, + "loss": 0.8783, + "step": 7445 + }, + { + "epoch": 0.45710426962153533, + "grad_norm": 0.7242187765526505, + "learning_rate": 1.1864046568244714e-05, + "loss": 0.8563, + "step": 7446 + }, + { + "epoch": 0.4571656588600018, + "grad_norm": 0.7763939003915776, + "learning_rate": 1.1862093031326101e-05, + "loss": 0.8634, + "step": 7447 + }, + { + "epoch": 0.4572270480984683, + "grad_norm": 0.7674052004028309, + "learning_rate": 1.1860139420788994e-05, + "loss": 0.9117, + "step": 7448 + }, + { + "epoch": 0.45728843733693486, + "grad_norm": 0.7384172640666139, + "learning_rate": 1.1858185736710621e-05, + "loss": 0.8611, + "step": 7449 + }, + { + "epoch": 0.45734982657540135, + "grad_norm": 0.7589277075602853, + "learning_rate": 1.1856231979168235e-05, + "loss": 0.8871, + "step": 7450 + }, + { + "epoch": 0.45741121581386784, + "grad_norm": 0.70722023105149, + "learning_rate": 1.1854278148239064e-05, + "loss": 0.9398, + "step": 7451 + }, + { + "epoch": 0.45747260505233434, + "grad_norm": 0.7109364959835217, + "learning_rate": 1.1852324244000365e-05, + "loss": 0.8618, + "step": 7452 + }, + { + "epoch": 0.4575339942908008, + "grad_norm": 0.7449869222480331, + "learning_rate": 1.185037026652938e-05, + "loss": 0.8837, + "step": 7453 + }, + { + "epoch": 0.4575953835292673, + "grad_norm": 0.7771121252574361, + "learning_rate": 1.1848416215903362e-05, + "loss": 0.8889, + "step": 7454 + }, + { + "epoch": 0.4576567727677338, + "grad_norm": 0.7518741248738521, + "learning_rate": 1.1846462092199567e-05, + "loss": 0.8811, + "step": 7455 + }, + { + "epoch": 0.4577181620062003, + "grad_norm": 0.8153566349388279, + "learning_rate": 1.1844507895495245e-05, + "loss": 0.8537, + "step": 7456 + }, + { + "epoch": 0.4577795512446668, + "grad_norm": 0.7581360081100632, + "learning_rate": 1.1842553625867668e-05, + "loss": 0.8296, + "step": 7457 + }, + { + "epoch": 0.4578409404831333, + "grad_norm": 0.7263511719574832, + "learning_rate": 1.1840599283394085e-05, + "loss": 0.8358, + "step": 7458 + }, + { + "epoch": 0.4579023297215998, + "grad_norm": 0.7663848497445511, + "learning_rate": 1.1838644868151772e-05, + "loss": 0.8429, + "step": 7459 + }, + { + "epoch": 0.4579637189600663, + "grad_norm": 0.7665074531609639, + "learning_rate": 1.1836690380217991e-05, + "loss": 0.8383, + "step": 7460 + }, + { + "epoch": 0.4580251081985328, + "grad_norm": 0.7686271920620019, + "learning_rate": 1.1834735819670018e-05, + "loss": 0.8471, + "step": 7461 + }, + { + "epoch": 0.4580864974369993, + "grad_norm": 0.7594523436259403, + "learning_rate": 1.1832781186585125e-05, + "loss": 0.9019, + "step": 7462 + }, + { + "epoch": 0.4581478866754658, + "grad_norm": 0.7349059152144799, + "learning_rate": 1.1830826481040587e-05, + "loss": 0.8616, + "step": 7463 + }, + { + "epoch": 0.4582092759139323, + "grad_norm": 0.7313688630113688, + "learning_rate": 1.1828871703113686e-05, + "loss": 0.8636, + "step": 7464 + }, + { + "epoch": 0.4582706651523988, + "grad_norm": 0.7521572509014901, + "learning_rate": 1.1826916852881709e-05, + "loss": 0.8431, + "step": 7465 + }, + { + "epoch": 0.4583320543908653, + "grad_norm": 0.7804867163131696, + "learning_rate": 1.1824961930421934e-05, + "loss": 0.9199, + "step": 7466 + }, + { + "epoch": 0.45839344362933176, + "grad_norm": 0.8095440869771603, + "learning_rate": 1.1823006935811656e-05, + "loss": 0.8543, + "step": 7467 + }, + { + "epoch": 0.45845483286779826, + "grad_norm": 0.770106099269308, + "learning_rate": 1.1821051869128165e-05, + "loss": 0.8714, + "step": 7468 + }, + { + "epoch": 0.45851622210626475, + "grad_norm": 0.800830041142692, + "learning_rate": 1.181909673044875e-05, + "loss": 0.8351, + "step": 7469 + }, + { + "epoch": 0.4585776113447313, + "grad_norm": 0.7936803531272395, + "learning_rate": 1.1817141519850713e-05, + "loss": 0.8831, + "step": 7470 + }, + { + "epoch": 0.4586390005831978, + "grad_norm": 0.7222384623732562, + "learning_rate": 1.1815186237411353e-05, + "loss": 0.8706, + "step": 7471 + }, + { + "epoch": 0.4587003898216643, + "grad_norm": 0.6986579657876597, + "learning_rate": 1.1813230883207974e-05, + "loss": 0.8574, + "step": 7472 + }, + { + "epoch": 0.45876177906013077, + "grad_norm": 0.6752964254930454, + "learning_rate": 1.1811275457317879e-05, + "loss": 0.8893, + "step": 7473 + }, + { + "epoch": 0.45882316829859726, + "grad_norm": 0.736768968107597, + "learning_rate": 1.1809319959818377e-05, + "loss": 0.8533, + "step": 7474 + }, + { + "epoch": 0.45888455753706375, + "grad_norm": 0.7422554110476415, + "learning_rate": 1.1807364390786785e-05, + "loss": 0.8889, + "step": 7475 + }, + { + "epoch": 0.45894594677553024, + "grad_norm": 0.7850773174680278, + "learning_rate": 1.1805408750300406e-05, + "loss": 0.8626, + "step": 7476 + }, + { + "epoch": 0.45900733601399674, + "grad_norm": 0.7384770115753455, + "learning_rate": 1.1803453038436566e-05, + "loss": 0.9011, + "step": 7477 + }, + { + "epoch": 0.45906872525246323, + "grad_norm": 0.7365952438818385, + "learning_rate": 1.1801497255272583e-05, + "loss": 0.8294, + "step": 7478 + }, + { + "epoch": 0.4591301144909297, + "grad_norm": 0.7700564415146378, + "learning_rate": 1.1799541400885774e-05, + "loss": 0.8812, + "step": 7479 + }, + { + "epoch": 0.4591915037293962, + "grad_norm": 0.7433101571347285, + "learning_rate": 1.1797585475353475e-05, + "loss": 0.8938, + "step": 7480 + }, + { + "epoch": 0.45925289296786276, + "grad_norm": 0.7868070507051977, + "learning_rate": 1.1795629478753004e-05, + "loss": 0.8992, + "step": 7481 + }, + { + "epoch": 0.45931428220632925, + "grad_norm": 0.7671109943344575, + "learning_rate": 1.1793673411161698e-05, + "loss": 0.9171, + "step": 7482 + }, + { + "epoch": 0.45937567144479574, + "grad_norm": 0.7654962037877916, + "learning_rate": 1.1791717272656886e-05, + "loss": 0.8707, + "step": 7483 + }, + { + "epoch": 0.45943706068326223, + "grad_norm": 0.7951850072311104, + "learning_rate": 1.178976106331591e-05, + "loss": 0.8565, + "step": 7484 + }, + { + "epoch": 0.4594984499217287, + "grad_norm": 0.740464022498234, + "learning_rate": 1.1787804783216106e-05, + "loss": 0.856, + "step": 7485 + }, + { + "epoch": 0.4595598391601952, + "grad_norm": 0.8563120718945602, + "learning_rate": 1.1785848432434814e-05, + "loss": 0.8442, + "step": 7486 + }, + { + "epoch": 0.4596212283986617, + "grad_norm": 0.7354009274090585, + "learning_rate": 1.178389201104939e-05, + "loss": 0.8683, + "step": 7487 + }, + { + "epoch": 0.4596826176371282, + "grad_norm": 0.8104389890778052, + "learning_rate": 1.1781935519137166e-05, + "loss": 0.8906, + "step": 7488 + }, + { + "epoch": 0.4597440068755947, + "grad_norm": 0.767419362306427, + "learning_rate": 1.1779978956775507e-05, + "loss": 0.8647, + "step": 7489 + }, + { + "epoch": 0.4598053961140612, + "grad_norm": 0.7115349717732167, + "learning_rate": 1.1778022324041754e-05, + "loss": 0.8482, + "step": 7490 + }, + { + "epoch": 0.45986678535252773, + "grad_norm": 0.8472067394882347, + "learning_rate": 1.177606562101327e-05, + "loss": 0.8784, + "step": 7491 + }, + { + "epoch": 0.4599281745909942, + "grad_norm": 0.7504317872735143, + "learning_rate": 1.1774108847767416e-05, + "loss": 0.8497, + "step": 7492 + }, + { + "epoch": 0.4599895638294607, + "grad_norm": 0.8369502036005081, + "learning_rate": 1.177215200438155e-05, + "loss": 0.8744, + "step": 7493 + }, + { + "epoch": 0.4600509530679272, + "grad_norm": 0.8076393109083637, + "learning_rate": 1.1770195090933035e-05, + "loss": 0.8659, + "step": 7494 + }, + { + "epoch": 0.4601123423063937, + "grad_norm": 0.7280468651457859, + "learning_rate": 1.176823810749924e-05, + "loss": 0.8295, + "step": 7495 + }, + { + "epoch": 0.4601737315448602, + "grad_norm": 0.8211460506151851, + "learning_rate": 1.1766281054157536e-05, + "loss": 0.8982, + "step": 7496 + }, + { + "epoch": 0.4602351207833267, + "grad_norm": 0.7541592726272967, + "learning_rate": 1.1764323930985298e-05, + "loss": 0.8761, + "step": 7497 + }, + { + "epoch": 0.46029651002179317, + "grad_norm": 0.7018654166969376, + "learning_rate": 1.1762366738059897e-05, + "loss": 0.8907, + "step": 7498 + }, + { + "epoch": 0.46035789926025966, + "grad_norm": 0.752729196379944, + "learning_rate": 1.1760409475458712e-05, + "loss": 0.8893, + "step": 7499 + }, + { + "epoch": 0.46041928849872615, + "grad_norm": 0.6800525832534287, + "learning_rate": 1.1758452143259128e-05, + "loss": 0.889, + "step": 7500 + }, + { + "epoch": 0.46048067773719265, + "grad_norm": 0.733339267160787, + "learning_rate": 1.175649474153852e-05, + "loss": 0.8426, + "step": 7501 + }, + { + "epoch": 0.4605420669756592, + "grad_norm": 0.6969161279443401, + "learning_rate": 1.1754537270374284e-05, + "loss": 0.8828, + "step": 7502 + }, + { + "epoch": 0.4606034562141257, + "grad_norm": 0.7200113219725907, + "learning_rate": 1.1752579729843807e-05, + "loss": 0.8563, + "step": 7503 + }, + { + "epoch": 0.4606648454525922, + "grad_norm": 0.6571564501649796, + "learning_rate": 1.175062212002448e-05, + "loss": 0.8519, + "step": 7504 + }, + { + "epoch": 0.46072623469105867, + "grad_norm": 0.7265418148178644, + "learning_rate": 1.1748664440993695e-05, + "loss": 0.8641, + "step": 7505 + }, + { + "epoch": 0.46078762392952516, + "grad_norm": 0.7198279057675327, + "learning_rate": 1.1746706692828853e-05, + "loss": 0.8799, + "step": 7506 + }, + { + "epoch": 0.46084901316799165, + "grad_norm": 0.6672418033129394, + "learning_rate": 1.1744748875607357e-05, + "loss": 0.8408, + "step": 7507 + }, + { + "epoch": 0.46091040240645814, + "grad_norm": 0.6936301720965231, + "learning_rate": 1.17427909894066e-05, + "loss": 0.8438, + "step": 7508 + }, + { + "epoch": 0.46097179164492463, + "grad_norm": 0.7115705962861486, + "learning_rate": 1.1740833034303997e-05, + "loss": 0.8698, + "step": 7509 + }, + { + "epoch": 0.4610331808833911, + "grad_norm": 0.8322884638167366, + "learning_rate": 1.1738875010376955e-05, + "loss": 0.9012, + "step": 7510 + }, + { + "epoch": 0.4610945701218576, + "grad_norm": 0.6289354663028275, + "learning_rate": 1.1736916917702881e-05, + "loss": 0.8097, + "step": 7511 + }, + { + "epoch": 0.4611559593603241, + "grad_norm": 0.768126557173663, + "learning_rate": 1.1734958756359196e-05, + "loss": 0.8528, + "step": 7512 + }, + { + "epoch": 0.46121734859879066, + "grad_norm": 0.7169312670206279, + "learning_rate": 1.1733000526423309e-05, + "loss": 0.8879, + "step": 7513 + }, + { + "epoch": 0.46127873783725715, + "grad_norm": 0.6847611818384081, + "learning_rate": 1.1731042227972645e-05, + "loss": 0.8372, + "step": 7514 + }, + { + "epoch": 0.46134012707572364, + "grad_norm": 0.775562354110037, + "learning_rate": 1.1729083861084618e-05, + "loss": 0.8895, + "step": 7515 + }, + { + "epoch": 0.46140151631419013, + "grad_norm": 0.8061112017059039, + "learning_rate": 1.1727125425836663e-05, + "loss": 0.8637, + "step": 7516 + }, + { + "epoch": 0.4614629055526566, + "grad_norm": 0.7547195687467958, + "learning_rate": 1.1725166922306202e-05, + "loss": 0.8814, + "step": 7517 + }, + { + "epoch": 0.4615242947911231, + "grad_norm": 0.7534044253498425, + "learning_rate": 1.1723208350570662e-05, + "loss": 0.8483, + "step": 7518 + }, + { + "epoch": 0.4615856840295896, + "grad_norm": 0.7866811902278542, + "learning_rate": 1.1721249710707485e-05, + "loss": 0.8861, + "step": 7519 + }, + { + "epoch": 0.4616470732680561, + "grad_norm": 0.8043396472431964, + "learning_rate": 1.1719291002794096e-05, + "loss": 0.88, + "step": 7520 + }, + { + "epoch": 0.4617084625065226, + "grad_norm": 0.751503089955557, + "learning_rate": 1.1717332226907942e-05, + "loss": 0.8461, + "step": 7521 + }, + { + "epoch": 0.4617698517449891, + "grad_norm": 0.7521842073974147, + "learning_rate": 1.1715373383126459e-05, + "loss": 0.8646, + "step": 7522 + }, + { + "epoch": 0.4618312409834556, + "grad_norm": 0.7909304144138296, + "learning_rate": 1.171341447152709e-05, + "loss": 0.8739, + "step": 7523 + }, + { + "epoch": 0.4618926302219221, + "grad_norm": 0.7628862576095861, + "learning_rate": 1.1711455492187284e-05, + "loss": 0.9038, + "step": 7524 + }, + { + "epoch": 0.4619540194603886, + "grad_norm": 0.7107506852367798, + "learning_rate": 1.1709496445184489e-05, + "loss": 0.8346, + "step": 7525 + }, + { + "epoch": 0.4620154086988551, + "grad_norm": 0.7550686981741404, + "learning_rate": 1.1707537330596159e-05, + "loss": 0.877, + "step": 7526 + }, + { + "epoch": 0.4620767979373216, + "grad_norm": 0.7906530017885639, + "learning_rate": 1.1705578148499743e-05, + "loss": 0.8724, + "step": 7527 + }, + { + "epoch": 0.4621381871757881, + "grad_norm": 0.7490208457874044, + "learning_rate": 1.17036188989727e-05, + "loss": 0.8397, + "step": 7528 + }, + { + "epoch": 0.4621995764142546, + "grad_norm": 0.7571782413714095, + "learning_rate": 1.1701659582092493e-05, + "loss": 0.8582, + "step": 7529 + }, + { + "epoch": 0.46226096565272107, + "grad_norm": 0.766101259842319, + "learning_rate": 1.1699700197936581e-05, + "loss": 0.9259, + "step": 7530 + }, + { + "epoch": 0.46232235489118756, + "grad_norm": 0.772542632885962, + "learning_rate": 1.1697740746582428e-05, + "loss": 0.8784, + "step": 7531 + }, + { + "epoch": 0.46238374412965405, + "grad_norm": 0.725475804742687, + "learning_rate": 1.1695781228107506e-05, + "loss": 0.8407, + "step": 7532 + }, + { + "epoch": 0.46244513336812054, + "grad_norm": 0.7024522461626885, + "learning_rate": 1.1693821642589276e-05, + "loss": 0.8512, + "step": 7533 + }, + { + "epoch": 0.4625065226065871, + "grad_norm": 0.7740425613418556, + "learning_rate": 1.1691861990105222e-05, + "loss": 0.8938, + "step": 7534 + }, + { + "epoch": 0.4625679118450536, + "grad_norm": 0.7606848952547897, + "learning_rate": 1.1689902270732816e-05, + "loss": 0.8773, + "step": 7535 + }, + { + "epoch": 0.4626293010835201, + "grad_norm": 0.8203655351190615, + "learning_rate": 1.1687942484549533e-05, + "loss": 0.8227, + "step": 7536 + }, + { + "epoch": 0.46269069032198656, + "grad_norm": 0.7626680313365337, + "learning_rate": 1.1685982631632857e-05, + "loss": 0.8265, + "step": 7537 + }, + { + "epoch": 0.46275207956045306, + "grad_norm": 0.6971256131316426, + "learning_rate": 1.1684022712060269e-05, + "loss": 0.7673, + "step": 7538 + }, + { + "epoch": 0.46281346879891955, + "grad_norm": 0.7014164482227622, + "learning_rate": 1.1682062725909257e-05, + "loss": 0.8717, + "step": 7539 + }, + { + "epoch": 0.46287485803738604, + "grad_norm": 0.8076091638307386, + "learning_rate": 1.1680102673257308e-05, + "loss": 0.8511, + "step": 7540 + }, + { + "epoch": 0.46293624727585253, + "grad_norm": 0.7654057852991688, + "learning_rate": 1.1678142554181915e-05, + "loss": 0.8559, + "step": 7541 + }, + { + "epoch": 0.462997636514319, + "grad_norm": 0.7818812905420544, + "learning_rate": 1.1676182368760573e-05, + "loss": 0.8978, + "step": 7542 + }, + { + "epoch": 0.4630590257527855, + "grad_norm": 0.7399615316504612, + "learning_rate": 1.1674222117070774e-05, + "loss": 0.9265, + "step": 7543 + }, + { + "epoch": 0.46312041499125206, + "grad_norm": 0.8256320250810827, + "learning_rate": 1.1672261799190026e-05, + "loss": 0.8654, + "step": 7544 + }, + { + "epoch": 0.46318180422971855, + "grad_norm": 0.752137030128421, + "learning_rate": 1.167030141519582e-05, + "loss": 0.8822, + "step": 7545 + }, + { + "epoch": 0.46324319346818504, + "grad_norm": 0.7201843284507333, + "learning_rate": 1.166834096516567e-05, + "loss": 0.8909, + "step": 7546 + }, + { + "epoch": 0.46330458270665154, + "grad_norm": 0.7751861397054958, + "learning_rate": 1.1666380449177073e-05, + "loss": 0.8917, + "step": 7547 + }, + { + "epoch": 0.463365971945118, + "grad_norm": 0.838029932136675, + "learning_rate": 1.1664419867307548e-05, + "loss": 0.9026, + "step": 7548 + }, + { + "epoch": 0.4634273611835845, + "grad_norm": 0.8123768933368958, + "learning_rate": 1.1662459219634603e-05, + "loss": 0.9004, + "step": 7549 + }, + { + "epoch": 0.463488750422051, + "grad_norm": 0.7543880794803738, + "learning_rate": 1.1660498506235754e-05, + "loss": 0.8465, + "step": 7550 + }, + { + "epoch": 0.4635501396605175, + "grad_norm": 0.7229559315156436, + "learning_rate": 1.1658537727188519e-05, + "loss": 0.8269, + "step": 7551 + }, + { + "epoch": 0.463611528898984, + "grad_norm": 0.7996242479553077, + "learning_rate": 1.1656576882570413e-05, + "loss": 0.8996, + "step": 7552 + }, + { + "epoch": 0.4636729181374505, + "grad_norm": 0.7557409604476935, + "learning_rate": 1.1654615972458968e-05, + "loss": 0.8693, + "step": 7553 + }, + { + "epoch": 0.463734307375917, + "grad_norm": 0.7991474284853051, + "learning_rate": 1.16526549969317e-05, + "loss": 0.8248, + "step": 7554 + }, + { + "epoch": 0.4637956966143835, + "grad_norm": 0.7377023447681629, + "learning_rate": 1.1650693956066146e-05, + "loss": 0.8697, + "step": 7555 + }, + { + "epoch": 0.46385708585285, + "grad_norm": 0.8005729148688826, + "learning_rate": 1.1648732849939827e-05, + "loss": 0.8756, + "step": 7556 + }, + { + "epoch": 0.4639184750913165, + "grad_norm": 0.7629486867787765, + "learning_rate": 1.164677167863028e-05, + "loss": 0.8769, + "step": 7557 + }, + { + "epoch": 0.463979864329783, + "grad_norm": 0.7953319602629569, + "learning_rate": 1.1644810442215044e-05, + "loss": 0.8636, + "step": 7558 + }, + { + "epoch": 0.4640412535682495, + "grad_norm": 0.7111988108341877, + "learning_rate": 1.1642849140771653e-05, + "loss": 0.8976, + "step": 7559 + }, + { + "epoch": 0.464102642806716, + "grad_norm": 0.762338953573442, + "learning_rate": 1.164088777437765e-05, + "loss": 0.9019, + "step": 7560 + }, + { + "epoch": 0.4641640320451825, + "grad_norm": 0.7343959681274369, + "learning_rate": 1.1638926343110574e-05, + "loss": 0.8603, + "step": 7561 + }, + { + "epoch": 0.46422542128364896, + "grad_norm": 0.7437355486499109, + "learning_rate": 1.1636964847047976e-05, + "loss": 0.8588, + "step": 7562 + }, + { + "epoch": 0.46428681052211546, + "grad_norm": 0.71028859810141, + "learning_rate": 1.1635003286267403e-05, + "loss": 0.834, + "step": 7563 + }, + { + "epoch": 0.46434819976058195, + "grad_norm": 0.7528001589148839, + "learning_rate": 1.1633041660846405e-05, + "loss": 0.8598, + "step": 7564 + }, + { + "epoch": 0.46440958899904844, + "grad_norm": 0.7976501024007132, + "learning_rate": 1.1631079970862536e-05, + "loss": 0.848, + "step": 7565 + }, + { + "epoch": 0.464470978237515, + "grad_norm": 0.7277343815201363, + "learning_rate": 1.1629118216393351e-05, + "loss": 0.8964, + "step": 7566 + }, + { + "epoch": 0.4645323674759815, + "grad_norm": 0.741299900196914, + "learning_rate": 1.1627156397516412e-05, + "loss": 0.8669, + "step": 7567 + }, + { + "epoch": 0.46459375671444797, + "grad_norm": 0.8048525858630637, + "learning_rate": 1.1625194514309277e-05, + "loss": 0.8514, + "step": 7568 + }, + { + "epoch": 0.46465514595291446, + "grad_norm": 0.7425251204269625, + "learning_rate": 1.1623232566849512e-05, + "loss": 0.8717, + "step": 7569 + }, + { + "epoch": 0.46471653519138095, + "grad_norm": 0.7438141203805285, + "learning_rate": 1.1621270555214677e-05, + "loss": 0.8667, + "step": 7570 + }, + { + "epoch": 0.46477792442984744, + "grad_norm": 0.7810835860189996, + "learning_rate": 1.1619308479482352e-05, + "loss": 0.9236, + "step": 7571 + }, + { + "epoch": 0.46483931366831394, + "grad_norm": 0.6768542936308484, + "learning_rate": 1.1617346339730098e-05, + "loss": 0.8403, + "step": 7572 + }, + { + "epoch": 0.4649007029067804, + "grad_norm": 0.8255278977940862, + "learning_rate": 1.1615384136035494e-05, + "loss": 0.8597, + "step": 7573 + }, + { + "epoch": 0.4649620921452469, + "grad_norm": 0.8206384422161174, + "learning_rate": 1.1613421868476115e-05, + "loss": 0.8651, + "step": 7574 + }, + { + "epoch": 0.4650234813837134, + "grad_norm": 0.7109631745198666, + "learning_rate": 1.1611459537129542e-05, + "loss": 0.8651, + "step": 7575 + }, + { + "epoch": 0.46508487062217996, + "grad_norm": 0.7627053071584906, + "learning_rate": 1.1609497142073356e-05, + "loss": 0.8034, + "step": 7576 + }, + { + "epoch": 0.46514625986064645, + "grad_norm": 0.809073070328644, + "learning_rate": 1.1607534683385135e-05, + "loss": 0.8766, + "step": 7577 + }, + { + "epoch": 0.46520764909911294, + "grad_norm": 0.7470397107136545, + "learning_rate": 1.1605572161142475e-05, + "loss": 0.8465, + "step": 7578 + }, + { + "epoch": 0.46526903833757943, + "grad_norm": 0.7370665218864719, + "learning_rate": 1.1603609575422959e-05, + "loss": 0.8674, + "step": 7579 + }, + { + "epoch": 0.4653304275760459, + "grad_norm": 0.7886206311691056, + "learning_rate": 1.1601646926304177e-05, + "loss": 0.8522, + "step": 7580 + }, + { + "epoch": 0.4653918168145124, + "grad_norm": 0.8146374416164418, + "learning_rate": 1.1599684213863728e-05, + "loss": 0.8967, + "step": 7581 + }, + { + "epoch": 0.4654532060529789, + "grad_norm": 0.8250313612301822, + "learning_rate": 1.1597721438179205e-05, + "loss": 0.9258, + "step": 7582 + }, + { + "epoch": 0.4655145952914454, + "grad_norm": 0.7084858098986264, + "learning_rate": 1.1595758599328213e-05, + "loss": 0.8138, + "step": 7583 + }, + { + "epoch": 0.4655759845299119, + "grad_norm": 0.7415600449589995, + "learning_rate": 1.1593795697388343e-05, + "loss": 0.8126, + "step": 7584 + }, + { + "epoch": 0.4656373737683784, + "grad_norm": 0.7331272097310799, + "learning_rate": 1.159183273243721e-05, + "loss": 0.8209, + "step": 7585 + }, + { + "epoch": 0.4656987630068449, + "grad_norm": 0.7656110807024621, + "learning_rate": 1.158986970455241e-05, + "loss": 0.8903, + "step": 7586 + }, + { + "epoch": 0.4657601522453114, + "grad_norm": 0.7636888494363725, + "learning_rate": 1.158790661381156e-05, + "loss": 0.9269, + "step": 7587 + }, + { + "epoch": 0.4658215414837779, + "grad_norm": 0.7153387874450545, + "learning_rate": 1.158594346029227e-05, + "loss": 0.8589, + "step": 7588 + }, + { + "epoch": 0.4658829307222444, + "grad_norm": 0.7727129268345152, + "learning_rate": 1.158398024407215e-05, + "loss": 0.9018, + "step": 7589 + }, + { + "epoch": 0.4659443199607109, + "grad_norm": 0.7575613530927757, + "learning_rate": 1.1582016965228823e-05, + "loss": 0.8752, + "step": 7590 + }, + { + "epoch": 0.4660057091991774, + "grad_norm": 0.7432946671936305, + "learning_rate": 1.15800536238399e-05, + "loss": 0.835, + "step": 7591 + }, + { + "epoch": 0.4660670984376439, + "grad_norm": 0.7482247907434718, + "learning_rate": 1.157809021998301e-05, + "loss": 0.8565, + "step": 7592 + }, + { + "epoch": 0.46612848767611037, + "grad_norm": 0.7190625829171073, + "learning_rate": 1.1576126753735772e-05, + "loss": 0.8463, + "step": 7593 + }, + { + "epoch": 0.46618987691457686, + "grad_norm": 0.7158685742644109, + "learning_rate": 1.1574163225175814e-05, + "loss": 0.8271, + "step": 7594 + }, + { + "epoch": 0.46625126615304335, + "grad_norm": 0.7768616966780206, + "learning_rate": 1.1572199634380763e-05, + "loss": 0.8703, + "step": 7595 + }, + { + "epoch": 0.46631265539150984, + "grad_norm": 0.7064261787818129, + "learning_rate": 1.1570235981428252e-05, + "loss": 0.8947, + "step": 7596 + }, + { + "epoch": 0.4663740446299764, + "grad_norm": 0.7288702708873219, + "learning_rate": 1.1568272266395915e-05, + "loss": 0.8442, + "step": 7597 + }, + { + "epoch": 0.4664354338684429, + "grad_norm": 0.8074613730979113, + "learning_rate": 1.1566308489361388e-05, + "loss": 0.9241, + "step": 7598 + }, + { + "epoch": 0.4664968231069094, + "grad_norm": 0.6366522435283225, + "learning_rate": 1.156434465040231e-05, + "loss": 0.6968, + "step": 7599 + }, + { + "epoch": 0.46655821234537587, + "grad_norm": 0.5686123571759175, + "learning_rate": 1.156238074959632e-05, + "loss": 0.6818, + "step": 7600 + }, + { + "epoch": 0.46661960158384236, + "grad_norm": 0.8215959326127904, + "learning_rate": 1.1560416787021065e-05, + "loss": 0.9225, + "step": 7601 + }, + { + "epoch": 0.46668099082230885, + "grad_norm": 0.7389201132948356, + "learning_rate": 1.1558452762754184e-05, + "loss": 0.8481, + "step": 7602 + }, + { + "epoch": 0.46674238006077534, + "grad_norm": 0.791679721626058, + "learning_rate": 1.1556488676873336e-05, + "loss": 0.8988, + "step": 7603 + }, + { + "epoch": 0.46680376929924183, + "grad_norm": 0.7642046071509483, + "learning_rate": 1.1554524529456162e-05, + "loss": 0.8868, + "step": 7604 + }, + { + "epoch": 0.4668651585377083, + "grad_norm": 0.7854551626265899, + "learning_rate": 1.155256032058032e-05, + "loss": 0.8385, + "step": 7605 + }, + { + "epoch": 0.4669265477761748, + "grad_norm": 0.7492334086388197, + "learning_rate": 1.1550596050323464e-05, + "loss": 0.839, + "step": 7606 + }, + { + "epoch": 0.4669879370146413, + "grad_norm": 0.7981955443632488, + "learning_rate": 1.1548631718763253e-05, + "loss": 0.9097, + "step": 7607 + }, + { + "epoch": 0.46704932625310785, + "grad_norm": 0.7737450387818472, + "learning_rate": 1.154666732597735e-05, + "loss": 0.8919, + "step": 7608 + }, + { + "epoch": 0.46711071549157435, + "grad_norm": 0.7468698983113123, + "learning_rate": 1.1544702872043411e-05, + "loss": 0.8667, + "step": 7609 + }, + { + "epoch": 0.46717210473004084, + "grad_norm": 0.7224033909960983, + "learning_rate": 1.1542738357039111e-05, + "loss": 0.8524, + "step": 7610 + }, + { + "epoch": 0.46723349396850733, + "grad_norm": 0.7433501498221031, + "learning_rate": 1.1540773781042109e-05, + "loss": 0.8303, + "step": 7611 + }, + { + "epoch": 0.4672948832069738, + "grad_norm": 0.7679430645587051, + "learning_rate": 1.1538809144130081e-05, + "loss": 0.8808, + "step": 7612 + }, + { + "epoch": 0.4673562724454403, + "grad_norm": 0.8521600006160716, + "learning_rate": 1.1536844446380698e-05, + "loss": 0.8715, + "step": 7613 + }, + { + "epoch": 0.4674176616839068, + "grad_norm": 0.7770340652001775, + "learning_rate": 1.1534879687871629e-05, + "loss": 0.889, + "step": 7614 + }, + { + "epoch": 0.4674790509223733, + "grad_norm": 0.75366991272358, + "learning_rate": 1.1532914868680564e-05, + "loss": 0.8712, + "step": 7615 + }, + { + "epoch": 0.4675404401608398, + "grad_norm": 0.736334445014511, + "learning_rate": 1.153094998888517e-05, + "loss": 0.8593, + "step": 7616 + }, + { + "epoch": 0.4676018293993063, + "grad_norm": 0.8091101831315318, + "learning_rate": 1.152898504856314e-05, + "loss": 0.8847, + "step": 7617 + }, + { + "epoch": 0.46766321863777277, + "grad_norm": 0.7697052565097029, + "learning_rate": 1.1527020047792148e-05, + "loss": 0.8372, + "step": 7618 + }, + { + "epoch": 0.4677246078762393, + "grad_norm": 0.8362282001384448, + "learning_rate": 1.1525054986649891e-05, + "loss": 0.892, + "step": 7619 + }, + { + "epoch": 0.4677859971147058, + "grad_norm": 0.6931282361830157, + "learning_rate": 1.152308986521405e-05, + "loss": 0.8569, + "step": 7620 + }, + { + "epoch": 0.4678473863531723, + "grad_norm": 0.7297644671330235, + "learning_rate": 1.1521124683562322e-05, + "loss": 0.8574, + "step": 7621 + }, + { + "epoch": 0.4679087755916388, + "grad_norm": 0.7803602656194065, + "learning_rate": 1.1519159441772403e-05, + "loss": 0.8915, + "step": 7622 + }, + { + "epoch": 0.4679701648301053, + "grad_norm": 0.7985386578612301, + "learning_rate": 1.1517194139921981e-05, + "loss": 0.9393, + "step": 7623 + }, + { + "epoch": 0.4680315540685718, + "grad_norm": 0.730453641603195, + "learning_rate": 1.1515228778088763e-05, + "loss": 0.8904, + "step": 7624 + }, + { + "epoch": 0.46809294330703827, + "grad_norm": 0.8128202670512834, + "learning_rate": 1.1513263356350446e-05, + "loss": 0.8782, + "step": 7625 + }, + { + "epoch": 0.46815433254550476, + "grad_norm": 0.7513922167289865, + "learning_rate": 1.1511297874784738e-05, + "loss": 0.9018, + "step": 7626 + }, + { + "epoch": 0.46821572178397125, + "grad_norm": 0.7725705981138815, + "learning_rate": 1.1509332333469339e-05, + "loss": 0.8608, + "step": 7627 + }, + { + "epoch": 0.46827711102243774, + "grad_norm": 0.7567149542029078, + "learning_rate": 1.150736673248196e-05, + "loss": 0.855, + "step": 7628 + }, + { + "epoch": 0.4683385002609043, + "grad_norm": 0.6629599656863869, + "learning_rate": 1.1505401071900313e-05, + "loss": 0.8135, + "step": 7629 + }, + { + "epoch": 0.4683998894993708, + "grad_norm": 0.7599402795471658, + "learning_rate": 1.150343535180211e-05, + "loss": 0.856, + "step": 7630 + }, + { + "epoch": 0.4684612787378373, + "grad_norm": 0.7298604470273483, + "learning_rate": 1.1501469572265066e-05, + "loss": 0.8944, + "step": 7631 + }, + { + "epoch": 0.46852266797630376, + "grad_norm": 0.8563612823035229, + "learning_rate": 1.1499503733366903e-05, + "loss": 0.8992, + "step": 7632 + }, + { + "epoch": 0.46858405721477026, + "grad_norm": 0.7705170189547937, + "learning_rate": 1.1497537835185336e-05, + "loss": 0.9162, + "step": 7633 + }, + { + "epoch": 0.46864544645323675, + "grad_norm": 0.7276698157277433, + "learning_rate": 1.1495571877798086e-05, + "loss": 0.849, + "step": 7634 + }, + { + "epoch": 0.46870683569170324, + "grad_norm": 0.8851310280596155, + "learning_rate": 1.1493605861282882e-05, + "loss": 0.8868, + "step": 7635 + }, + { + "epoch": 0.46876822493016973, + "grad_norm": 0.7261658001919157, + "learning_rate": 1.1491639785717452e-05, + "loss": 0.8252, + "step": 7636 + }, + { + "epoch": 0.4688296141686362, + "grad_norm": 0.7611141637783825, + "learning_rate": 1.1489673651179523e-05, + "loss": 0.8503, + "step": 7637 + }, + { + "epoch": 0.4688910034071027, + "grad_norm": 0.7662387017007319, + "learning_rate": 1.1487707457746826e-05, + "loss": 0.8826, + "step": 7638 + }, + { + "epoch": 0.4689523926455692, + "grad_norm": 0.8133510766924799, + "learning_rate": 1.1485741205497094e-05, + "loss": 0.9162, + "step": 7639 + }, + { + "epoch": 0.46901378188403575, + "grad_norm": 0.7133158822939181, + "learning_rate": 1.148377489450807e-05, + "loss": 0.8434, + "step": 7640 + }, + { + "epoch": 0.46907517112250224, + "grad_norm": 0.7240057598237175, + "learning_rate": 1.1481808524857487e-05, + "loss": 0.8614, + "step": 7641 + }, + { + "epoch": 0.46913656036096874, + "grad_norm": 0.6539392847235568, + "learning_rate": 1.1479842096623091e-05, + "loss": 0.8133, + "step": 7642 + }, + { + "epoch": 0.4691979495994352, + "grad_norm": 0.6665876781152306, + "learning_rate": 1.1477875609882617e-05, + "loss": 0.8536, + "step": 7643 + }, + { + "epoch": 0.4692593388379017, + "grad_norm": 0.7402429255579384, + "learning_rate": 1.1475909064713818e-05, + "loss": 0.8895, + "step": 7644 + }, + { + "epoch": 0.4693207280763682, + "grad_norm": 0.7596654053777551, + "learning_rate": 1.147394246119444e-05, + "loss": 0.8667, + "step": 7645 + }, + { + "epoch": 0.4693821173148347, + "grad_norm": 0.765138232319007, + "learning_rate": 1.1471975799402233e-05, + "loss": 0.9045, + "step": 7646 + }, + { + "epoch": 0.4694435065533012, + "grad_norm": 0.7659973346620677, + "learning_rate": 1.1470009079414953e-05, + "loss": 0.8438, + "step": 7647 + }, + { + "epoch": 0.4695048957917677, + "grad_norm": 0.8140970817038885, + "learning_rate": 1.1468042301310347e-05, + "loss": 0.8944, + "step": 7648 + }, + { + "epoch": 0.4695662850302342, + "grad_norm": 0.8885296197755467, + "learning_rate": 1.1466075465166182e-05, + "loss": 0.8846, + "step": 7649 + }, + { + "epoch": 0.4696276742687007, + "grad_norm": 0.8322191966900487, + "learning_rate": 1.1464108571060209e-05, + "loss": 0.8985, + "step": 7650 + }, + { + "epoch": 0.4696890635071672, + "grad_norm": 0.7669001030654022, + "learning_rate": 1.1462141619070193e-05, + "loss": 0.8774, + "step": 7651 + }, + { + "epoch": 0.4697504527456337, + "grad_norm": 0.7149884410357005, + "learning_rate": 1.1460174609273902e-05, + "loss": 0.8587, + "step": 7652 + }, + { + "epoch": 0.4698118419841002, + "grad_norm": 0.7324021491253158, + "learning_rate": 1.1458207541749096e-05, + "loss": 0.8259, + "step": 7653 + }, + { + "epoch": 0.4698732312225667, + "grad_norm": 0.8029860101061472, + "learning_rate": 1.145624041657355e-05, + "loss": 0.8481, + "step": 7654 + }, + { + "epoch": 0.4699346204610332, + "grad_norm": 0.6802716393186043, + "learning_rate": 1.1454273233825028e-05, + "loss": 0.8198, + "step": 7655 + }, + { + "epoch": 0.4699960096994997, + "grad_norm": 0.7149908179859105, + "learning_rate": 1.145230599358131e-05, + "loss": 0.8608, + "step": 7656 + }, + { + "epoch": 0.47005739893796616, + "grad_norm": 0.6883404096218982, + "learning_rate": 1.1450338695920169e-05, + "loss": 0.8855, + "step": 7657 + }, + { + "epoch": 0.47011878817643266, + "grad_norm": 0.8047532950195676, + "learning_rate": 1.144837134091938e-05, + "loss": 0.9001, + "step": 7658 + }, + { + "epoch": 0.47018017741489915, + "grad_norm": 0.7539363744998897, + "learning_rate": 1.144640392865673e-05, + "loss": 0.8959, + "step": 7659 + }, + { + "epoch": 0.47024156665336564, + "grad_norm": 0.8321497560722936, + "learning_rate": 1.1444436459209988e-05, + "loss": 0.8267, + "step": 7660 + }, + { + "epoch": 0.4703029558918322, + "grad_norm": 0.7677153462032985, + "learning_rate": 1.1442468932656957e-05, + "loss": 0.9099, + "step": 7661 + }, + { + "epoch": 0.4703643451302987, + "grad_norm": 0.7889774350015829, + "learning_rate": 1.1440501349075408e-05, + "loss": 0.8387, + "step": 7662 + }, + { + "epoch": 0.47042573436876517, + "grad_norm": 0.7828417312920335, + "learning_rate": 1.1438533708543141e-05, + "loss": 0.8135, + "step": 7663 + }, + { + "epoch": 0.47048712360723166, + "grad_norm": 0.7478319000927369, + "learning_rate": 1.143656601113794e-05, + "loss": 0.879, + "step": 7664 + }, + { + "epoch": 0.47054851284569815, + "grad_norm": 0.7729063122734173, + "learning_rate": 1.14345982569376e-05, + "loss": 0.8153, + "step": 7665 + }, + { + "epoch": 0.47060990208416464, + "grad_norm": 0.8573533710238835, + "learning_rate": 1.1432630446019918e-05, + "loss": 0.86, + "step": 7666 + }, + { + "epoch": 0.47067129132263114, + "grad_norm": 0.7590556712142424, + "learning_rate": 1.1430662578462694e-05, + "loss": 0.838, + "step": 7667 + }, + { + "epoch": 0.4707326805610976, + "grad_norm": 0.7175170397762369, + "learning_rate": 1.1428694654343726e-05, + "loss": 0.8131, + "step": 7668 + }, + { + "epoch": 0.4707940697995641, + "grad_norm": 0.8275598110858471, + "learning_rate": 1.1426726673740817e-05, + "loss": 0.8839, + "step": 7669 + }, + { + "epoch": 0.4708554590380306, + "grad_norm": 0.772536059727323, + "learning_rate": 1.1424758636731774e-05, + "loss": 0.8425, + "step": 7670 + }, + { + "epoch": 0.47091684827649716, + "grad_norm": 0.8201144865026263, + "learning_rate": 1.14227905433944e-05, + "loss": 0.9017, + "step": 7671 + }, + { + "epoch": 0.47097823751496365, + "grad_norm": 0.7787461450677753, + "learning_rate": 1.1420822393806508e-05, + "loss": 0.8793, + "step": 7672 + }, + { + "epoch": 0.47103962675343014, + "grad_norm": 0.7984418682048353, + "learning_rate": 1.1418854188045904e-05, + "loss": 0.8445, + "step": 7673 + }, + { + "epoch": 0.47110101599189663, + "grad_norm": 0.8780251528362931, + "learning_rate": 1.1416885926190409e-05, + "loss": 0.8615, + "step": 7674 + }, + { + "epoch": 0.4711624052303631, + "grad_norm": 0.7260070726908675, + "learning_rate": 1.1414917608317832e-05, + "loss": 0.8501, + "step": 7675 + }, + { + "epoch": 0.4712237944688296, + "grad_norm": 0.7771626034928578, + "learning_rate": 1.1412949234505999e-05, + "loss": 0.9099, + "step": 7676 + }, + { + "epoch": 0.4712851837072961, + "grad_norm": 0.7285476112440764, + "learning_rate": 1.1410980804832722e-05, + "loss": 0.8625, + "step": 7677 + }, + { + "epoch": 0.4713465729457626, + "grad_norm": 0.7641837057057606, + "learning_rate": 1.1409012319375828e-05, + "loss": 0.8375, + "step": 7678 + }, + { + "epoch": 0.4714079621842291, + "grad_norm": 0.7614984065495675, + "learning_rate": 1.1407043778213142e-05, + "loss": 0.8761, + "step": 7679 + }, + { + "epoch": 0.4714693514226956, + "grad_norm": 0.7423981465241772, + "learning_rate": 1.1405075181422489e-05, + "loss": 0.867, + "step": 7680 + }, + { + "epoch": 0.4715307406611621, + "grad_norm": 0.720466528728775, + "learning_rate": 1.14031065290817e-05, + "loss": 0.8395, + "step": 7681 + }, + { + "epoch": 0.4715921298996286, + "grad_norm": 0.8621272874138802, + "learning_rate": 1.1401137821268607e-05, + "loss": 0.9122, + "step": 7682 + }, + { + "epoch": 0.4716535191380951, + "grad_norm": 0.7499951126756137, + "learning_rate": 1.139916905806104e-05, + "loss": 0.8346, + "step": 7683 + }, + { + "epoch": 0.4717149083765616, + "grad_norm": 0.8620997413105865, + "learning_rate": 1.1397200239536836e-05, + "loss": 0.9136, + "step": 7684 + }, + { + "epoch": 0.4717762976150281, + "grad_norm": 0.7731707402728834, + "learning_rate": 1.1395231365773833e-05, + "loss": 0.8945, + "step": 7685 + }, + { + "epoch": 0.4718376868534946, + "grad_norm": 0.7481008925416273, + "learning_rate": 1.1393262436849876e-05, + "loss": 0.8354, + "step": 7686 + }, + { + "epoch": 0.4718990760919611, + "grad_norm": 0.8588635678804829, + "learning_rate": 1.13912934528428e-05, + "loss": 0.8972, + "step": 7687 + }, + { + "epoch": 0.47196046533042757, + "grad_norm": 0.8202029620092314, + "learning_rate": 1.1389324413830454e-05, + "loss": 0.9065, + "step": 7688 + }, + { + "epoch": 0.47202185456889406, + "grad_norm": 0.7318992319623148, + "learning_rate": 1.1387355319890685e-05, + "loss": 0.851, + "step": 7689 + }, + { + "epoch": 0.47208324380736055, + "grad_norm": 0.7609453420515186, + "learning_rate": 1.1385386171101338e-05, + "loss": 0.8719, + "step": 7690 + }, + { + "epoch": 0.47214463304582704, + "grad_norm": 0.7026582264989515, + "learning_rate": 1.1383416967540266e-05, + "loss": 0.8469, + "step": 7691 + }, + { + "epoch": 0.47220602228429354, + "grad_norm": 0.7568317261694892, + "learning_rate": 1.138144770928532e-05, + "loss": 0.8064, + "step": 7692 + }, + { + "epoch": 0.4722674115227601, + "grad_norm": 0.8551186639260655, + "learning_rate": 1.137947839641436e-05, + "loss": 0.9514, + "step": 7693 + }, + { + "epoch": 0.4723288007612266, + "grad_norm": 0.8166791104262353, + "learning_rate": 1.1377509029005243e-05, + "loss": 0.8782, + "step": 7694 + }, + { + "epoch": 0.47239018999969307, + "grad_norm": 0.6842696604213699, + "learning_rate": 1.1375539607135827e-05, + "loss": 0.8236, + "step": 7695 + }, + { + "epoch": 0.47245157923815956, + "grad_norm": 0.8107414308588786, + "learning_rate": 1.1373570130883968e-05, + "loss": 0.8803, + "step": 7696 + }, + { + "epoch": 0.47251296847662605, + "grad_norm": 0.851418761679186, + "learning_rate": 1.1371600600327538e-05, + "loss": 0.897, + "step": 7697 + }, + { + "epoch": 0.47257435771509254, + "grad_norm": 0.8983051494938715, + "learning_rate": 1.1369631015544402e-05, + "loss": 0.8851, + "step": 7698 + }, + { + "epoch": 0.47263574695355903, + "grad_norm": 0.8056921431902153, + "learning_rate": 1.1367661376612425e-05, + "loss": 0.8422, + "step": 7699 + }, + { + "epoch": 0.4726971361920255, + "grad_norm": 0.8165496093287716, + "learning_rate": 1.136569168360948e-05, + "loss": 0.8461, + "step": 7700 + }, + { + "epoch": 0.472758525430492, + "grad_norm": 0.809373223972153, + "learning_rate": 1.1363721936613439e-05, + "loss": 0.8551, + "step": 7701 + }, + { + "epoch": 0.4728199146689585, + "grad_norm": 0.746620499365757, + "learning_rate": 1.1361752135702175e-05, + "loss": 0.83, + "step": 7702 + }, + { + "epoch": 0.47288130390742505, + "grad_norm": 0.8137017986902388, + "learning_rate": 1.1359782280953564e-05, + "loss": 0.8499, + "step": 7703 + }, + { + "epoch": 0.47294269314589155, + "grad_norm": 0.799277023116157, + "learning_rate": 1.1357812372445492e-05, + "loss": 0.8927, + "step": 7704 + }, + { + "epoch": 0.47300408238435804, + "grad_norm": 0.7178966456259079, + "learning_rate": 1.1355842410255831e-05, + "loss": 0.8665, + "step": 7705 + }, + { + "epoch": 0.47306547162282453, + "grad_norm": 0.7727197581302411, + "learning_rate": 1.135387239446247e-05, + "loss": 0.837, + "step": 7706 + }, + { + "epoch": 0.473126860861291, + "grad_norm": 0.7084241831263223, + "learning_rate": 1.135190232514329e-05, + "loss": 0.8843, + "step": 7707 + }, + { + "epoch": 0.4731882500997575, + "grad_norm": 0.7992215188892275, + "learning_rate": 1.1349932202376182e-05, + "loss": 0.8388, + "step": 7708 + }, + { + "epoch": 0.473249639338224, + "grad_norm": 0.6656591663201382, + "learning_rate": 1.1347962026239032e-05, + "loss": 0.8108, + "step": 7709 + }, + { + "epoch": 0.4733110285766905, + "grad_norm": 0.7145535658456467, + "learning_rate": 1.1345991796809734e-05, + "loss": 0.8221, + "step": 7710 + }, + { + "epoch": 0.473372417815157, + "grad_norm": 0.7420113622705153, + "learning_rate": 1.1344021514166186e-05, + "loss": 0.8353, + "step": 7711 + }, + { + "epoch": 0.4734338070536235, + "grad_norm": 0.8244589772793475, + "learning_rate": 1.1342051178386276e-05, + "loss": 0.9265, + "step": 7712 + }, + { + "epoch": 0.47349519629208997, + "grad_norm": 0.7407353162387322, + "learning_rate": 1.1340080789547905e-05, + "loss": 0.8726, + "step": 7713 + }, + { + "epoch": 0.4735565855305565, + "grad_norm": 0.7271125991484315, + "learning_rate": 1.1338110347728973e-05, + "loss": 0.8831, + "step": 7714 + }, + { + "epoch": 0.473617974769023, + "grad_norm": 0.7314314080771306, + "learning_rate": 1.1336139853007382e-05, + "loss": 0.9066, + "step": 7715 + }, + { + "epoch": 0.4736793640074895, + "grad_norm": 0.737010735299934, + "learning_rate": 1.1334169305461037e-05, + "loss": 0.8504, + "step": 7716 + }, + { + "epoch": 0.473740753245956, + "grad_norm": 0.6722238289475122, + "learning_rate": 1.1332198705167843e-05, + "loss": 0.8861, + "step": 7717 + }, + { + "epoch": 0.4738021424844225, + "grad_norm": 0.7234968478226361, + "learning_rate": 1.1330228052205712e-05, + "loss": 0.86, + "step": 7718 + }, + { + "epoch": 0.473863531722889, + "grad_norm": 0.6593881900107449, + "learning_rate": 1.1328257346652547e-05, + "loss": 0.6835, + "step": 7719 + }, + { + "epoch": 0.47392492096135547, + "grad_norm": 0.816666133916174, + "learning_rate": 1.1326286588586268e-05, + "loss": 0.8544, + "step": 7720 + }, + { + "epoch": 0.47398631019982196, + "grad_norm": 0.7601045128424191, + "learning_rate": 1.1324315778084788e-05, + "loss": 0.8249, + "step": 7721 + }, + { + "epoch": 0.47404769943828845, + "grad_norm": 0.695848697502685, + "learning_rate": 1.1322344915226018e-05, + "loss": 0.8538, + "step": 7722 + }, + { + "epoch": 0.47410908867675494, + "grad_norm": 0.7801316502055105, + "learning_rate": 1.1320374000087883e-05, + "loss": 0.8628, + "step": 7723 + }, + { + "epoch": 0.4741704779152215, + "grad_norm": 0.8270096235410596, + "learning_rate": 1.1318403032748303e-05, + "loss": 0.8489, + "step": 7724 + }, + { + "epoch": 0.474231867153688, + "grad_norm": 0.8162858390572112, + "learning_rate": 1.1316432013285198e-05, + "loss": 0.8773, + "step": 7725 + }, + { + "epoch": 0.47429325639215447, + "grad_norm": 0.8348532423034938, + "learning_rate": 1.1314460941776497e-05, + "loss": 0.8776, + "step": 7726 + }, + { + "epoch": 0.47435464563062096, + "grad_norm": 0.7758108900360123, + "learning_rate": 1.1312489818300123e-05, + "loss": 0.8186, + "step": 7727 + }, + { + "epoch": 0.47441603486908746, + "grad_norm": 0.7326162590929624, + "learning_rate": 1.131051864293401e-05, + "loss": 0.861, + "step": 7728 + }, + { + "epoch": 0.47447742410755395, + "grad_norm": 0.7509657262926291, + "learning_rate": 1.1308547415756084e-05, + "loss": 0.7894, + "step": 7729 + }, + { + "epoch": 0.47453881334602044, + "grad_norm": 0.827976319218649, + "learning_rate": 1.1306576136844277e-05, + "loss": 0.8795, + "step": 7730 + }, + { + "epoch": 0.47460020258448693, + "grad_norm": 0.7368590746020545, + "learning_rate": 1.1304604806276528e-05, + "loss": 0.8135, + "step": 7731 + }, + { + "epoch": 0.4746615918229534, + "grad_norm": 0.701620236761841, + "learning_rate": 1.1302633424130779e-05, + "loss": 0.8303, + "step": 7732 + }, + { + "epoch": 0.4747229810614199, + "grad_norm": 0.76040247502634, + "learning_rate": 1.1300661990484958e-05, + "loss": 0.884, + "step": 7733 + }, + { + "epoch": 0.4747843702998864, + "grad_norm": 0.809293780691845, + "learning_rate": 1.1298690505417014e-05, + "loss": 0.8283, + "step": 7734 + }, + { + "epoch": 0.47484575953835295, + "grad_norm": 0.7977525293739557, + "learning_rate": 1.1296718969004888e-05, + "loss": 0.8837, + "step": 7735 + }, + { + "epoch": 0.47490714877681944, + "grad_norm": 0.8179123167951697, + "learning_rate": 1.1294747381326527e-05, + "loss": 0.8926, + "step": 7736 + }, + { + "epoch": 0.47496853801528593, + "grad_norm": 0.7997691671824249, + "learning_rate": 1.1292775742459875e-05, + "loss": 0.8694, + "step": 7737 + }, + { + "epoch": 0.4750299272537524, + "grad_norm": 0.5995864469780879, + "learning_rate": 1.1290804052482886e-05, + "loss": 0.6773, + "step": 7738 + }, + { + "epoch": 0.4750913164922189, + "grad_norm": 0.7990775866332139, + "learning_rate": 1.1288832311473507e-05, + "loss": 0.8376, + "step": 7739 + }, + { + "epoch": 0.4751527057306854, + "grad_norm": 0.75384326890518, + "learning_rate": 1.1286860519509697e-05, + "loss": 0.859, + "step": 7740 + }, + { + "epoch": 0.4752140949691519, + "grad_norm": 0.8040595119793896, + "learning_rate": 1.1284888676669405e-05, + "loss": 0.9344, + "step": 7741 + }, + { + "epoch": 0.4752754842076184, + "grad_norm": 0.6947006404062596, + "learning_rate": 1.1282916783030591e-05, + "loss": 0.8453, + "step": 7742 + }, + { + "epoch": 0.4753368734460849, + "grad_norm": 0.726302449853418, + "learning_rate": 1.1280944838671219e-05, + "loss": 0.8531, + "step": 7743 + }, + { + "epoch": 0.4753982626845514, + "grad_norm": 0.7346894752008978, + "learning_rate": 1.1278972843669242e-05, + "loss": 0.8697, + "step": 7744 + }, + { + "epoch": 0.47545965192301787, + "grad_norm": 0.7096637488007811, + "learning_rate": 1.1277000798102631e-05, + "loss": 0.8704, + "step": 7745 + }, + { + "epoch": 0.4755210411614844, + "grad_norm": 0.7518072888527491, + "learning_rate": 1.1275028702049348e-05, + "loss": 0.8351, + "step": 7746 + }, + { + "epoch": 0.4755824303999509, + "grad_norm": 0.7882491572445388, + "learning_rate": 1.127305655558736e-05, + "loss": 0.853, + "step": 7747 + }, + { + "epoch": 0.4756438196384174, + "grad_norm": 0.7725614415679053, + "learning_rate": 1.127108435879464e-05, + "loss": 0.8593, + "step": 7748 + }, + { + "epoch": 0.4757052088768839, + "grad_norm": 0.7387515228000735, + "learning_rate": 1.1269112111749155e-05, + "loss": 0.8256, + "step": 7749 + }, + { + "epoch": 0.4757665981153504, + "grad_norm": 0.7876099044784053, + "learning_rate": 1.1267139814528882e-05, + "loss": 0.9714, + "step": 7750 + }, + { + "epoch": 0.4758279873538169, + "grad_norm": 0.7893943513653512, + "learning_rate": 1.1265167467211793e-05, + "loss": 0.8625, + "step": 7751 + }, + { + "epoch": 0.47588937659228336, + "grad_norm": 0.749076704651459, + "learning_rate": 1.1263195069875867e-05, + "loss": 0.8108, + "step": 7752 + }, + { + "epoch": 0.47595076583074986, + "grad_norm": 0.8187177443668322, + "learning_rate": 1.1261222622599086e-05, + "loss": 0.9279, + "step": 7753 + }, + { + "epoch": 0.47601215506921635, + "grad_norm": 0.7180128408787056, + "learning_rate": 1.1259250125459429e-05, + "loss": 0.8503, + "step": 7754 + }, + { + "epoch": 0.47607354430768284, + "grad_norm": 0.7515709792120048, + "learning_rate": 1.125727757853488e-05, + "loss": 0.8608, + "step": 7755 + }, + { + "epoch": 0.4761349335461494, + "grad_norm": 0.6587659145755327, + "learning_rate": 1.1255304981903418e-05, + "loss": 0.8406, + "step": 7756 + }, + { + "epoch": 0.4761963227846159, + "grad_norm": 0.7604196070495094, + "learning_rate": 1.1253332335643043e-05, + "loss": 0.8946, + "step": 7757 + }, + { + "epoch": 0.47625771202308237, + "grad_norm": 0.8182772051152681, + "learning_rate": 1.1251359639831736e-05, + "loss": 0.9002, + "step": 7758 + }, + { + "epoch": 0.47631910126154886, + "grad_norm": 0.7636210289277774, + "learning_rate": 1.1249386894547489e-05, + "loss": 0.908, + "step": 7759 + }, + { + "epoch": 0.47638049050001535, + "grad_norm": 0.7525051960212104, + "learning_rate": 1.1247414099868297e-05, + "loss": 0.8204, + "step": 7760 + }, + { + "epoch": 0.47644187973848184, + "grad_norm": 0.8426810110767705, + "learning_rate": 1.1245441255872154e-05, + "loss": 0.9452, + "step": 7761 + }, + { + "epoch": 0.47650326897694834, + "grad_norm": 0.8286572517424428, + "learning_rate": 1.1243468362637055e-05, + "loss": 0.8776, + "step": 7762 + }, + { + "epoch": 0.4765646582154148, + "grad_norm": 0.7069482817584121, + "learning_rate": 1.1241495420241003e-05, + "loss": 0.884, + "step": 7763 + }, + { + "epoch": 0.4766260474538813, + "grad_norm": 0.8319076649475675, + "learning_rate": 1.1239522428761996e-05, + "loss": 0.8493, + "step": 7764 + }, + { + "epoch": 0.4766874366923478, + "grad_norm": 0.8147558023251379, + "learning_rate": 1.1237549388278039e-05, + "loss": 0.8638, + "step": 7765 + }, + { + "epoch": 0.4767488259308143, + "grad_norm": 0.730712640137976, + "learning_rate": 1.1235576298867135e-05, + "loss": 0.8113, + "step": 7766 + }, + { + "epoch": 0.47681021516928085, + "grad_norm": 0.8156261141248907, + "learning_rate": 1.123360316060729e-05, + "loss": 0.8615, + "step": 7767 + }, + { + "epoch": 0.47687160440774734, + "grad_norm": 0.7138155304250234, + "learning_rate": 1.1231629973576519e-05, + "loss": 0.8482, + "step": 7768 + }, + { + "epoch": 0.47693299364621383, + "grad_norm": 0.8154733675490069, + "learning_rate": 1.1229656737852823e-05, + "loss": 0.8721, + "step": 7769 + }, + { + "epoch": 0.4769943828846803, + "grad_norm": 0.8300739617307027, + "learning_rate": 1.1227683453514223e-05, + "loss": 0.9401, + "step": 7770 + }, + { + "epoch": 0.4770557721231468, + "grad_norm": 0.7515260748097056, + "learning_rate": 1.1225710120638726e-05, + "loss": 0.8476, + "step": 7771 + }, + { + "epoch": 0.4771171613616133, + "grad_norm": 0.7075002596320762, + "learning_rate": 1.1223736739304354e-05, + "loss": 0.8279, + "step": 7772 + }, + { + "epoch": 0.4771785506000798, + "grad_norm": 0.7177776680576233, + "learning_rate": 1.1221763309589126e-05, + "loss": 0.841, + "step": 7773 + }, + { + "epoch": 0.4772399398385463, + "grad_norm": 0.7473457785638514, + "learning_rate": 1.1219789831571058e-05, + "loss": 0.8445, + "step": 7774 + }, + { + "epoch": 0.4773013290770128, + "grad_norm": 0.7690163109549455, + "learning_rate": 1.1217816305328176e-05, + "loss": 0.8624, + "step": 7775 + }, + { + "epoch": 0.4773627183154793, + "grad_norm": 0.7098646195679497, + "learning_rate": 1.12158427309385e-05, + "loss": 0.8633, + "step": 7776 + }, + { + "epoch": 0.4774241075539458, + "grad_norm": 0.7691274228255045, + "learning_rate": 1.1213869108480058e-05, + "loss": 0.8632, + "step": 7777 + }, + { + "epoch": 0.4774854967924123, + "grad_norm": 0.7906975146551429, + "learning_rate": 1.121189543803088e-05, + "loss": 0.8163, + "step": 7778 + }, + { + "epoch": 0.4775468860308788, + "grad_norm": 0.8119774058490943, + "learning_rate": 1.1209921719668992e-05, + "loss": 0.8573, + "step": 7779 + }, + { + "epoch": 0.4776082752693453, + "grad_norm": 0.8254226464790018, + "learning_rate": 1.1207947953472427e-05, + "loss": 0.916, + "step": 7780 + }, + { + "epoch": 0.4776696645078118, + "grad_norm": 0.7461285680233162, + "learning_rate": 1.1205974139519218e-05, + "loss": 0.8652, + "step": 7781 + }, + { + "epoch": 0.4777310537462783, + "grad_norm": 0.8182237148101897, + "learning_rate": 1.1204000277887405e-05, + "loss": 0.9042, + "step": 7782 + }, + { + "epoch": 0.47779244298474477, + "grad_norm": 0.7448217352008042, + "learning_rate": 1.1202026368655017e-05, + "loss": 0.8522, + "step": 7783 + }, + { + "epoch": 0.47785383222321126, + "grad_norm": 0.6115856786851487, + "learning_rate": 1.12000524119001e-05, + "loss": 0.8195, + "step": 7784 + }, + { + "epoch": 0.47791522146167775, + "grad_norm": 0.7225548971388528, + "learning_rate": 1.1198078407700695e-05, + "loss": 0.8132, + "step": 7785 + }, + { + "epoch": 0.47797661070014424, + "grad_norm": 0.7326126184766445, + "learning_rate": 1.119610435613484e-05, + "loss": 0.848, + "step": 7786 + }, + { + "epoch": 0.47803799993861074, + "grad_norm": 0.7031180859597534, + "learning_rate": 1.1194130257280581e-05, + "loss": 0.8343, + "step": 7787 + }, + { + "epoch": 0.4780993891770773, + "grad_norm": 0.8172369815423787, + "learning_rate": 1.1192156111215969e-05, + "loss": 0.8926, + "step": 7788 + }, + { + "epoch": 0.4781607784155438, + "grad_norm": 0.8090544932709279, + "learning_rate": 1.119018191801905e-05, + "loss": 0.8761, + "step": 7789 + }, + { + "epoch": 0.47822216765401027, + "grad_norm": 0.7480656728071604, + "learning_rate": 1.1188207677767873e-05, + "loss": 0.899, + "step": 7790 + }, + { + "epoch": 0.47828355689247676, + "grad_norm": 0.7900048337467468, + "learning_rate": 1.1186233390540493e-05, + "loss": 0.8511, + "step": 7791 + }, + { + "epoch": 0.47834494613094325, + "grad_norm": 0.7463186309840197, + "learning_rate": 1.1184259056414961e-05, + "loss": 0.8181, + "step": 7792 + }, + { + "epoch": 0.47840633536940974, + "grad_norm": 0.6758457224673577, + "learning_rate": 1.1182284675469335e-05, + "loss": 0.7749, + "step": 7793 + }, + { + "epoch": 0.47846772460787623, + "grad_norm": 0.7628840939761017, + "learning_rate": 1.1180310247781672e-05, + "loss": 0.8517, + "step": 7794 + }, + { + "epoch": 0.4785291138463427, + "grad_norm": 0.8230450695463184, + "learning_rate": 1.1178335773430033e-05, + "loss": 0.9182, + "step": 7795 + }, + { + "epoch": 0.4785905030848092, + "grad_norm": 0.8225392967177559, + "learning_rate": 1.1176361252492478e-05, + "loss": 0.8995, + "step": 7796 + }, + { + "epoch": 0.4786518923232757, + "grad_norm": 0.7946948022981417, + "learning_rate": 1.1174386685047072e-05, + "loss": 0.8758, + "step": 7797 + }, + { + "epoch": 0.47871328156174225, + "grad_norm": 0.7693789143570285, + "learning_rate": 1.1172412071171878e-05, + "loss": 0.887, + "step": 7798 + }, + { + "epoch": 0.47877467080020875, + "grad_norm": 0.7458713128939956, + "learning_rate": 1.1170437410944965e-05, + "loss": 0.8227, + "step": 7799 + }, + { + "epoch": 0.47883606003867524, + "grad_norm": 0.815103611416231, + "learning_rate": 1.1168462704444404e-05, + "loss": 0.8361, + "step": 7800 + }, + { + "epoch": 0.47889744927714173, + "grad_norm": 0.7317132404024567, + "learning_rate": 1.116648795174826e-05, + "loss": 0.8386, + "step": 7801 + }, + { + "epoch": 0.4789588385156082, + "grad_norm": 0.7106972933115905, + "learning_rate": 1.116451315293461e-05, + "loss": 0.8233, + "step": 7802 + }, + { + "epoch": 0.4790202277540747, + "grad_norm": 0.7699307643614297, + "learning_rate": 1.1162538308081523e-05, + "loss": 0.8743, + "step": 7803 + }, + { + "epoch": 0.4790816169925412, + "grad_norm": 0.8104051528210945, + "learning_rate": 1.1160563417267081e-05, + "loss": 0.8926, + "step": 7804 + }, + { + "epoch": 0.4791430062310077, + "grad_norm": 0.783757881541956, + "learning_rate": 1.1158588480569363e-05, + "loss": 0.8563, + "step": 7805 + }, + { + "epoch": 0.4792043954694742, + "grad_norm": 0.7545608982861668, + "learning_rate": 1.1156613498066442e-05, + "loss": 0.8539, + "step": 7806 + }, + { + "epoch": 0.4792657847079407, + "grad_norm": 0.8213830675132754, + "learning_rate": 1.1154638469836408e-05, + "loss": 0.8954, + "step": 7807 + }, + { + "epoch": 0.47932717394640717, + "grad_norm": 0.7845447069708972, + "learning_rate": 1.1152663395957333e-05, + "loss": 0.8946, + "step": 7808 + }, + { + "epoch": 0.4793885631848737, + "grad_norm": 0.7676599184280798, + "learning_rate": 1.1150688276507313e-05, + "loss": 0.858, + "step": 7809 + }, + { + "epoch": 0.4794499524233402, + "grad_norm": 0.703873240238344, + "learning_rate": 1.1148713111564432e-05, + "loss": 0.8173, + "step": 7810 + }, + { + "epoch": 0.4795113416618067, + "grad_norm": 0.7149529619902373, + "learning_rate": 1.1146737901206775e-05, + "loss": 0.8269, + "step": 7811 + }, + { + "epoch": 0.4795727309002732, + "grad_norm": 0.8085076709403424, + "learning_rate": 1.1144762645512438e-05, + "loss": 0.8509, + "step": 7812 + }, + { + "epoch": 0.4796341201387397, + "grad_norm": 0.7459815943919538, + "learning_rate": 1.1142787344559509e-05, + "loss": 0.843, + "step": 7813 + }, + { + "epoch": 0.4796955093772062, + "grad_norm": 0.725544221650116, + "learning_rate": 1.1140811998426089e-05, + "loss": 0.8411, + "step": 7814 + }, + { + "epoch": 0.47975689861567267, + "grad_norm": 0.723345301157356, + "learning_rate": 1.1138836607190265e-05, + "loss": 0.7925, + "step": 7815 + }, + { + "epoch": 0.47981828785413916, + "grad_norm": 0.7479913935017584, + "learning_rate": 1.113686117093014e-05, + "loss": 0.8417, + "step": 7816 + }, + { + "epoch": 0.47987967709260565, + "grad_norm": 0.7428546059606507, + "learning_rate": 1.113488568972381e-05, + "loss": 0.8616, + "step": 7817 + }, + { + "epoch": 0.47994106633107214, + "grad_norm": 0.7816800300718683, + "learning_rate": 1.1132910163649385e-05, + "loss": 0.8395, + "step": 7818 + }, + { + "epoch": 0.48000245556953863, + "grad_norm": 0.772685100345014, + "learning_rate": 1.1130934592784956e-05, + "loss": 0.8651, + "step": 7819 + }, + { + "epoch": 0.4800638448080052, + "grad_norm": 0.7303864348419716, + "learning_rate": 1.1128958977208635e-05, + "loss": 0.8284, + "step": 7820 + }, + { + "epoch": 0.48012523404647167, + "grad_norm": 0.8579968981709288, + "learning_rate": 1.112698331699853e-05, + "loss": 0.9066, + "step": 7821 + }, + { + "epoch": 0.48018662328493816, + "grad_norm": 0.7310082441663643, + "learning_rate": 1.1125007612232746e-05, + "loss": 0.8295, + "step": 7822 + }, + { + "epoch": 0.48024801252340465, + "grad_norm": 0.7864974833706767, + "learning_rate": 1.1123031862989393e-05, + "loss": 0.9091, + "step": 7823 + }, + { + "epoch": 0.48030940176187115, + "grad_norm": 0.7325702263826609, + "learning_rate": 1.1121056069346585e-05, + "loss": 0.8619, + "step": 7824 + }, + { + "epoch": 0.48037079100033764, + "grad_norm": 0.7426555976961726, + "learning_rate": 1.1119080231382435e-05, + "loss": 0.8409, + "step": 7825 + }, + { + "epoch": 0.48043218023880413, + "grad_norm": 0.7309293394529777, + "learning_rate": 1.1117104349175057e-05, + "loss": 0.8228, + "step": 7826 + }, + { + "epoch": 0.4804935694772706, + "grad_norm": 0.7909511484136658, + "learning_rate": 1.111512842280257e-05, + "loss": 0.8717, + "step": 7827 + }, + { + "epoch": 0.4805549587157371, + "grad_norm": 0.7918396528246332, + "learning_rate": 1.1113152452343093e-05, + "loss": 0.9035, + "step": 7828 + }, + { + "epoch": 0.4806163479542036, + "grad_norm": 0.7987555569962796, + "learning_rate": 1.1111176437874747e-05, + "loss": 0.8079, + "step": 7829 + }, + { + "epoch": 0.48067773719267015, + "grad_norm": 0.7184919346137103, + "learning_rate": 1.1109200379475651e-05, + "loss": 0.8574, + "step": 7830 + }, + { + "epoch": 0.48073912643113664, + "grad_norm": 0.7269924391588563, + "learning_rate": 1.1107224277223931e-05, + "loss": 0.8424, + "step": 7831 + }, + { + "epoch": 0.48080051566960313, + "grad_norm": 0.8076393383701668, + "learning_rate": 1.1105248131197717e-05, + "loss": 0.8996, + "step": 7832 + }, + { + "epoch": 0.4808619049080696, + "grad_norm": 0.8056450449394379, + "learning_rate": 1.1103271941475129e-05, + "loss": 0.8731, + "step": 7833 + }, + { + "epoch": 0.4809232941465361, + "grad_norm": 0.7886732693230106, + "learning_rate": 1.1101295708134304e-05, + "loss": 0.8271, + "step": 7834 + }, + { + "epoch": 0.4809846833850026, + "grad_norm": 0.7713063581970744, + "learning_rate": 1.1099319431253367e-05, + "loss": 0.8429, + "step": 7835 + }, + { + "epoch": 0.4810460726234691, + "grad_norm": 0.7731995802101718, + "learning_rate": 1.1097343110910452e-05, + "loss": 0.8707, + "step": 7836 + }, + { + "epoch": 0.4811074618619356, + "grad_norm": 0.8049902503054144, + "learning_rate": 1.10953667471837e-05, + "loss": 0.8486, + "step": 7837 + }, + { + "epoch": 0.4811688511004021, + "grad_norm": 0.7790991633342583, + "learning_rate": 1.1093390340151237e-05, + "loss": 0.8903, + "step": 7838 + }, + { + "epoch": 0.4812302403388686, + "grad_norm": 0.771094825295428, + "learning_rate": 1.1091413889891211e-05, + "loss": 0.8124, + "step": 7839 + }, + { + "epoch": 0.48129162957733507, + "grad_norm": 0.7803520443922024, + "learning_rate": 1.1089437396481752e-05, + "loss": 0.8704, + "step": 7840 + }, + { + "epoch": 0.4813530188158016, + "grad_norm": 0.7658089444524214, + "learning_rate": 1.1087460860001009e-05, + "loss": 0.8451, + "step": 7841 + }, + { + "epoch": 0.4814144080542681, + "grad_norm": 0.8356656344098495, + "learning_rate": 1.1085484280527121e-05, + "loss": 0.8162, + "step": 7842 + }, + { + "epoch": 0.4814757972927346, + "grad_norm": 0.7278426343266369, + "learning_rate": 1.1083507658138231e-05, + "loss": 0.8108, + "step": 7843 + }, + { + "epoch": 0.4815371865312011, + "grad_norm": 0.851259316469437, + "learning_rate": 1.1081530992912493e-05, + "loss": 0.9538, + "step": 7844 + }, + { + "epoch": 0.4815985757696676, + "grad_norm": 0.7000188607590241, + "learning_rate": 1.1079554284928047e-05, + "loss": 0.8146, + "step": 7845 + }, + { + "epoch": 0.48165996500813407, + "grad_norm": 0.8205142169894928, + "learning_rate": 1.107757753426305e-05, + "loss": 0.8315, + "step": 7846 + }, + { + "epoch": 0.48172135424660056, + "grad_norm": 0.7525938026961195, + "learning_rate": 1.1075600740995645e-05, + "loss": 0.825, + "step": 7847 + }, + { + "epoch": 0.48178274348506706, + "grad_norm": 0.7538135489144514, + "learning_rate": 1.1073623905203993e-05, + "loss": 0.8083, + "step": 7848 + }, + { + "epoch": 0.48184413272353355, + "grad_norm": 0.7451824138113944, + "learning_rate": 1.1071647026966245e-05, + "loss": 0.8383, + "step": 7849 + }, + { + "epoch": 0.48190552196200004, + "grad_norm": 0.8156198839968672, + "learning_rate": 1.106967010636056e-05, + "loss": 0.8763, + "step": 7850 + }, + { + "epoch": 0.4819669112004666, + "grad_norm": 0.7000962345788375, + "learning_rate": 1.1067693143465092e-05, + "loss": 0.8347, + "step": 7851 + }, + { + "epoch": 0.4820283004389331, + "grad_norm": 0.8007500786950374, + "learning_rate": 1.1065716138358004e-05, + "loss": 0.872, + "step": 7852 + }, + { + "epoch": 0.48208968967739957, + "grad_norm": 0.747787166352023, + "learning_rate": 1.106373909111746e-05, + "loss": 0.8361, + "step": 7853 + }, + { + "epoch": 0.48215107891586606, + "grad_norm": 0.5826699317028889, + "learning_rate": 1.1061762001821618e-05, + "loss": 0.705, + "step": 7854 + }, + { + "epoch": 0.48221246815433255, + "grad_norm": 0.7520755575470235, + "learning_rate": 1.1059784870548647e-05, + "loss": 0.9219, + "step": 7855 + }, + { + "epoch": 0.48227385739279904, + "grad_norm": 0.8281367030378713, + "learning_rate": 1.105780769737671e-05, + "loss": 0.8703, + "step": 7856 + }, + { + "epoch": 0.48233524663126554, + "grad_norm": 0.8535051055595462, + "learning_rate": 1.105583048238398e-05, + "loss": 0.8366, + "step": 7857 + }, + { + "epoch": 0.482396635869732, + "grad_norm": 0.7768154714198664, + "learning_rate": 1.1053853225648619e-05, + "loss": 0.8556, + "step": 7858 + }, + { + "epoch": 0.4824580251081985, + "grad_norm": 0.8113270253093996, + "learning_rate": 1.1051875927248807e-05, + "loss": 0.827, + "step": 7859 + }, + { + "epoch": 0.482519414346665, + "grad_norm": 0.749144224877868, + "learning_rate": 1.1049898587262715e-05, + "loss": 0.7826, + "step": 7860 + }, + { + "epoch": 0.4825808035851315, + "grad_norm": 0.7866253569937911, + "learning_rate": 1.1047921205768515e-05, + "loss": 0.8374, + "step": 7861 + }, + { + "epoch": 0.48264219282359805, + "grad_norm": 0.7679990498528688, + "learning_rate": 1.1045943782844385e-05, + "loss": 0.832, + "step": 7862 + }, + { + "epoch": 0.48270358206206454, + "grad_norm": 0.8495199332444443, + "learning_rate": 1.1043966318568502e-05, + "loss": 0.8857, + "step": 7863 + }, + { + "epoch": 0.48276497130053103, + "grad_norm": 0.7757374054380356, + "learning_rate": 1.1041988813019051e-05, + "loss": 0.8957, + "step": 7864 + }, + { + "epoch": 0.4828263605389975, + "grad_norm": 0.7562880772536433, + "learning_rate": 1.1040011266274205e-05, + "loss": 0.8519, + "step": 7865 + }, + { + "epoch": 0.482887749777464, + "grad_norm": 0.7635431669819366, + "learning_rate": 1.1038033678412152e-05, + "loss": 0.8126, + "step": 7866 + }, + { + "epoch": 0.4829491390159305, + "grad_norm": 0.8030673446230503, + "learning_rate": 1.1036056049511077e-05, + "loss": 0.8111, + "step": 7867 + }, + { + "epoch": 0.483010528254397, + "grad_norm": 0.7240970303540896, + "learning_rate": 1.1034078379649164e-05, + "loss": 0.7982, + "step": 7868 + }, + { + "epoch": 0.4830719174928635, + "grad_norm": 0.8267129660709737, + "learning_rate": 1.1032100668904606e-05, + "loss": 0.855, + "step": 7869 + }, + { + "epoch": 0.48313330673133, + "grad_norm": 0.8971367858990685, + "learning_rate": 1.1030122917355584e-05, + "loss": 0.8814, + "step": 7870 + }, + { + "epoch": 0.4831946959697965, + "grad_norm": 0.7805125520872969, + "learning_rate": 1.1028145125080297e-05, + "loss": 0.84, + "step": 7871 + }, + { + "epoch": 0.48325608520826296, + "grad_norm": 0.8550883538037054, + "learning_rate": 1.1026167292156928e-05, + "loss": 0.8623, + "step": 7872 + }, + { + "epoch": 0.4833174744467295, + "grad_norm": 0.7817111617792556, + "learning_rate": 1.1024189418663685e-05, + "loss": 0.8768, + "step": 7873 + }, + { + "epoch": 0.483378863685196, + "grad_norm": 0.8416417853617604, + "learning_rate": 1.1022211504678753e-05, + "loss": 0.841, + "step": 7874 + }, + { + "epoch": 0.4834402529236625, + "grad_norm": 0.764250147744579, + "learning_rate": 1.102023355028033e-05, + "loss": 0.8128, + "step": 7875 + }, + { + "epoch": 0.483501642162129, + "grad_norm": 0.7328651181094407, + "learning_rate": 1.1018255555546624e-05, + "loss": 0.8712, + "step": 7876 + }, + { + "epoch": 0.4835630314005955, + "grad_norm": 0.7397455778485452, + "learning_rate": 1.1016277520555828e-05, + "loss": 0.8106, + "step": 7877 + }, + { + "epoch": 0.48362442063906197, + "grad_norm": 0.7420272094103528, + "learning_rate": 1.1014299445386146e-05, + "loss": 0.8759, + "step": 7878 + }, + { + "epoch": 0.48368580987752846, + "grad_norm": 0.739015024762715, + "learning_rate": 1.101232133011578e-05, + "loss": 0.8757, + "step": 7879 + }, + { + "epoch": 0.48374719911599495, + "grad_norm": 0.7332658865587971, + "learning_rate": 1.101034317482294e-05, + "loss": 0.8172, + "step": 7880 + }, + { + "epoch": 0.48380858835446144, + "grad_norm": 0.8293361220802077, + "learning_rate": 1.100836497958583e-05, + "loss": 0.878, + "step": 7881 + }, + { + "epoch": 0.48386997759292794, + "grad_norm": 0.7822092524693114, + "learning_rate": 1.1006386744482658e-05, + "loss": 0.8872, + "step": 7882 + }, + { + "epoch": 0.4839313668313945, + "grad_norm": 0.8261798008680238, + "learning_rate": 1.1004408469591638e-05, + "loss": 0.8298, + "step": 7883 + }, + { + "epoch": 0.483992756069861, + "grad_norm": 0.8144806077126052, + "learning_rate": 1.1002430154990977e-05, + "loss": 0.8475, + "step": 7884 + }, + { + "epoch": 0.48405414530832747, + "grad_norm": 0.8339912105845332, + "learning_rate": 1.1000451800758892e-05, + "loss": 0.8372, + "step": 7885 + }, + { + "epoch": 0.48411553454679396, + "grad_norm": 0.77204063486675, + "learning_rate": 1.0998473406973596e-05, + "loss": 0.7938, + "step": 7886 + }, + { + "epoch": 0.48417692378526045, + "grad_norm": 0.8123320035118783, + "learning_rate": 1.0996494973713305e-05, + "loss": 0.8528, + "step": 7887 + }, + { + "epoch": 0.48423831302372694, + "grad_norm": 0.7674991838448616, + "learning_rate": 1.0994516501056241e-05, + "loss": 0.8804, + "step": 7888 + }, + { + "epoch": 0.48429970226219343, + "grad_norm": 0.8364450866607952, + "learning_rate": 1.0992537989080618e-05, + "loss": 0.9153, + "step": 7889 + }, + { + "epoch": 0.4843610915006599, + "grad_norm": 0.8210416176362424, + "learning_rate": 1.0990559437864658e-05, + "loss": 0.8276, + "step": 7890 + }, + { + "epoch": 0.4844224807391264, + "grad_norm": 0.7646043737618503, + "learning_rate": 1.098858084748659e-05, + "loss": 0.8189, + "step": 7891 + }, + { + "epoch": 0.4844838699775929, + "grad_norm": 0.9048882501590305, + "learning_rate": 1.0986602218024632e-05, + "loss": 0.8872, + "step": 7892 + }, + { + "epoch": 0.4845452592160594, + "grad_norm": 0.7673267149185976, + "learning_rate": 1.0984623549557012e-05, + "loss": 0.8497, + "step": 7893 + }, + { + "epoch": 0.48460664845452595, + "grad_norm": 0.7033818169362159, + "learning_rate": 1.0982644842161956e-05, + "loss": 0.8189, + "step": 7894 + }, + { + "epoch": 0.48466803769299244, + "grad_norm": 0.7248855764118071, + "learning_rate": 1.0980666095917694e-05, + "loss": 0.8322, + "step": 7895 + }, + { + "epoch": 0.48472942693145893, + "grad_norm": 0.8352604982183609, + "learning_rate": 1.0978687310902459e-05, + "loss": 0.8209, + "step": 7896 + }, + { + "epoch": 0.4847908161699254, + "grad_norm": 0.801171822393558, + "learning_rate": 1.0976708487194474e-05, + "loss": 0.8119, + "step": 7897 + }, + { + "epoch": 0.4848522054083919, + "grad_norm": 0.627407017216701, + "learning_rate": 1.0974729624871983e-05, + "loss": 0.7248, + "step": 7898 + }, + { + "epoch": 0.4849135946468584, + "grad_norm": 0.837644774994588, + "learning_rate": 1.0972750724013217e-05, + "loss": 0.8767, + "step": 7899 + }, + { + "epoch": 0.4849749838853249, + "grad_norm": 0.7355081812730795, + "learning_rate": 1.097077178469641e-05, + "loss": 0.801, + "step": 7900 + }, + { + "epoch": 0.4850363731237914, + "grad_norm": 0.821714570921351, + "learning_rate": 1.0968792806999806e-05, + "loss": 0.9169, + "step": 7901 + }, + { + "epoch": 0.4850977623622579, + "grad_norm": 0.8240324254851734, + "learning_rate": 1.0966813791001635e-05, + "loss": 0.8585, + "step": 7902 + }, + { + "epoch": 0.48515915160072437, + "grad_norm": 0.8034819996397313, + "learning_rate": 1.096483473678015e-05, + "loss": 0.8556, + "step": 7903 + }, + { + "epoch": 0.4852205408391909, + "grad_norm": 0.7707753781264146, + "learning_rate": 1.0962855644413584e-05, + "loss": 0.8698, + "step": 7904 + }, + { + "epoch": 0.4852819300776574, + "grad_norm": 0.7861119988712952, + "learning_rate": 1.0960876513980185e-05, + "loss": 0.8442, + "step": 7905 + }, + { + "epoch": 0.4853433193161239, + "grad_norm": 0.8017023026096384, + "learning_rate": 1.09588973455582e-05, + "loss": 0.8738, + "step": 7906 + }, + { + "epoch": 0.4854047085545904, + "grad_norm": 0.7595746722447676, + "learning_rate": 1.0956918139225871e-05, + "loss": 0.8584, + "step": 7907 + }, + { + "epoch": 0.4854660977930569, + "grad_norm": 0.7443747423721895, + "learning_rate": 1.0954938895061455e-05, + "loss": 0.8419, + "step": 7908 + }, + { + "epoch": 0.4855274870315234, + "grad_norm": 0.6487068613723076, + "learning_rate": 1.0952959613143193e-05, + "loss": 0.8036, + "step": 7909 + }, + { + "epoch": 0.48558887626998987, + "grad_norm": 0.5968214621160457, + "learning_rate": 1.0950980293549342e-05, + "loss": 0.717, + "step": 7910 + }, + { + "epoch": 0.48565026550845636, + "grad_norm": 0.7765794589611066, + "learning_rate": 1.0949000936358157e-05, + "loss": 0.868, + "step": 7911 + }, + { + "epoch": 0.48571165474692285, + "grad_norm": 0.7686118832633643, + "learning_rate": 1.0947021541647884e-05, + "loss": 0.8986, + "step": 7912 + }, + { + "epoch": 0.48577304398538934, + "grad_norm": 0.7437952063418586, + "learning_rate": 1.0945042109496789e-05, + "loss": 0.8549, + "step": 7913 + }, + { + "epoch": 0.48583443322385583, + "grad_norm": 0.6891733093680678, + "learning_rate": 1.0943062639983119e-05, + "loss": 0.822, + "step": 7914 + }, + { + "epoch": 0.4858958224623224, + "grad_norm": 0.7928362568686669, + "learning_rate": 1.0941083133185146e-05, + "loss": 0.8797, + "step": 7915 + }, + { + "epoch": 0.48595721170078887, + "grad_norm": 0.8626290008254327, + "learning_rate": 1.0939103589181119e-05, + "loss": 0.8915, + "step": 7916 + }, + { + "epoch": 0.48601860093925536, + "grad_norm": 0.7290178381870773, + "learning_rate": 1.0937124008049305e-05, + "loss": 0.836, + "step": 7917 + }, + { + "epoch": 0.48607999017772185, + "grad_norm": 0.7020991579861182, + "learning_rate": 1.093514438986797e-05, + "loss": 0.8632, + "step": 7918 + }, + { + "epoch": 0.48614137941618835, + "grad_norm": 0.8161048538468102, + "learning_rate": 1.0933164734715371e-05, + "loss": 0.8426, + "step": 7919 + }, + { + "epoch": 0.48620276865465484, + "grad_norm": 0.5994912065619937, + "learning_rate": 1.0931185042669783e-05, + "loss": 0.7276, + "step": 7920 + }, + { + "epoch": 0.48626415789312133, + "grad_norm": 0.7102405417682274, + "learning_rate": 1.0929205313809465e-05, + "loss": 0.8789, + "step": 7921 + }, + { + "epoch": 0.4863255471315878, + "grad_norm": 0.80379612353342, + "learning_rate": 1.0927225548212696e-05, + "loss": 0.898, + "step": 7922 + }, + { + "epoch": 0.4863869363700543, + "grad_norm": 0.7522282873239288, + "learning_rate": 1.092524574595774e-05, + "loss": 0.8067, + "step": 7923 + }, + { + "epoch": 0.4864483256085208, + "grad_norm": 0.7321383907305291, + "learning_rate": 1.0923265907122872e-05, + "loss": 0.8743, + "step": 7924 + }, + { + "epoch": 0.4865097148469873, + "grad_norm": 0.851329731677074, + "learning_rate": 1.0921286031786365e-05, + "loss": 0.8632, + "step": 7925 + }, + { + "epoch": 0.48657110408545384, + "grad_norm": 0.7829084751010525, + "learning_rate": 1.0919306120026493e-05, + "loss": 0.8678, + "step": 7926 + }, + { + "epoch": 0.48663249332392033, + "grad_norm": 0.7033386083390578, + "learning_rate": 1.0917326171921531e-05, + "loss": 0.8159, + "step": 7927 + }, + { + "epoch": 0.4866938825623868, + "grad_norm": 0.7695545435805785, + "learning_rate": 1.0915346187549765e-05, + "loss": 0.8614, + "step": 7928 + }, + { + "epoch": 0.4867552718008533, + "grad_norm": 0.7870318562958626, + "learning_rate": 1.0913366166989462e-05, + "loss": 0.8799, + "step": 7929 + }, + { + "epoch": 0.4868166610393198, + "grad_norm": 0.7305612169929572, + "learning_rate": 1.0911386110318913e-05, + "loss": 0.8135, + "step": 7930 + }, + { + "epoch": 0.4868780502777863, + "grad_norm": 0.9029094110072063, + "learning_rate": 1.0909406017616397e-05, + "loss": 0.8434, + "step": 7931 + }, + { + "epoch": 0.4869394395162528, + "grad_norm": 0.8220673988776758, + "learning_rate": 1.0907425888960196e-05, + "loss": 0.8468, + "step": 7932 + }, + { + "epoch": 0.4870008287547193, + "grad_norm": 0.7365120905123427, + "learning_rate": 1.0905445724428598e-05, + "loss": 0.8386, + "step": 7933 + }, + { + "epoch": 0.4870622179931858, + "grad_norm": 0.8643498142733662, + "learning_rate": 1.0903465524099885e-05, + "loss": 0.8599, + "step": 7934 + }, + { + "epoch": 0.48712360723165227, + "grad_norm": 0.7180865575936373, + "learning_rate": 1.090148528805235e-05, + "loss": 0.8633, + "step": 7935 + }, + { + "epoch": 0.4871849964701188, + "grad_norm": 0.752161337000964, + "learning_rate": 1.089950501636428e-05, + "loss": 0.8692, + "step": 7936 + }, + { + "epoch": 0.4872463857085853, + "grad_norm": 0.7363546457613558, + "learning_rate": 1.0897524709113965e-05, + "loss": 0.8985, + "step": 7937 + }, + { + "epoch": 0.4873077749470518, + "grad_norm": 0.765066337884793, + "learning_rate": 1.08955443663797e-05, + "loss": 0.85, + "step": 7938 + }, + { + "epoch": 0.4873691641855183, + "grad_norm": 0.7357250204821965, + "learning_rate": 1.0893563988239773e-05, + "loss": 0.8582, + "step": 7939 + }, + { + "epoch": 0.4874305534239848, + "grad_norm": 0.7804506953845186, + "learning_rate": 1.0891583574772486e-05, + "loss": 0.8816, + "step": 7940 + }, + { + "epoch": 0.48749194266245127, + "grad_norm": 0.7957716546545429, + "learning_rate": 1.0889603126056127e-05, + "loss": 0.8618, + "step": 7941 + }, + { + "epoch": 0.48755333190091776, + "grad_norm": 0.7356546052592162, + "learning_rate": 1.0887622642169002e-05, + "loss": 0.8118, + "step": 7942 + }, + { + "epoch": 0.48761472113938426, + "grad_norm": 0.8488662670286802, + "learning_rate": 1.0885642123189407e-05, + "loss": 0.8943, + "step": 7943 + }, + { + "epoch": 0.48767611037785075, + "grad_norm": 0.6840675371226521, + "learning_rate": 1.0883661569195641e-05, + "loss": 0.8084, + "step": 7944 + }, + { + "epoch": 0.48773749961631724, + "grad_norm": 0.8083887141646406, + "learning_rate": 1.0881680980266007e-05, + "loss": 0.8755, + "step": 7945 + }, + { + "epoch": 0.48779888885478373, + "grad_norm": 0.7950920092500602, + "learning_rate": 1.0879700356478808e-05, + "loss": 0.8545, + "step": 7946 + }, + { + "epoch": 0.4878602780932503, + "grad_norm": 0.7281309716269299, + "learning_rate": 1.0877719697912353e-05, + "loss": 0.8644, + "step": 7947 + }, + { + "epoch": 0.48792166733171677, + "grad_norm": 0.7490729634442088, + "learning_rate": 1.0875739004644935e-05, + "loss": 0.8087, + "step": 7948 + }, + { + "epoch": 0.48798305657018326, + "grad_norm": 0.749447412556226, + "learning_rate": 1.0873758276754877e-05, + "loss": 0.8698, + "step": 7949 + }, + { + "epoch": 0.48804444580864975, + "grad_norm": 0.70054834776504, + "learning_rate": 1.0871777514320481e-05, + "loss": 0.8948, + "step": 7950 + }, + { + "epoch": 0.48810583504711624, + "grad_norm": 0.7072819228976643, + "learning_rate": 1.0869796717420055e-05, + "loss": 0.8543, + "step": 7951 + }, + { + "epoch": 0.48816722428558273, + "grad_norm": 0.7911848952460485, + "learning_rate": 1.0867815886131916e-05, + "loss": 0.8233, + "step": 7952 + }, + { + "epoch": 0.4882286135240492, + "grad_norm": 0.7957203629720071, + "learning_rate": 1.086583502053437e-05, + "loss": 0.8866, + "step": 7953 + }, + { + "epoch": 0.4882900027625157, + "grad_norm": 0.813140344141894, + "learning_rate": 1.0863854120705738e-05, + "loss": 0.8944, + "step": 7954 + }, + { + "epoch": 0.4883513920009822, + "grad_norm": 0.8840514675096245, + "learning_rate": 1.086187318672433e-05, + "loss": 0.8807, + "step": 7955 + }, + { + "epoch": 0.4884127812394487, + "grad_norm": 0.8143702694313747, + "learning_rate": 1.0859892218668466e-05, + "loss": 0.815, + "step": 7956 + }, + { + "epoch": 0.48847417047791525, + "grad_norm": 0.7559008459143244, + "learning_rate": 1.0857911216616464e-05, + "loss": 0.8184, + "step": 7957 + }, + { + "epoch": 0.48853555971638174, + "grad_norm": 0.7842560219186496, + "learning_rate": 1.0855930180646643e-05, + "loss": 0.8278, + "step": 7958 + }, + { + "epoch": 0.48859694895484823, + "grad_norm": 0.7628749597030203, + "learning_rate": 1.0853949110837321e-05, + "loss": 0.8251, + "step": 7959 + }, + { + "epoch": 0.4886583381933147, + "grad_norm": 0.8453235632185723, + "learning_rate": 1.0851968007266827e-05, + "loss": 0.8796, + "step": 7960 + }, + { + "epoch": 0.4887197274317812, + "grad_norm": 0.7502475826167567, + "learning_rate": 1.0849986870013481e-05, + "loss": 0.856, + "step": 7961 + }, + { + "epoch": 0.4887811166702477, + "grad_norm": 0.8040562456732339, + "learning_rate": 1.0848005699155608e-05, + "loss": 0.8791, + "step": 7962 + }, + { + "epoch": 0.4888425059087142, + "grad_norm": 0.8263867208325097, + "learning_rate": 1.0846024494771534e-05, + "loss": 0.8238, + "step": 7963 + }, + { + "epoch": 0.4889038951471807, + "grad_norm": 0.8318615911964915, + "learning_rate": 1.0844043256939585e-05, + "loss": 0.8664, + "step": 7964 + }, + { + "epoch": 0.4889652843856472, + "grad_norm": 0.7936043095558964, + "learning_rate": 1.0842061985738095e-05, + "loss": 0.7995, + "step": 7965 + }, + { + "epoch": 0.4890266736241137, + "grad_norm": 0.7876734669031233, + "learning_rate": 1.0840080681245389e-05, + "loss": 0.8638, + "step": 7966 + }, + { + "epoch": 0.48908806286258016, + "grad_norm": 0.8470974656815838, + "learning_rate": 1.0838099343539803e-05, + "loss": 0.8865, + "step": 7967 + }, + { + "epoch": 0.4891494521010467, + "grad_norm": 0.7244687894674264, + "learning_rate": 1.0836117972699663e-05, + "loss": 0.8399, + "step": 7968 + }, + { + "epoch": 0.4892108413395132, + "grad_norm": 0.7997894366024102, + "learning_rate": 1.083413656880331e-05, + "loss": 0.8448, + "step": 7969 + }, + { + "epoch": 0.4892722305779797, + "grad_norm": 0.8157907791293303, + "learning_rate": 1.0832155131929076e-05, + "loss": 0.863, + "step": 7970 + }, + { + "epoch": 0.4893336198164462, + "grad_norm": 0.8063230658474853, + "learning_rate": 1.0830173662155299e-05, + "loss": 0.855, + "step": 7971 + }, + { + "epoch": 0.4893950090549127, + "grad_norm": 0.7713414707656964, + "learning_rate": 1.0828192159560322e-05, + "loss": 0.8472, + "step": 7972 + }, + { + "epoch": 0.48945639829337917, + "grad_norm": 0.8072416195682642, + "learning_rate": 1.0826210624222473e-05, + "loss": 0.817, + "step": 7973 + }, + { + "epoch": 0.48951778753184566, + "grad_norm": 0.8296262450423514, + "learning_rate": 1.08242290562201e-05, + "loss": 0.8802, + "step": 7974 + }, + { + "epoch": 0.48957917677031215, + "grad_norm": 0.7898383616395158, + "learning_rate": 1.082224745563155e-05, + "loss": 0.8348, + "step": 7975 + }, + { + "epoch": 0.48964056600877864, + "grad_norm": 0.7370409952775483, + "learning_rate": 1.0820265822535155e-05, + "loss": 0.8323, + "step": 7976 + }, + { + "epoch": 0.48970195524724514, + "grad_norm": 0.5953958679738377, + "learning_rate": 1.0818284157009267e-05, + "loss": 0.7029, + "step": 7977 + }, + { + "epoch": 0.4897633444857117, + "grad_norm": 0.857107909101726, + "learning_rate": 1.0816302459132226e-05, + "loss": 0.8727, + "step": 7978 + }, + { + "epoch": 0.4898247337241782, + "grad_norm": 0.8137883973547628, + "learning_rate": 1.0814320728982391e-05, + "loss": 0.8391, + "step": 7979 + }, + { + "epoch": 0.48988612296264467, + "grad_norm": 0.7254112231147335, + "learning_rate": 1.0812338966638094e-05, + "loss": 0.8362, + "step": 7980 + }, + { + "epoch": 0.48994751220111116, + "grad_norm": 0.8140654245822759, + "learning_rate": 1.0810357172177696e-05, + "loss": 0.8123, + "step": 7981 + }, + { + "epoch": 0.49000890143957765, + "grad_norm": 0.7497072180853679, + "learning_rate": 1.0808375345679544e-05, + "loss": 0.8119, + "step": 7982 + }, + { + "epoch": 0.49007029067804414, + "grad_norm": 0.7459003566255672, + "learning_rate": 1.0806393487221994e-05, + "loss": 0.8507, + "step": 7983 + }, + { + "epoch": 0.49013167991651063, + "grad_norm": 0.7693490585662998, + "learning_rate": 1.0804411596883396e-05, + "loss": 0.8357, + "step": 7984 + }, + { + "epoch": 0.4901930691549771, + "grad_norm": 0.8223795084354483, + "learning_rate": 1.0802429674742102e-05, + "loss": 0.9232, + "step": 7985 + }, + { + "epoch": 0.4902544583934436, + "grad_norm": 0.7599735034002877, + "learning_rate": 1.0800447720876473e-05, + "loss": 0.8616, + "step": 7986 + }, + { + "epoch": 0.4903158476319101, + "grad_norm": 0.867852400619779, + "learning_rate": 1.0798465735364864e-05, + "loss": 0.8855, + "step": 7987 + }, + { + "epoch": 0.4903772368703766, + "grad_norm": 0.8210205500600474, + "learning_rate": 1.0796483718285636e-05, + "loss": 0.8433, + "step": 7988 + }, + { + "epoch": 0.49043862610884315, + "grad_norm": 0.7782276836272772, + "learning_rate": 1.0794501669717146e-05, + "loss": 0.8136, + "step": 7989 + }, + { + "epoch": 0.49050001534730964, + "grad_norm": 0.8396747531087568, + "learning_rate": 1.0792519589737756e-05, + "loss": 0.8596, + "step": 7990 + }, + { + "epoch": 0.49056140458577613, + "grad_norm": 0.8024965285940496, + "learning_rate": 1.0790537478425824e-05, + "loss": 0.8736, + "step": 7991 + }, + { + "epoch": 0.4906227938242426, + "grad_norm": 0.8659847072396709, + "learning_rate": 1.0788555335859721e-05, + "loss": 0.8766, + "step": 7992 + }, + { + "epoch": 0.4906841830627091, + "grad_norm": 0.6984890179109918, + "learning_rate": 1.0786573162117809e-05, + "loss": 0.8497, + "step": 7993 + }, + { + "epoch": 0.4907455723011756, + "grad_norm": 0.8537332886076148, + "learning_rate": 1.0784590957278452e-05, + "loss": 0.8533, + "step": 7994 + }, + { + "epoch": 0.4908069615396421, + "grad_norm": 0.6491892858340308, + "learning_rate": 1.0782608721420015e-05, + "loss": 0.7716, + "step": 7995 + }, + { + "epoch": 0.4908683507781086, + "grad_norm": 0.8204248951792706, + "learning_rate": 1.0780626454620873e-05, + "loss": 0.8812, + "step": 7996 + }, + { + "epoch": 0.4909297400165751, + "grad_norm": 0.748141296014705, + "learning_rate": 1.0778644156959392e-05, + "loss": 0.8302, + "step": 7997 + }, + { + "epoch": 0.49099112925504157, + "grad_norm": 0.7726556081532924, + "learning_rate": 1.0776661828513942e-05, + "loss": 0.8324, + "step": 7998 + }, + { + "epoch": 0.49105251849350806, + "grad_norm": 0.8003132112591445, + "learning_rate": 1.0774679469362899e-05, + "loss": 0.8472, + "step": 7999 + }, + { + "epoch": 0.4911139077319746, + "grad_norm": 0.835713608370469, + "learning_rate": 1.0772697079584628e-05, + "loss": 0.8577, + "step": 8000 + }, + { + "epoch": 0.4911752969704411, + "grad_norm": 0.8043400469728545, + "learning_rate": 1.0770714659257513e-05, + "loss": 0.8891, + "step": 8001 + }, + { + "epoch": 0.4912366862089076, + "grad_norm": 0.864671291484569, + "learning_rate": 1.0768732208459924e-05, + "loss": 0.8408, + "step": 8002 + }, + { + "epoch": 0.4912980754473741, + "grad_norm": 0.8904000356484482, + "learning_rate": 1.0766749727270238e-05, + "loss": 0.9372, + "step": 8003 + }, + { + "epoch": 0.4913594646858406, + "grad_norm": 0.7393986148613979, + "learning_rate": 1.0764767215766838e-05, + "loss": 0.841, + "step": 8004 + }, + { + "epoch": 0.49142085392430707, + "grad_norm": 0.7919482796212775, + "learning_rate": 1.0762784674028095e-05, + "loss": 0.8475, + "step": 8005 + }, + { + "epoch": 0.49148224316277356, + "grad_norm": 0.8084985874695769, + "learning_rate": 1.0760802102132398e-05, + "loss": 0.8469, + "step": 8006 + }, + { + "epoch": 0.49154363240124005, + "grad_norm": 0.7754557320472849, + "learning_rate": 1.0758819500158124e-05, + "loss": 0.8126, + "step": 8007 + }, + { + "epoch": 0.49160502163970654, + "grad_norm": 0.8212523072748388, + "learning_rate": 1.0756836868183655e-05, + "loss": 0.8756, + "step": 8008 + }, + { + "epoch": 0.49166641087817303, + "grad_norm": 0.7841471378457727, + "learning_rate": 1.075485420628738e-05, + "loss": 0.9204, + "step": 8009 + }, + { + "epoch": 0.4917278001166396, + "grad_norm": 0.7200687341962713, + "learning_rate": 1.0752871514547676e-05, + "loss": 0.8311, + "step": 8010 + }, + { + "epoch": 0.49178918935510607, + "grad_norm": 0.785061578870347, + "learning_rate": 1.075088879304294e-05, + "loss": 0.8806, + "step": 8011 + }, + { + "epoch": 0.49185057859357256, + "grad_norm": 0.8647783203754591, + "learning_rate": 1.074890604185155e-05, + "loss": 0.8823, + "step": 8012 + }, + { + "epoch": 0.49191196783203905, + "grad_norm": 0.8261090006526379, + "learning_rate": 1.07469232610519e-05, + "loss": 0.8436, + "step": 8013 + }, + { + "epoch": 0.49197335707050555, + "grad_norm": 0.7142083479224209, + "learning_rate": 1.0744940450722378e-05, + "loss": 0.8562, + "step": 8014 + }, + { + "epoch": 0.49203474630897204, + "grad_norm": 0.751133418551469, + "learning_rate": 1.0742957610941378e-05, + "loss": 0.8014, + "step": 8015 + }, + { + "epoch": 0.49209613554743853, + "grad_norm": 0.777946651748155, + "learning_rate": 1.0740974741787289e-05, + "loss": 0.8598, + "step": 8016 + }, + { + "epoch": 0.492157524785905, + "grad_norm": 0.7416386690389346, + "learning_rate": 1.0738991843338502e-05, + "loss": 0.8665, + "step": 8017 + }, + { + "epoch": 0.4922189140243715, + "grad_norm": 0.7959541161153367, + "learning_rate": 1.0737008915673418e-05, + "loss": 0.8421, + "step": 8018 + }, + { + "epoch": 0.492280303262838, + "grad_norm": 0.8159544011964016, + "learning_rate": 1.073502595887043e-05, + "loss": 0.877, + "step": 8019 + }, + { + "epoch": 0.4923416925013045, + "grad_norm": 0.7641716158101236, + "learning_rate": 1.0733042973007934e-05, + "loss": 0.8079, + "step": 8020 + }, + { + "epoch": 0.49240308173977104, + "grad_norm": 0.7394976487134408, + "learning_rate": 1.0731059958164331e-05, + "loss": 0.8677, + "step": 8021 + }, + { + "epoch": 0.49246447097823753, + "grad_norm": 0.7526811236544461, + "learning_rate": 1.0729076914418014e-05, + "loss": 0.8142, + "step": 8022 + }, + { + "epoch": 0.492525860216704, + "grad_norm": 0.8178734447434197, + "learning_rate": 1.072709384184739e-05, + "loss": 0.8355, + "step": 8023 + }, + { + "epoch": 0.4925872494551705, + "grad_norm": 0.8322802499868949, + "learning_rate": 1.0725110740530855e-05, + "loss": 0.8751, + "step": 8024 + }, + { + "epoch": 0.492648638693637, + "grad_norm": 0.7561909246318982, + "learning_rate": 1.0723127610546818e-05, + "loss": 0.8233, + "step": 8025 + }, + { + "epoch": 0.4927100279321035, + "grad_norm": 0.7173702859709155, + "learning_rate": 1.0721144451973677e-05, + "loss": 0.8321, + "step": 8026 + }, + { + "epoch": 0.49277141717057, + "grad_norm": 0.7646290526271097, + "learning_rate": 1.071916126488984e-05, + "loss": 0.8714, + "step": 8027 + }, + { + "epoch": 0.4928328064090365, + "grad_norm": 0.8849317464910283, + "learning_rate": 1.071717804937371e-05, + "loss": 0.8449, + "step": 8028 + }, + { + "epoch": 0.492894195647503, + "grad_norm": 0.7111923306896824, + "learning_rate": 1.0715194805503697e-05, + "loss": 0.8765, + "step": 8029 + }, + { + "epoch": 0.49295558488596947, + "grad_norm": 0.7934184443263411, + "learning_rate": 1.0713211533358205e-05, + "loss": 0.8709, + "step": 8030 + }, + { + "epoch": 0.493016974124436, + "grad_norm": 0.8406309538298077, + "learning_rate": 1.0711228233015652e-05, + "loss": 0.8786, + "step": 8031 + }, + { + "epoch": 0.4930783633629025, + "grad_norm": 0.7605788623114742, + "learning_rate": 1.0709244904554439e-05, + "loss": 0.8885, + "step": 8032 + }, + { + "epoch": 0.493139752601369, + "grad_norm": 0.7920798086261057, + "learning_rate": 1.0707261548052985e-05, + "loss": 0.877, + "step": 8033 + }, + { + "epoch": 0.4932011418398355, + "grad_norm": 0.7976977329011341, + "learning_rate": 1.0705278163589696e-05, + "loss": 0.8373, + "step": 8034 + }, + { + "epoch": 0.493262531078302, + "grad_norm": 0.7748204981770183, + "learning_rate": 1.0703294751242989e-05, + "loss": 0.8576, + "step": 8035 + }, + { + "epoch": 0.49332392031676847, + "grad_norm": 0.7947117869413584, + "learning_rate": 1.0701311311091285e-05, + "loss": 0.8567, + "step": 8036 + }, + { + "epoch": 0.49338530955523496, + "grad_norm": 0.8164858223340233, + "learning_rate": 1.0699327843212986e-05, + "loss": 0.8973, + "step": 8037 + }, + { + "epoch": 0.49344669879370145, + "grad_norm": 0.7097941774326317, + "learning_rate": 1.0697344347686522e-05, + "loss": 0.8607, + "step": 8038 + }, + { + "epoch": 0.49350808803216795, + "grad_norm": 0.7733499853100869, + "learning_rate": 1.0695360824590304e-05, + "loss": 0.8066, + "step": 8039 + }, + { + "epoch": 0.49356947727063444, + "grad_norm": 0.7773736276351735, + "learning_rate": 1.0693377274002757e-05, + "loss": 0.8472, + "step": 8040 + }, + { + "epoch": 0.49363086650910093, + "grad_norm": 0.7663892759884124, + "learning_rate": 1.0691393696002295e-05, + "loss": 0.8562, + "step": 8041 + }, + { + "epoch": 0.4936922557475675, + "grad_norm": 0.7521227488539682, + "learning_rate": 1.068941009066734e-05, + "loss": 0.8258, + "step": 8042 + }, + { + "epoch": 0.49375364498603397, + "grad_norm": 0.858140308301358, + "learning_rate": 1.068742645807632e-05, + "loss": 0.9046, + "step": 8043 + }, + { + "epoch": 0.49381503422450046, + "grad_norm": 0.7587261016876309, + "learning_rate": 1.0685442798307654e-05, + "loss": 0.837, + "step": 8044 + }, + { + "epoch": 0.49387642346296695, + "grad_norm": 0.8276169774457689, + "learning_rate": 1.0683459111439771e-05, + "loss": 0.8955, + "step": 8045 + }, + { + "epoch": 0.49393781270143344, + "grad_norm": 0.8737608460597811, + "learning_rate": 1.0681475397551093e-05, + "loss": 0.8462, + "step": 8046 + }, + { + "epoch": 0.49399920193989993, + "grad_norm": 0.7485009199277083, + "learning_rate": 1.0679491656720047e-05, + "loss": 0.853, + "step": 8047 + }, + { + "epoch": 0.4940605911783664, + "grad_norm": 0.826219635915963, + "learning_rate": 1.0677507889025063e-05, + "loss": 0.8478, + "step": 8048 + }, + { + "epoch": 0.4941219804168329, + "grad_norm": 0.8208756199510477, + "learning_rate": 1.0675524094544564e-05, + "loss": 0.8904, + "step": 8049 + }, + { + "epoch": 0.4941833696552994, + "grad_norm": 0.7467207425372346, + "learning_rate": 1.0673540273356988e-05, + "loss": 0.8498, + "step": 8050 + }, + { + "epoch": 0.4942447588937659, + "grad_norm": 0.8153417272874511, + "learning_rate": 1.0671556425540763e-05, + "loss": 0.8806, + "step": 8051 + }, + { + "epoch": 0.4943061481322324, + "grad_norm": 0.7172977972466952, + "learning_rate": 1.066957255117432e-05, + "loss": 0.856, + "step": 8052 + }, + { + "epoch": 0.49436753737069894, + "grad_norm": 0.8184090138587047, + "learning_rate": 1.0667588650336094e-05, + "loss": 0.8678, + "step": 8053 + }, + { + "epoch": 0.49442892660916543, + "grad_norm": 0.7063894753402132, + "learning_rate": 1.0665604723104517e-05, + "loss": 0.8472, + "step": 8054 + }, + { + "epoch": 0.4944903158476319, + "grad_norm": 0.825311580360987, + "learning_rate": 1.0663620769558024e-05, + "loss": 0.8641, + "step": 8055 + }, + { + "epoch": 0.4945517050860984, + "grad_norm": 0.7099113399514924, + "learning_rate": 1.0661636789775055e-05, + "loss": 0.8834, + "step": 8056 + }, + { + "epoch": 0.4946130943245649, + "grad_norm": 0.7546359261102266, + "learning_rate": 1.0659652783834045e-05, + "loss": 0.8288, + "step": 8057 + }, + { + "epoch": 0.4946744835630314, + "grad_norm": 0.8396810326994629, + "learning_rate": 1.065766875181343e-05, + "loss": 0.8763, + "step": 8058 + }, + { + "epoch": 0.4947358728014979, + "grad_norm": 0.8430341675296161, + "learning_rate": 1.0655684693791655e-05, + "loss": 0.8265, + "step": 8059 + }, + { + "epoch": 0.4947972620399644, + "grad_norm": 0.7664992228113208, + "learning_rate": 1.0653700609847153e-05, + "loss": 0.8297, + "step": 8060 + }, + { + "epoch": 0.49485865127843087, + "grad_norm": 0.7565458117667315, + "learning_rate": 1.0651716500058376e-05, + "loss": 0.8882, + "step": 8061 + }, + { + "epoch": 0.49492004051689736, + "grad_norm": 0.8160927554172701, + "learning_rate": 1.0649732364503756e-05, + "loss": 0.8364, + "step": 8062 + }, + { + "epoch": 0.4949814297553639, + "grad_norm": 0.7500051853965797, + "learning_rate": 1.064774820326174e-05, + "loss": 0.8434, + "step": 8063 + }, + { + "epoch": 0.4950428189938304, + "grad_norm": 0.5964134448525044, + "learning_rate": 1.0645764016410776e-05, + "loss": 0.73, + "step": 8064 + }, + { + "epoch": 0.4951042082322969, + "grad_norm": 0.7806805052360027, + "learning_rate": 1.0643779804029304e-05, + "loss": 0.8152, + "step": 8065 + }, + { + "epoch": 0.4951655974707634, + "grad_norm": 0.8031692955070451, + "learning_rate": 1.0641795566195774e-05, + "loss": 0.8337, + "step": 8066 + }, + { + "epoch": 0.4952269867092299, + "grad_norm": 0.7542736154899057, + "learning_rate": 1.0639811302988631e-05, + "loss": 0.8588, + "step": 8067 + }, + { + "epoch": 0.49528837594769637, + "grad_norm": 0.7552143100631795, + "learning_rate": 1.063782701448633e-05, + "loss": 0.8228, + "step": 8068 + }, + { + "epoch": 0.49534976518616286, + "grad_norm": 0.7782679508437627, + "learning_rate": 1.0635842700767309e-05, + "loss": 0.894, + "step": 8069 + }, + { + "epoch": 0.49541115442462935, + "grad_norm": 0.708249387771797, + "learning_rate": 1.063385836191003e-05, + "loss": 0.7911, + "step": 8070 + }, + { + "epoch": 0.49547254366309584, + "grad_norm": 0.8331959821438156, + "learning_rate": 1.0631873997992941e-05, + "loss": 0.8787, + "step": 8071 + }, + { + "epoch": 0.49553393290156234, + "grad_norm": 0.82911277890362, + "learning_rate": 1.062988960909449e-05, + "loss": 0.8751, + "step": 8072 + }, + { + "epoch": 0.4955953221400288, + "grad_norm": 0.8623888127986037, + "learning_rate": 1.0627905195293135e-05, + "loss": 0.8811, + "step": 8073 + }, + { + "epoch": 0.4956567113784954, + "grad_norm": 0.7868863831292547, + "learning_rate": 1.062592075666733e-05, + "loss": 0.8755, + "step": 8074 + }, + { + "epoch": 0.49571810061696187, + "grad_norm": 0.7387637194337965, + "learning_rate": 1.062393629329553e-05, + "loss": 0.8647, + "step": 8075 + }, + { + "epoch": 0.49577948985542836, + "grad_norm": 0.8014786121061818, + "learning_rate": 1.062195180525619e-05, + "loss": 0.8931, + "step": 8076 + }, + { + "epoch": 0.49584087909389485, + "grad_norm": 0.7474746526490406, + "learning_rate": 1.0619967292627769e-05, + "loss": 0.8437, + "step": 8077 + }, + { + "epoch": 0.49590226833236134, + "grad_norm": 0.7751524454647034, + "learning_rate": 1.0617982755488725e-05, + "loss": 0.8504, + "step": 8078 + }, + { + "epoch": 0.49596365757082783, + "grad_norm": 0.8551521215970453, + "learning_rate": 1.0615998193917518e-05, + "loss": 0.8954, + "step": 8079 + }, + { + "epoch": 0.4960250468092943, + "grad_norm": 0.7637521192372763, + "learning_rate": 1.0614013607992609e-05, + "loss": 0.8885, + "step": 8080 + }, + { + "epoch": 0.4960864360477608, + "grad_norm": 0.771169034831998, + "learning_rate": 1.0612028997792455e-05, + "loss": 0.8476, + "step": 8081 + }, + { + "epoch": 0.4961478252862273, + "grad_norm": 0.8178641075908073, + "learning_rate": 1.0610044363395524e-05, + "loss": 0.8407, + "step": 8082 + }, + { + "epoch": 0.4962092145246938, + "grad_norm": 0.7331488875292121, + "learning_rate": 1.0608059704880275e-05, + "loss": 0.8448, + "step": 8083 + }, + { + "epoch": 0.49627060376316035, + "grad_norm": 0.7689460689160903, + "learning_rate": 1.0606075022325174e-05, + "loss": 0.8573, + "step": 8084 + }, + { + "epoch": 0.49633199300162684, + "grad_norm": 0.8520940492955413, + "learning_rate": 1.0604090315808689e-05, + "loss": 0.8419, + "step": 8085 + }, + { + "epoch": 0.49639338224009333, + "grad_norm": 0.8236052592501557, + "learning_rate": 1.060210558540928e-05, + "loss": 0.8514, + "step": 8086 + }, + { + "epoch": 0.4964547714785598, + "grad_norm": 0.7842818944016334, + "learning_rate": 1.0600120831205413e-05, + "loss": 0.8698, + "step": 8087 + }, + { + "epoch": 0.4965161607170263, + "grad_norm": 0.7834479979334735, + "learning_rate": 1.0598136053275565e-05, + "loss": 0.8523, + "step": 8088 + }, + { + "epoch": 0.4965775499554928, + "grad_norm": 0.7599373324595405, + "learning_rate": 1.05961512516982e-05, + "loss": 0.8227, + "step": 8089 + }, + { + "epoch": 0.4966389391939593, + "grad_norm": 0.7730113527863216, + "learning_rate": 1.0594166426551787e-05, + "loss": 0.8604, + "step": 8090 + }, + { + "epoch": 0.4967003284324258, + "grad_norm": 0.7754741029419009, + "learning_rate": 1.0592181577914798e-05, + "loss": 0.8287, + "step": 8091 + }, + { + "epoch": 0.4967617176708923, + "grad_norm": 0.8166783325196567, + "learning_rate": 1.05901967058657e-05, + "loss": 0.8576, + "step": 8092 + }, + { + "epoch": 0.49682310690935877, + "grad_norm": 0.9037036646628716, + "learning_rate": 1.0588211810482974e-05, + "loss": 0.8981, + "step": 8093 + }, + { + "epoch": 0.49688449614782526, + "grad_norm": 0.8007712913693377, + "learning_rate": 1.0586226891845086e-05, + "loss": 0.867, + "step": 8094 + }, + { + "epoch": 0.4969458853862918, + "grad_norm": 0.7960110448013458, + "learning_rate": 1.0584241950030515e-05, + "loss": 0.8685, + "step": 8095 + }, + { + "epoch": 0.4970072746247583, + "grad_norm": 0.6866905553511655, + "learning_rate": 1.0582256985117735e-05, + "loss": 0.843, + "step": 8096 + }, + { + "epoch": 0.4970686638632248, + "grad_norm": 0.8431065398837508, + "learning_rate": 1.058027199718522e-05, + "loss": 0.8886, + "step": 8097 + }, + { + "epoch": 0.4971300531016913, + "grad_norm": 0.6771568744327517, + "learning_rate": 1.0578286986311454e-05, + "loss": 0.8023, + "step": 8098 + }, + { + "epoch": 0.4971914423401578, + "grad_norm": 0.7211735401791374, + "learning_rate": 1.0576301952574908e-05, + "loss": 0.842, + "step": 8099 + }, + { + "epoch": 0.49725283157862427, + "grad_norm": 0.7522530141172098, + "learning_rate": 1.0574316896054066e-05, + "loss": 0.8362, + "step": 8100 + }, + { + "epoch": 0.49731422081709076, + "grad_norm": 0.8139367750374666, + "learning_rate": 1.0572331816827402e-05, + "loss": 0.8295, + "step": 8101 + }, + { + "epoch": 0.49737561005555725, + "grad_norm": 0.8109991876367179, + "learning_rate": 1.0570346714973401e-05, + "loss": 0.8186, + "step": 8102 + }, + { + "epoch": 0.49743699929402374, + "grad_norm": 0.8528449849778423, + "learning_rate": 1.0568361590570546e-05, + "loss": 0.7771, + "step": 8103 + }, + { + "epoch": 0.49749838853249023, + "grad_norm": 0.8363309125052631, + "learning_rate": 1.0566376443697315e-05, + "loss": 0.8583, + "step": 8104 + }, + { + "epoch": 0.4975597777709567, + "grad_norm": 0.7972894437490355, + "learning_rate": 1.0564391274432196e-05, + "loss": 0.8703, + "step": 8105 + }, + { + "epoch": 0.49762116700942327, + "grad_norm": 0.819576996197453, + "learning_rate": 1.0562406082853668e-05, + "loss": 0.8319, + "step": 8106 + }, + { + "epoch": 0.49768255624788976, + "grad_norm": 0.7307676093102743, + "learning_rate": 1.0560420869040221e-05, + "loss": 0.8376, + "step": 8107 + }, + { + "epoch": 0.49774394548635625, + "grad_norm": 0.8280265426274517, + "learning_rate": 1.0558435633070342e-05, + "loss": 0.8751, + "step": 8108 + }, + { + "epoch": 0.49780533472482275, + "grad_norm": 0.7595524139254805, + "learning_rate": 1.0556450375022516e-05, + "loss": 0.8341, + "step": 8109 + }, + { + "epoch": 0.49786672396328924, + "grad_norm": 0.7492804348223865, + "learning_rate": 1.0554465094975227e-05, + "loss": 0.7984, + "step": 8110 + }, + { + "epoch": 0.49792811320175573, + "grad_norm": 0.838568762475531, + "learning_rate": 1.055247979300697e-05, + "loss": 0.8565, + "step": 8111 + }, + { + "epoch": 0.4979895024402222, + "grad_norm": 0.8629955226573118, + "learning_rate": 1.055049446919623e-05, + "loss": 0.8609, + "step": 8112 + }, + { + "epoch": 0.4980508916786887, + "grad_norm": 0.8069994274489426, + "learning_rate": 1.05485091236215e-05, + "loss": 0.8786, + "step": 8113 + }, + { + "epoch": 0.4981122809171552, + "grad_norm": 0.7022123911834032, + "learning_rate": 1.0546523756361271e-05, + "loss": 0.8157, + "step": 8114 + }, + { + "epoch": 0.4981736701556217, + "grad_norm": 0.8621632551888955, + "learning_rate": 1.0544538367494037e-05, + "loss": 0.8751, + "step": 8115 + }, + { + "epoch": 0.49823505939408824, + "grad_norm": 0.7249855705481296, + "learning_rate": 1.0542552957098287e-05, + "loss": 0.8673, + "step": 8116 + }, + { + "epoch": 0.49829644863255473, + "grad_norm": 0.7487044388615293, + "learning_rate": 1.0540567525252517e-05, + "loss": 0.826, + "step": 8117 + }, + { + "epoch": 0.4983578378710212, + "grad_norm": 0.7583789365665428, + "learning_rate": 1.0538582072035221e-05, + "loss": 0.8252, + "step": 8118 + }, + { + "epoch": 0.4984192271094877, + "grad_norm": 0.8233949788179544, + "learning_rate": 1.0536596597524892e-05, + "loss": 0.8522, + "step": 8119 + }, + { + "epoch": 0.4984806163479542, + "grad_norm": 0.8096379041846304, + "learning_rate": 1.0534611101800034e-05, + "loss": 0.8829, + "step": 8120 + }, + { + "epoch": 0.4985420055864207, + "grad_norm": 0.8543722426869941, + "learning_rate": 1.053262558493914e-05, + "loss": 0.8256, + "step": 8121 + }, + { + "epoch": 0.4986033948248872, + "grad_norm": 0.7712047535780131, + "learning_rate": 1.0530640047020708e-05, + "loss": 0.8938, + "step": 8122 + }, + { + "epoch": 0.4986647840633537, + "grad_norm": 0.814295385687819, + "learning_rate": 1.0528654488123236e-05, + "loss": 0.8339, + "step": 8123 + }, + { + "epoch": 0.4987261733018202, + "grad_norm": 0.8005211113713983, + "learning_rate": 1.0526668908325222e-05, + "loss": 0.8858, + "step": 8124 + }, + { + "epoch": 0.49878756254028667, + "grad_norm": 0.8047598782150538, + "learning_rate": 1.0524683307705175e-05, + "loss": 0.8711, + "step": 8125 + }, + { + "epoch": 0.49884895177875316, + "grad_norm": 0.8446054712884769, + "learning_rate": 1.0522697686341585e-05, + "loss": 0.8282, + "step": 8126 + }, + { + "epoch": 0.4989103410172197, + "grad_norm": 0.7485530562807406, + "learning_rate": 1.0520712044312963e-05, + "loss": 0.8709, + "step": 8127 + }, + { + "epoch": 0.4989717302556862, + "grad_norm": 0.7881785501554268, + "learning_rate": 1.0518726381697807e-05, + "loss": 0.8318, + "step": 8128 + }, + { + "epoch": 0.4990331194941527, + "grad_norm": 0.8268247539238197, + "learning_rate": 1.0516740698574624e-05, + "loss": 0.8458, + "step": 8129 + }, + { + "epoch": 0.4990945087326192, + "grad_norm": 0.7609059181640994, + "learning_rate": 1.0514754995021918e-05, + "loss": 0.8704, + "step": 8130 + }, + { + "epoch": 0.49915589797108567, + "grad_norm": 0.7618416022684619, + "learning_rate": 1.0512769271118193e-05, + "loss": 0.8734, + "step": 8131 + }, + { + "epoch": 0.49921728720955216, + "grad_norm": 0.7178905097828414, + "learning_rate": 1.0510783526941959e-05, + "loss": 0.8233, + "step": 8132 + }, + { + "epoch": 0.49927867644801865, + "grad_norm": 0.8207802544250351, + "learning_rate": 1.0508797762571714e-05, + "loss": 0.8725, + "step": 8133 + }, + { + "epoch": 0.49934006568648515, + "grad_norm": 0.7553703856969339, + "learning_rate": 1.0506811978085977e-05, + "loss": 0.8202, + "step": 8134 + }, + { + "epoch": 0.49940145492495164, + "grad_norm": 0.8111377453319283, + "learning_rate": 1.0504826173563252e-05, + "loss": 0.8328, + "step": 8135 + }, + { + "epoch": 0.49946284416341813, + "grad_norm": 0.749203101096755, + "learning_rate": 1.0502840349082046e-05, + "loss": 0.8292, + "step": 8136 + }, + { + "epoch": 0.4995242334018847, + "grad_norm": 0.7755586591499428, + "learning_rate": 1.0500854504720874e-05, + "loss": 0.8729, + "step": 8137 + }, + { + "epoch": 0.49958562264035117, + "grad_norm": 0.7643166123368901, + "learning_rate": 1.0498868640558242e-05, + "loss": 0.8345, + "step": 8138 + }, + { + "epoch": 0.49964701187881766, + "grad_norm": 0.7363170194142261, + "learning_rate": 1.0496882756672667e-05, + "loss": 0.8693, + "step": 8139 + }, + { + "epoch": 0.49970840111728415, + "grad_norm": 0.7946401392523916, + "learning_rate": 1.0494896853142658e-05, + "loss": 0.8251, + "step": 8140 + }, + { + "epoch": 0.49976979035575064, + "grad_norm": 0.7305996171376934, + "learning_rate": 1.049291093004673e-05, + "loss": 0.8198, + "step": 8141 + }, + { + "epoch": 0.49983117959421713, + "grad_norm": 0.84231164309886, + "learning_rate": 1.0490924987463396e-05, + "loss": 0.8765, + "step": 8142 + }, + { + "epoch": 0.4998925688326836, + "grad_norm": 0.7420521059204481, + "learning_rate": 1.0488939025471172e-05, + "loss": 0.8395, + "step": 8143 + }, + { + "epoch": 0.4999539580711501, + "grad_norm": 0.8373997168625087, + "learning_rate": 1.0486953044148573e-05, + "loss": 0.8381, + "step": 8144 + }, + { + "epoch": 0.5000153473096166, + "grad_norm": 0.8062658149561238, + "learning_rate": 1.0484967043574114e-05, + "loss": 0.8753, + "step": 8145 + }, + { + "epoch": 0.5000767365480832, + "grad_norm": 0.7429654722138886, + "learning_rate": 1.0482981023826318e-05, + "loss": 0.8741, + "step": 8146 + }, + { + "epoch": 0.5001381257865496, + "grad_norm": 0.7531567902968014, + "learning_rate": 1.0480994984983696e-05, + "loss": 0.8586, + "step": 8147 + }, + { + "epoch": 0.5001995150250161, + "grad_norm": 0.8015971765149105, + "learning_rate": 1.0479008927124772e-05, + "loss": 0.8347, + "step": 8148 + }, + { + "epoch": 0.5002609042634826, + "grad_norm": 0.7731657531868377, + "learning_rate": 1.0477022850328063e-05, + "loss": 0.8282, + "step": 8149 + }, + { + "epoch": 0.5003222935019491, + "grad_norm": 0.8088536911094727, + "learning_rate": 1.0475036754672087e-05, + "loss": 0.8321, + "step": 8150 + }, + { + "epoch": 0.5003836827404156, + "grad_norm": 0.7917309564989153, + "learning_rate": 1.0473050640235367e-05, + "loss": 0.8175, + "step": 8151 + }, + { + "epoch": 0.5004450719788821, + "grad_norm": 0.749343188715656, + "learning_rate": 1.0471064507096427e-05, + "loss": 0.8339, + "step": 8152 + }, + { + "epoch": 0.5005064612173487, + "grad_norm": 0.7923104848996703, + "learning_rate": 1.0469078355333788e-05, + "loss": 0.882, + "step": 8153 + }, + { + "epoch": 0.5005678504558151, + "grad_norm": 0.7417387590082674, + "learning_rate": 1.0467092185025973e-05, + "loss": 0.8474, + "step": 8154 + }, + { + "epoch": 0.5006292396942816, + "grad_norm": 0.7423453914335326, + "learning_rate": 1.0465105996251505e-05, + "loss": 0.8246, + "step": 8155 + }, + { + "epoch": 0.5006906289327481, + "grad_norm": 0.8233741380000854, + "learning_rate": 1.0463119789088907e-05, + "loss": 0.8132, + "step": 8156 + }, + { + "epoch": 0.5007520181712146, + "grad_norm": 0.8420193306271215, + "learning_rate": 1.0461133563616712e-05, + "loss": 0.8186, + "step": 8157 + }, + { + "epoch": 0.500813407409681, + "grad_norm": 0.8159430216457101, + "learning_rate": 1.0459147319913436e-05, + "loss": 0.8836, + "step": 8158 + }, + { + "epoch": 0.5008747966481476, + "grad_norm": 0.7543858687550727, + "learning_rate": 1.0457161058057614e-05, + "loss": 0.8652, + "step": 8159 + }, + { + "epoch": 0.500936185886614, + "grad_norm": 0.8129840454879713, + "learning_rate": 1.045517477812777e-05, + "loss": 0.8232, + "step": 8160 + }, + { + "epoch": 0.5009975751250806, + "grad_norm": 0.7410821670920709, + "learning_rate": 1.045318848020243e-05, + "loss": 0.8177, + "step": 8161 + }, + { + "epoch": 0.501058964363547, + "grad_norm": 0.7781025149657855, + "learning_rate": 1.0451202164360128e-05, + "loss": 0.898, + "step": 8162 + }, + { + "epoch": 0.5011203536020136, + "grad_norm": 0.8137469468746555, + "learning_rate": 1.044921583067939e-05, + "loss": 0.8359, + "step": 8163 + }, + { + "epoch": 0.5011817428404801, + "grad_norm": 0.8138429184858407, + "learning_rate": 1.044722947923875e-05, + "loss": 0.8553, + "step": 8164 + }, + { + "epoch": 0.5012431320789466, + "grad_norm": 0.7596235970007692, + "learning_rate": 1.0445243110116733e-05, + "loss": 0.8267, + "step": 8165 + }, + { + "epoch": 0.5013045213174131, + "grad_norm": 0.8466228526906301, + "learning_rate": 1.0443256723391877e-05, + "loss": 0.8761, + "step": 8166 + }, + { + "epoch": 0.5013659105558795, + "grad_norm": 0.8025886101371839, + "learning_rate": 1.0441270319142711e-05, + "loss": 0.8201, + "step": 8167 + }, + { + "epoch": 0.5014272997943461, + "grad_norm": 0.8594978505345918, + "learning_rate": 1.0439283897447768e-05, + "loss": 0.8564, + "step": 8168 + }, + { + "epoch": 0.5014886890328125, + "grad_norm": 0.8580159958016067, + "learning_rate": 1.0437297458385587e-05, + "loss": 0.8184, + "step": 8169 + }, + { + "epoch": 0.5015500782712791, + "grad_norm": 0.7497565770103138, + "learning_rate": 1.0435311002034697e-05, + "loss": 0.8599, + "step": 8170 + }, + { + "epoch": 0.5016114675097455, + "grad_norm": 0.7962509810147969, + "learning_rate": 1.0433324528473632e-05, + "loss": 0.856, + "step": 8171 + }, + { + "epoch": 0.501672856748212, + "grad_norm": 0.5833609898584459, + "learning_rate": 1.0431338037780934e-05, + "loss": 0.6689, + "step": 8172 + }, + { + "epoch": 0.5017342459866785, + "grad_norm": 0.92786273216212, + "learning_rate": 1.0429351530035137e-05, + "loss": 0.8928, + "step": 8173 + }, + { + "epoch": 0.501795635225145, + "grad_norm": 0.8083635672391106, + "learning_rate": 1.0427365005314776e-05, + "loss": 0.9535, + "step": 8174 + }, + { + "epoch": 0.5018570244636116, + "grad_norm": 0.77754706676551, + "learning_rate": 1.042537846369839e-05, + "loss": 0.8408, + "step": 8175 + }, + { + "epoch": 0.501918413702078, + "grad_norm": 0.7490446814139738, + "learning_rate": 1.0423391905264519e-05, + "loss": 0.8715, + "step": 8176 + }, + { + "epoch": 0.5019798029405446, + "grad_norm": 0.8125614841214049, + "learning_rate": 1.0421405330091701e-05, + "loss": 0.8436, + "step": 8177 + }, + { + "epoch": 0.502041192179011, + "grad_norm": 0.5834681496436438, + "learning_rate": 1.0419418738258475e-05, + "loss": 0.6733, + "step": 8178 + }, + { + "epoch": 0.5021025814174775, + "grad_norm": 0.8601376746175708, + "learning_rate": 1.0417432129843389e-05, + "loss": 0.8579, + "step": 8179 + }, + { + "epoch": 0.502163970655944, + "grad_norm": 0.7901146767849688, + "learning_rate": 1.0415445504924973e-05, + "loss": 0.8723, + "step": 8180 + }, + { + "epoch": 0.5022253598944105, + "grad_norm": 0.8135647633067568, + "learning_rate": 1.0413458863581775e-05, + "loss": 0.8107, + "step": 8181 + }, + { + "epoch": 0.502286749132877, + "grad_norm": 0.8014831936223579, + "learning_rate": 1.0411472205892339e-05, + "loss": 0.863, + "step": 8182 + }, + { + "epoch": 0.5023481383713435, + "grad_norm": 0.8351810484243346, + "learning_rate": 1.0409485531935202e-05, + "loss": 0.8718, + "step": 8183 + }, + { + "epoch": 0.50240952760981, + "grad_norm": 0.8394967818116545, + "learning_rate": 1.0407498841788915e-05, + "loss": 0.8367, + "step": 8184 + }, + { + "epoch": 0.5024709168482765, + "grad_norm": 0.8616792218405854, + "learning_rate": 1.0405512135532019e-05, + "loss": 0.8028, + "step": 8185 + }, + { + "epoch": 0.502532306086743, + "grad_norm": 0.8049591351757391, + "learning_rate": 1.0403525413243058e-05, + "loss": 0.8476, + "step": 8186 + }, + { + "epoch": 0.5025936953252095, + "grad_norm": 0.77087057303579, + "learning_rate": 1.0401538675000582e-05, + "loss": 0.8548, + "step": 8187 + }, + { + "epoch": 0.502655084563676, + "grad_norm": 0.761148798392674, + "learning_rate": 1.0399551920883131e-05, + "loss": 0.8449, + "step": 8188 + }, + { + "epoch": 0.5027164738021425, + "grad_norm": 0.7211580262495146, + "learning_rate": 1.039756515096926e-05, + "loss": 0.8682, + "step": 8189 + }, + { + "epoch": 0.502777863040609, + "grad_norm": 0.8153494201880984, + "learning_rate": 1.0395578365337506e-05, + "loss": 0.8394, + "step": 8190 + }, + { + "epoch": 0.5028392522790754, + "grad_norm": 0.7959127763526938, + "learning_rate": 1.0393591564066428e-05, + "loss": 0.8544, + "step": 8191 + }, + { + "epoch": 0.502900641517542, + "grad_norm": 0.6987348009510699, + "learning_rate": 1.039160474723457e-05, + "loss": 0.7829, + "step": 8192 + }, + { + "epoch": 0.5029620307560084, + "grad_norm": 0.8189076586525781, + "learning_rate": 1.0389617914920481e-05, + "loss": 0.8618, + "step": 8193 + }, + { + "epoch": 0.503023419994475, + "grad_norm": 0.8129064413626282, + "learning_rate": 1.0387631067202715e-05, + "loss": 0.8617, + "step": 8194 + }, + { + "epoch": 0.5030848092329414, + "grad_norm": 0.8439116197341471, + "learning_rate": 1.0385644204159816e-05, + "loss": 0.8737, + "step": 8195 + }, + { + "epoch": 0.503146198471408, + "grad_norm": 0.7498203907719867, + "learning_rate": 1.0383657325870342e-05, + "loss": 0.812, + "step": 8196 + }, + { + "epoch": 0.5032075877098745, + "grad_norm": 0.6208407684808316, + "learning_rate": 1.0381670432412837e-05, + "loss": 0.6958, + "step": 8197 + }, + { + "epoch": 0.5032689769483409, + "grad_norm": 0.7886709408349328, + "learning_rate": 1.0379683523865863e-05, + "loss": 0.839, + "step": 8198 + }, + { + "epoch": 0.5033303661868075, + "grad_norm": 0.8478427770352788, + "learning_rate": 1.0377696600307967e-05, + "loss": 0.8977, + "step": 8199 + }, + { + "epoch": 0.5033917554252739, + "grad_norm": 0.8423628445778631, + "learning_rate": 1.0375709661817703e-05, + "loss": 0.8617, + "step": 8200 + }, + { + "epoch": 0.5034531446637405, + "grad_norm": 0.806631380957543, + "learning_rate": 1.037372270847363e-05, + "loss": 0.8658, + "step": 8201 + }, + { + "epoch": 0.5035145339022069, + "grad_norm": 0.7565986617327123, + "learning_rate": 1.0371735740354296e-05, + "loss": 0.8152, + "step": 8202 + }, + { + "epoch": 0.5035759231406735, + "grad_norm": 0.8027524528938587, + "learning_rate": 1.0369748757538263e-05, + "loss": 0.8548, + "step": 8203 + }, + { + "epoch": 0.5036373123791399, + "grad_norm": 0.8014043045087422, + "learning_rate": 1.0367761760104083e-05, + "loss": 0.8478, + "step": 8204 + }, + { + "epoch": 0.5036987016176064, + "grad_norm": 0.8515742477457712, + "learning_rate": 1.0365774748130315e-05, + "loss": 0.8831, + "step": 8205 + }, + { + "epoch": 0.503760090856073, + "grad_norm": 0.7367789338167421, + "learning_rate": 1.0363787721695514e-05, + "loss": 0.7949, + "step": 8206 + }, + { + "epoch": 0.5038214800945394, + "grad_norm": 0.7450117819479481, + "learning_rate": 1.0361800680878235e-05, + "loss": 0.8132, + "step": 8207 + }, + { + "epoch": 0.503882869333006, + "grad_norm": 0.728973037580976, + "learning_rate": 1.0359813625757044e-05, + "loss": 0.8333, + "step": 8208 + }, + { + "epoch": 0.5039442585714724, + "grad_norm": 0.8356351300680904, + "learning_rate": 1.0357826556410495e-05, + "loss": 0.8151, + "step": 8209 + }, + { + "epoch": 0.504005647809939, + "grad_norm": 0.6905683434912586, + "learning_rate": 1.0355839472917148e-05, + "loss": 0.7808, + "step": 8210 + }, + { + "epoch": 0.5040670370484054, + "grad_norm": 0.8797832025621121, + "learning_rate": 1.0353852375355564e-05, + "loss": 0.8458, + "step": 8211 + }, + { + "epoch": 0.5041284262868719, + "grad_norm": 0.7561940746569219, + "learning_rate": 1.0351865263804304e-05, + "loss": 0.8558, + "step": 8212 + }, + { + "epoch": 0.5041898155253384, + "grad_norm": 0.8060002848980002, + "learning_rate": 1.034987813834193e-05, + "loss": 0.8221, + "step": 8213 + }, + { + "epoch": 0.5042512047638049, + "grad_norm": 0.7636711605174061, + "learning_rate": 1.0347890999046998e-05, + "loss": 0.82, + "step": 8214 + }, + { + "epoch": 0.5043125940022714, + "grad_norm": 0.874689186456709, + "learning_rate": 1.0345903845998073e-05, + "loss": 0.806, + "step": 8215 + }, + { + "epoch": 0.5043739832407379, + "grad_norm": 0.8171468148807828, + "learning_rate": 1.0343916679273721e-05, + "loss": 0.8664, + "step": 8216 + }, + { + "epoch": 0.5044353724792044, + "grad_norm": 0.8574085056544407, + "learning_rate": 1.0341929498952506e-05, + "loss": 0.8687, + "step": 8217 + }, + { + "epoch": 0.5044967617176709, + "grad_norm": 0.7347239622392694, + "learning_rate": 1.0339942305112986e-05, + "loss": 0.8702, + "step": 8218 + }, + { + "epoch": 0.5045581509561374, + "grad_norm": 0.7971262360590374, + "learning_rate": 1.033795509783373e-05, + "loss": 0.8489, + "step": 8219 + }, + { + "epoch": 0.5046195401946039, + "grad_norm": 0.8178046191181193, + "learning_rate": 1.0335967877193299e-05, + "loss": 0.8243, + "step": 8220 + }, + { + "epoch": 0.5046809294330704, + "grad_norm": 0.7299509629607746, + "learning_rate": 1.0333980643270264e-05, + "loss": 0.8166, + "step": 8221 + }, + { + "epoch": 0.5047423186715368, + "grad_norm": 0.7398565083829723, + "learning_rate": 1.0331993396143186e-05, + "loss": 0.793, + "step": 8222 + }, + { + "epoch": 0.5048037079100034, + "grad_norm": 0.821304568798222, + "learning_rate": 1.0330006135890633e-05, + "loss": 0.8096, + "step": 8223 + }, + { + "epoch": 0.5048650971484698, + "grad_norm": 0.8254410770261612, + "learning_rate": 1.0328018862591177e-05, + "loss": 0.8205, + "step": 8224 + }, + { + "epoch": 0.5049264863869364, + "grad_norm": 0.8375506378473454, + "learning_rate": 1.0326031576323374e-05, + "loss": 0.8821, + "step": 8225 + }, + { + "epoch": 0.5049878756254028, + "grad_norm": 0.8766567771634645, + "learning_rate": 1.0324044277165806e-05, + "loss": 0.8734, + "step": 8226 + }, + { + "epoch": 0.5050492648638694, + "grad_norm": 0.6821662253498683, + "learning_rate": 1.0322056965197027e-05, + "loss": 0.8141, + "step": 8227 + }, + { + "epoch": 0.5051106541023359, + "grad_norm": 0.7400583073348338, + "learning_rate": 1.032006964049562e-05, + "loss": 0.8302, + "step": 8228 + }, + { + "epoch": 0.5051720433408023, + "grad_norm": 0.808552059468962, + "learning_rate": 1.0318082303140145e-05, + "loss": 0.8582, + "step": 8229 + }, + { + "epoch": 0.5052334325792689, + "grad_norm": 0.7877658270046833, + "learning_rate": 1.0316094953209177e-05, + "loss": 0.8612, + "step": 8230 + }, + { + "epoch": 0.5052948218177353, + "grad_norm": 0.7615455556127081, + "learning_rate": 1.0314107590781284e-05, + "loss": 0.8244, + "step": 8231 + }, + { + "epoch": 0.5053562110562019, + "grad_norm": 0.7483973789105516, + "learning_rate": 1.0312120215935038e-05, + "loss": 0.831, + "step": 8232 + }, + { + "epoch": 0.5054176002946683, + "grad_norm": 0.8456323768225592, + "learning_rate": 1.0310132828749013e-05, + "loss": 0.8279, + "step": 8233 + }, + { + "epoch": 0.5054789895331349, + "grad_norm": 0.8354621824969872, + "learning_rate": 1.0308145429301775e-05, + "loss": 0.8437, + "step": 8234 + }, + { + "epoch": 0.5055403787716013, + "grad_norm": 0.7265661601152673, + "learning_rate": 1.03061580176719e-05, + "loss": 0.8252, + "step": 8235 + }, + { + "epoch": 0.5056017680100678, + "grad_norm": 0.8015424697052451, + "learning_rate": 1.0304170593937963e-05, + "loss": 0.8437, + "step": 8236 + }, + { + "epoch": 0.5056631572485343, + "grad_norm": 0.7700153743520282, + "learning_rate": 1.0302183158178535e-05, + "loss": 0.8835, + "step": 8237 + }, + { + "epoch": 0.5057245464870008, + "grad_norm": 0.7208669168037687, + "learning_rate": 1.0300195710472191e-05, + "loss": 0.8596, + "step": 8238 + }, + { + "epoch": 0.5057859357254674, + "grad_norm": 0.840182445022528, + "learning_rate": 1.0298208250897504e-05, + "loss": 0.8569, + "step": 8239 + }, + { + "epoch": 0.5058473249639338, + "grad_norm": 0.7801141634317997, + "learning_rate": 1.029622077953305e-05, + "loss": 0.8545, + "step": 8240 + }, + { + "epoch": 0.5059087142024004, + "grad_norm": 0.5872294945392007, + "learning_rate": 1.0294233296457407e-05, + "loss": 0.6596, + "step": 8241 + }, + { + "epoch": 0.5059701034408668, + "grad_norm": 0.7861883744632597, + "learning_rate": 1.0292245801749146e-05, + "loss": 0.8276, + "step": 8242 + }, + { + "epoch": 0.5060314926793333, + "grad_norm": 0.7833106032413898, + "learning_rate": 1.0290258295486846e-05, + "loss": 0.8504, + "step": 8243 + }, + { + "epoch": 0.5060928819177998, + "grad_norm": 0.8374725154560833, + "learning_rate": 1.0288270777749083e-05, + "loss": 0.8468, + "step": 8244 + }, + { + "epoch": 0.5061542711562663, + "grad_norm": 0.8370115311168839, + "learning_rate": 1.0286283248614435e-05, + "loss": 0.9087, + "step": 8245 + }, + { + "epoch": 0.5062156603947328, + "grad_norm": 0.7760258205783364, + "learning_rate": 1.0284295708161476e-05, + "loss": 0.8744, + "step": 8246 + }, + { + "epoch": 0.5062770496331993, + "grad_norm": 0.7873395213713053, + "learning_rate": 1.028230815646879e-05, + "loss": 0.8679, + "step": 8247 + }, + { + "epoch": 0.5063384388716659, + "grad_norm": 0.8190174586531614, + "learning_rate": 1.0280320593614952e-05, + "loss": 0.8101, + "step": 8248 + }, + { + "epoch": 0.5063998281101323, + "grad_norm": 0.7076100995267697, + "learning_rate": 1.0278333019678542e-05, + "loss": 0.8444, + "step": 8249 + }, + { + "epoch": 0.5064612173485988, + "grad_norm": 0.6095228724017883, + "learning_rate": 1.0276345434738137e-05, + "loss": 0.7113, + "step": 8250 + }, + { + "epoch": 0.5065226065870653, + "grad_norm": 0.7711674308235071, + "learning_rate": 1.0274357838872322e-05, + "loss": 0.8425, + "step": 8251 + }, + { + "epoch": 0.5065839958255318, + "grad_norm": 0.8562563797399144, + "learning_rate": 1.0272370232159672e-05, + "loss": 0.8485, + "step": 8252 + }, + { + "epoch": 0.5066453850639983, + "grad_norm": 0.7222361881209918, + "learning_rate": 1.0270382614678774e-05, + "loss": 0.8384, + "step": 8253 + }, + { + "epoch": 0.5067067743024648, + "grad_norm": 0.9275896261951784, + "learning_rate": 1.02683949865082e-05, + "loss": 0.8721, + "step": 8254 + }, + { + "epoch": 0.5067681635409312, + "grad_norm": 0.8552884195366208, + "learning_rate": 1.0266407347726538e-05, + "loss": 0.8302, + "step": 8255 + }, + { + "epoch": 0.5068295527793978, + "grad_norm": 0.6789915868080664, + "learning_rate": 1.0264419698412368e-05, + "loss": 0.8065, + "step": 8256 + }, + { + "epoch": 0.5068909420178642, + "grad_norm": 0.8337328622890743, + "learning_rate": 1.0262432038644275e-05, + "loss": 0.8062, + "step": 8257 + }, + { + "epoch": 0.5069523312563308, + "grad_norm": 0.8216480265986805, + "learning_rate": 1.0260444368500841e-05, + "loss": 0.8673, + "step": 8258 + }, + { + "epoch": 0.5070137204947973, + "grad_norm": 0.765487739183549, + "learning_rate": 1.0258456688060645e-05, + "loss": 0.7937, + "step": 8259 + }, + { + "epoch": 0.5070751097332638, + "grad_norm": 0.8351363544014787, + "learning_rate": 1.0256468997402278e-05, + "loss": 0.8419, + "step": 8260 + }, + { + "epoch": 0.5071364989717303, + "grad_norm": 0.7897915462251375, + "learning_rate": 1.0254481296604315e-05, + "loss": 0.8373, + "step": 8261 + }, + { + "epoch": 0.5071978882101967, + "grad_norm": 0.8594856243931696, + "learning_rate": 1.025249358574535e-05, + "loss": 0.8898, + "step": 8262 + }, + { + "epoch": 0.5072592774486633, + "grad_norm": 0.8132132765660156, + "learning_rate": 1.0250505864903958e-05, + "loss": 0.8667, + "step": 8263 + }, + { + "epoch": 0.5073206666871297, + "grad_norm": 0.8158143889927636, + "learning_rate": 1.024851813415873e-05, + "loss": 0.8568, + "step": 8264 + }, + { + "epoch": 0.5073820559255963, + "grad_norm": 0.8717497714172574, + "learning_rate": 1.0246530393588256e-05, + "loss": 0.8427, + "step": 8265 + }, + { + "epoch": 0.5074434451640627, + "grad_norm": 0.7485864573154424, + "learning_rate": 1.0244542643271113e-05, + "loss": 0.8366, + "step": 8266 + }, + { + "epoch": 0.5075048344025292, + "grad_norm": 0.8075441998575159, + "learning_rate": 1.0242554883285893e-05, + "loss": 0.8165, + "step": 8267 + }, + { + "epoch": 0.5075662236409957, + "grad_norm": 0.8144540751239252, + "learning_rate": 1.0240567113711181e-05, + "loss": 0.8702, + "step": 8268 + }, + { + "epoch": 0.5076276128794622, + "grad_norm": 0.748578446081729, + "learning_rate": 1.0238579334625565e-05, + "loss": 0.8615, + "step": 8269 + }, + { + "epoch": 0.5076890021179288, + "grad_norm": 0.7302784736185055, + "learning_rate": 1.023659154610763e-05, + "loss": 0.8422, + "step": 8270 + }, + { + "epoch": 0.5077503913563952, + "grad_norm": 0.7019355171728857, + "learning_rate": 1.0234603748235965e-05, + "loss": 0.7929, + "step": 8271 + }, + { + "epoch": 0.5078117805948618, + "grad_norm": 0.7864963007077947, + "learning_rate": 1.0232615941089161e-05, + "loss": 0.8425, + "step": 8272 + }, + { + "epoch": 0.5078731698333282, + "grad_norm": 0.717265515597853, + "learning_rate": 1.0230628124745805e-05, + "loss": 0.8079, + "step": 8273 + }, + { + "epoch": 0.5079345590717947, + "grad_norm": 0.8021442498411312, + "learning_rate": 1.0228640299284487e-05, + "loss": 0.873, + "step": 8274 + }, + { + "epoch": 0.5079959483102612, + "grad_norm": 0.8078689168719777, + "learning_rate": 1.0226652464783792e-05, + "loss": 0.8523, + "step": 8275 + }, + { + "epoch": 0.5080573375487277, + "grad_norm": 0.7607856749707483, + "learning_rate": 1.0224664621322315e-05, + "loss": 0.884, + "step": 8276 + }, + { + "epoch": 0.5081187267871942, + "grad_norm": 0.7568533632612748, + "learning_rate": 1.0222676768978643e-05, + "loss": 0.8705, + "step": 8277 + }, + { + "epoch": 0.5081801160256607, + "grad_norm": 0.7373668754090051, + "learning_rate": 1.0220688907831367e-05, + "loss": 0.861, + "step": 8278 + }, + { + "epoch": 0.5082415052641271, + "grad_norm": 0.8609664998092577, + "learning_rate": 1.0218701037959077e-05, + "loss": 0.8165, + "step": 8279 + }, + { + "epoch": 0.5083028945025937, + "grad_norm": 0.8373885749805191, + "learning_rate": 1.0216713159440368e-05, + "loss": 0.8772, + "step": 8280 + }, + { + "epoch": 0.5083642837410602, + "grad_norm": 0.819766983052478, + "learning_rate": 1.021472527235383e-05, + "loss": 0.892, + "step": 8281 + }, + { + "epoch": 0.5084256729795267, + "grad_norm": 0.9218008216622996, + "learning_rate": 1.021273737677805e-05, + "loss": 0.8441, + "step": 8282 + }, + { + "epoch": 0.5084870622179932, + "grad_norm": 0.8292993213863095, + "learning_rate": 1.0210749472791625e-05, + "loss": 0.8347, + "step": 8283 + }, + { + "epoch": 0.5085484514564597, + "grad_norm": 0.7226985816466962, + "learning_rate": 1.0208761560473144e-05, + "loss": 0.81, + "step": 8284 + }, + { + "epoch": 0.5086098406949262, + "grad_norm": 0.8150249605467137, + "learning_rate": 1.0206773639901206e-05, + "loss": 0.841, + "step": 8285 + }, + { + "epoch": 0.5086712299333926, + "grad_norm": 0.7069390509745064, + "learning_rate": 1.0204785711154397e-05, + "loss": 0.8314, + "step": 8286 + }, + { + "epoch": 0.5087326191718592, + "grad_norm": 0.7006516990381357, + "learning_rate": 1.0202797774311315e-05, + "loss": 0.8068, + "step": 8287 + }, + { + "epoch": 0.5087940084103256, + "grad_norm": 0.7979148570623361, + "learning_rate": 1.0200809829450553e-05, + "loss": 0.8712, + "step": 8288 + }, + { + "epoch": 0.5088553976487922, + "grad_norm": 0.7903353012815924, + "learning_rate": 1.0198821876650702e-05, + "loss": 0.7942, + "step": 8289 + }, + { + "epoch": 0.5089167868872586, + "grad_norm": 0.908142068894723, + "learning_rate": 1.0196833915990363e-05, + "loss": 0.8524, + "step": 8290 + }, + { + "epoch": 0.5089781761257252, + "grad_norm": 0.7978234727256842, + "learning_rate": 1.0194845947548122e-05, + "loss": 0.8823, + "step": 8291 + }, + { + "epoch": 0.5090395653641917, + "grad_norm": 0.748094844898223, + "learning_rate": 1.0192857971402582e-05, + "loss": 0.875, + "step": 8292 + }, + { + "epoch": 0.5091009546026581, + "grad_norm": 0.8092579045203475, + "learning_rate": 1.0190869987632332e-05, + "loss": 0.8888, + "step": 8293 + }, + { + "epoch": 0.5091623438411247, + "grad_norm": 0.799037088590559, + "learning_rate": 1.0188881996315972e-05, + "loss": 0.8128, + "step": 8294 + }, + { + "epoch": 0.5092237330795911, + "grad_norm": 0.8137620442336855, + "learning_rate": 1.0186893997532098e-05, + "loss": 0.8418, + "step": 8295 + }, + { + "epoch": 0.5092851223180577, + "grad_norm": 0.7394577469672162, + "learning_rate": 1.01849059913593e-05, + "loss": 0.8218, + "step": 8296 + }, + { + "epoch": 0.5093465115565241, + "grad_norm": 0.6058923504275988, + "learning_rate": 1.0182917977876185e-05, + "loss": 0.6454, + "step": 8297 + }, + { + "epoch": 0.5094079007949907, + "grad_norm": 0.788070956568809, + "learning_rate": 1.018092995716134e-05, + "loss": 0.8544, + "step": 8298 + }, + { + "epoch": 0.5094692900334571, + "grad_norm": 0.7835978978644612, + "learning_rate": 1.0178941929293367e-05, + "loss": 0.8412, + "step": 8299 + }, + { + "epoch": 0.5095306792719236, + "grad_norm": 0.6844179423869011, + "learning_rate": 1.0176953894350863e-05, + "loss": 0.8074, + "step": 8300 + }, + { + "epoch": 0.5095920685103902, + "grad_norm": 0.8107631959090965, + "learning_rate": 1.0174965852412426e-05, + "loss": 0.8227, + "step": 8301 + }, + { + "epoch": 0.5096534577488566, + "grad_norm": 0.7751236245968706, + "learning_rate": 1.0172977803556651e-05, + "loss": 0.8618, + "step": 8302 + }, + { + "epoch": 0.5097148469873232, + "grad_norm": 0.8510657722866714, + "learning_rate": 1.017098974786214e-05, + "loss": 0.8471, + "step": 8303 + }, + { + "epoch": 0.5097762362257896, + "grad_norm": 0.8500654446178928, + "learning_rate": 1.0169001685407489e-05, + "loss": 0.8419, + "step": 8304 + }, + { + "epoch": 0.5098376254642562, + "grad_norm": 0.7758003903218121, + "learning_rate": 1.0167013616271298e-05, + "loss": 0.8035, + "step": 8305 + }, + { + "epoch": 0.5098990147027226, + "grad_norm": 0.7070402929641516, + "learning_rate": 1.0165025540532165e-05, + "loss": 0.8338, + "step": 8306 + }, + { + "epoch": 0.5099604039411891, + "grad_norm": 0.7710322447342333, + "learning_rate": 1.0163037458268689e-05, + "loss": 0.8346, + "step": 8307 + }, + { + "epoch": 0.5100217931796556, + "grad_norm": 0.7690751501361461, + "learning_rate": 1.0161049369559473e-05, + "loss": 0.8096, + "step": 8308 + }, + { + "epoch": 0.5100831824181221, + "grad_norm": 0.7804482825377472, + "learning_rate": 1.0159061274483113e-05, + "loss": 0.833, + "step": 8309 + }, + { + "epoch": 0.5101445716565886, + "grad_norm": 0.7645385921358383, + "learning_rate": 1.0157073173118207e-05, + "loss": 0.762, + "step": 8310 + }, + { + "epoch": 0.5102059608950551, + "grad_norm": 0.7150070448846851, + "learning_rate": 1.0155085065543361e-05, + "loss": 0.8181, + "step": 8311 + }, + { + "epoch": 0.5102673501335216, + "grad_norm": 0.7898054227899693, + "learning_rate": 1.0153096951837174e-05, + "loss": 0.8252, + "step": 8312 + }, + { + "epoch": 0.5103287393719881, + "grad_norm": 0.7886768494541317, + "learning_rate": 1.0151108832078245e-05, + "loss": 0.8124, + "step": 8313 + }, + { + "epoch": 0.5103901286104546, + "grad_norm": 0.7701174519227554, + "learning_rate": 1.0149120706345175e-05, + "loss": 0.8459, + "step": 8314 + }, + { + "epoch": 0.5104515178489211, + "grad_norm": 0.7430736163225438, + "learning_rate": 1.0147132574716565e-05, + "loss": 0.8244, + "step": 8315 + }, + { + "epoch": 0.5105129070873876, + "grad_norm": 0.758747166111702, + "learning_rate": 1.0145144437271017e-05, + "loss": 0.8156, + "step": 8316 + }, + { + "epoch": 0.510574296325854, + "grad_norm": 0.8082334412347162, + "learning_rate": 1.0143156294087135e-05, + "loss": 0.8529, + "step": 8317 + }, + { + "epoch": 0.5106356855643206, + "grad_norm": 0.7480045858880867, + "learning_rate": 1.0141168145243519e-05, + "loss": 0.8102, + "step": 8318 + }, + { + "epoch": 0.510697074802787, + "grad_norm": 0.8235715841944502, + "learning_rate": 1.013917999081877e-05, + "loss": 0.8601, + "step": 8319 + }, + { + "epoch": 0.5107584640412536, + "grad_norm": 0.8261520888935165, + "learning_rate": 1.0137191830891493e-05, + "loss": 0.8823, + "step": 8320 + }, + { + "epoch": 0.51081985327972, + "grad_norm": 0.8172181793739505, + "learning_rate": 1.0135203665540288e-05, + "loss": 0.8513, + "step": 8321 + }, + { + "epoch": 0.5108812425181866, + "grad_norm": 0.8104259044901022, + "learning_rate": 1.0133215494843762e-05, + "loss": 0.8106, + "step": 8322 + }, + { + "epoch": 0.5109426317566531, + "grad_norm": 0.8194187567317802, + "learning_rate": 1.013122731888051e-05, + "loss": 0.8694, + "step": 8323 + }, + { + "epoch": 0.5110040209951195, + "grad_norm": 0.7121527940377057, + "learning_rate": 1.0129239137729146e-05, + "loss": 0.7982, + "step": 8324 + }, + { + "epoch": 0.5110654102335861, + "grad_norm": 0.815071712986431, + "learning_rate": 1.0127250951468261e-05, + "loss": 0.8402, + "step": 8325 + }, + { + "epoch": 0.5111267994720525, + "grad_norm": 0.7852913446164339, + "learning_rate": 1.0125262760176468e-05, + "loss": 0.8396, + "step": 8326 + }, + { + "epoch": 0.5111881887105191, + "grad_norm": 0.7998320423240296, + "learning_rate": 1.012327456393237e-05, + "loss": 0.8525, + "step": 8327 + }, + { + "epoch": 0.5112495779489855, + "grad_norm": 0.8152236991126861, + "learning_rate": 1.0121286362814566e-05, + "loss": 0.8365, + "step": 8328 + }, + { + "epoch": 0.5113109671874521, + "grad_norm": 0.8748208087488395, + "learning_rate": 1.0119298156901669e-05, + "loss": 0.8634, + "step": 8329 + }, + { + "epoch": 0.5113723564259185, + "grad_norm": 0.8419018401034867, + "learning_rate": 1.0117309946272271e-05, + "loss": 0.8809, + "step": 8330 + }, + { + "epoch": 0.511433745664385, + "grad_norm": 0.7966601052375414, + "learning_rate": 1.0115321731004987e-05, + "loss": 0.8065, + "step": 8331 + }, + { + "epoch": 0.5114951349028515, + "grad_norm": 0.7464368574848578, + "learning_rate": 1.0113333511178418e-05, + "loss": 0.8042, + "step": 8332 + }, + { + "epoch": 0.511556524141318, + "grad_norm": 0.8223397055689013, + "learning_rate": 1.0111345286871171e-05, + "loss": 0.8499, + "step": 8333 + }, + { + "epoch": 0.5116179133797846, + "grad_norm": 0.7525442114195829, + "learning_rate": 1.0109357058161847e-05, + "loss": 0.8301, + "step": 8334 + }, + { + "epoch": 0.511679302618251, + "grad_norm": 0.9046983091741821, + "learning_rate": 1.0107368825129051e-05, + "loss": 0.8461, + "step": 8335 + }, + { + "epoch": 0.5117406918567176, + "grad_norm": 0.7896087237290671, + "learning_rate": 1.0105380587851394e-05, + "loss": 0.8314, + "step": 8336 + }, + { + "epoch": 0.511802081095184, + "grad_norm": 0.8646906478361843, + "learning_rate": 1.0103392346407478e-05, + "loss": 0.8893, + "step": 8337 + }, + { + "epoch": 0.5118634703336505, + "grad_norm": 0.7439529144605548, + "learning_rate": 1.010140410087591e-05, + "loss": 0.7967, + "step": 8338 + }, + { + "epoch": 0.511924859572117, + "grad_norm": 0.8126980902098, + "learning_rate": 1.00994158513353e-05, + "loss": 0.8316, + "step": 8339 + }, + { + "epoch": 0.5119862488105835, + "grad_norm": 0.8343744902388154, + "learning_rate": 1.0097427597864245e-05, + "loss": 0.8075, + "step": 8340 + }, + { + "epoch": 0.51204763804905, + "grad_norm": 0.816480360203534, + "learning_rate": 1.0095439340541355e-05, + "loss": 0.8303, + "step": 8341 + }, + { + "epoch": 0.5121090272875165, + "grad_norm": 0.8361391560470168, + "learning_rate": 1.0093451079445238e-05, + "loss": 0.8329, + "step": 8342 + }, + { + "epoch": 0.5121704165259829, + "grad_norm": 0.7647630220026803, + "learning_rate": 1.00914628146545e-05, + "loss": 0.8028, + "step": 8343 + }, + { + "epoch": 0.5122318057644495, + "grad_norm": 0.763444889120544, + "learning_rate": 1.008947454624775e-05, + "loss": 0.8005, + "step": 8344 + }, + { + "epoch": 0.512293195002916, + "grad_norm": 0.7997050813742347, + "learning_rate": 1.0087486274303591e-05, + "loss": 0.8548, + "step": 8345 + }, + { + "epoch": 0.5123545842413825, + "grad_norm": 0.8634823099960574, + "learning_rate": 1.0085497998900632e-05, + "loss": 0.9265, + "step": 8346 + }, + { + "epoch": 0.512415973479849, + "grad_norm": 0.790336878941551, + "learning_rate": 1.0083509720117482e-05, + "loss": 0.8447, + "step": 8347 + }, + { + "epoch": 0.5124773627183155, + "grad_norm": 0.8196154074183032, + "learning_rate": 1.008152143803274e-05, + "loss": 0.8214, + "step": 8348 + }, + { + "epoch": 0.512538751956782, + "grad_norm": 0.7912602029700425, + "learning_rate": 1.0079533152725025e-05, + "loss": 0.8397, + "step": 8349 + }, + { + "epoch": 0.5126001411952484, + "grad_norm": 0.8013202368191625, + "learning_rate": 1.0077544864272937e-05, + "loss": 0.8495, + "step": 8350 + }, + { + "epoch": 0.512661530433715, + "grad_norm": 0.803353066025815, + "learning_rate": 1.0075556572755087e-05, + "loss": 0.8475, + "step": 8351 + }, + { + "epoch": 0.5127229196721814, + "grad_norm": 0.7845795481159528, + "learning_rate": 1.0073568278250081e-05, + "loss": 0.8761, + "step": 8352 + }, + { + "epoch": 0.512784308910648, + "grad_norm": 0.801568154354439, + "learning_rate": 1.0071579980836526e-05, + "loss": 0.8117, + "step": 8353 + }, + { + "epoch": 0.5128456981491145, + "grad_norm": 0.8652087702014728, + "learning_rate": 1.0069591680593036e-05, + "loss": 0.8472, + "step": 8354 + }, + { + "epoch": 0.512907087387581, + "grad_norm": 0.8709306498144774, + "learning_rate": 1.006760337759821e-05, + "loss": 0.8779, + "step": 8355 + }, + { + "epoch": 0.5129684766260475, + "grad_norm": 0.6703699850643071, + "learning_rate": 1.0065615071930661e-05, + "loss": 0.7862, + "step": 8356 + }, + { + "epoch": 0.5130298658645139, + "grad_norm": 0.809181984820337, + "learning_rate": 1.0063626763668999e-05, + "loss": 0.8001, + "step": 8357 + }, + { + "epoch": 0.5130912551029805, + "grad_norm": 0.8728043196368059, + "learning_rate": 1.0061638452891831e-05, + "loss": 0.8182, + "step": 8358 + }, + { + "epoch": 0.5131526443414469, + "grad_norm": 0.7051087759927126, + "learning_rate": 1.0059650139677765e-05, + "loss": 0.8359, + "step": 8359 + }, + { + "epoch": 0.5132140335799135, + "grad_norm": 0.8722412605427405, + "learning_rate": 1.0057661824105409e-05, + "loss": 0.8436, + "step": 8360 + }, + { + "epoch": 0.5132754228183799, + "grad_norm": 0.8696335613886786, + "learning_rate": 1.0055673506253377e-05, + "loss": 0.8793, + "step": 8361 + }, + { + "epoch": 0.5133368120568464, + "grad_norm": 0.7653661050039222, + "learning_rate": 1.0053685186200267e-05, + "loss": 0.8628, + "step": 8362 + }, + { + "epoch": 0.5133982012953129, + "grad_norm": 0.844985797368568, + "learning_rate": 1.0051696864024699e-05, + "loss": 0.8542, + "step": 8363 + }, + { + "epoch": 0.5134595905337794, + "grad_norm": 0.8274867301747456, + "learning_rate": 1.0049708539805274e-05, + "loss": 0.8281, + "step": 8364 + }, + { + "epoch": 0.513520979772246, + "grad_norm": 0.8025833749533776, + "learning_rate": 1.0047720213620607e-05, + "loss": 0.8023, + "step": 8365 + }, + { + "epoch": 0.5135823690107124, + "grad_norm": 0.8360876155218755, + "learning_rate": 1.0045731885549303e-05, + "loss": 0.8724, + "step": 8366 + }, + { + "epoch": 0.513643758249179, + "grad_norm": 0.8154567008152768, + "learning_rate": 1.0043743555669974e-05, + "loss": 0.8578, + "step": 8367 + }, + { + "epoch": 0.5137051474876454, + "grad_norm": 0.704024492320826, + "learning_rate": 1.0041755224061229e-05, + "loss": 0.8569, + "step": 8368 + }, + { + "epoch": 0.5137665367261119, + "grad_norm": 0.806828742413585, + "learning_rate": 1.0039766890801676e-05, + "loss": 0.8708, + "step": 8369 + }, + { + "epoch": 0.5138279259645784, + "grad_norm": 0.7427763887314739, + "learning_rate": 1.0037778555969927e-05, + "loss": 0.8391, + "step": 8370 + }, + { + "epoch": 0.5138893152030449, + "grad_norm": 0.7757929545172201, + "learning_rate": 1.0035790219644589e-05, + "loss": 0.854, + "step": 8371 + }, + { + "epoch": 0.5139507044415114, + "grad_norm": 0.6941510234289264, + "learning_rate": 1.0033801881904269e-05, + "loss": 0.8423, + "step": 8372 + }, + { + "epoch": 0.5140120936799779, + "grad_norm": 0.745913501519633, + "learning_rate": 1.0031813542827581e-05, + "loss": 0.8046, + "step": 8373 + }, + { + "epoch": 0.5140734829184443, + "grad_norm": 0.765506498667368, + "learning_rate": 1.0029825202493133e-05, + "loss": 0.8293, + "step": 8374 + }, + { + "epoch": 0.5141348721569109, + "grad_norm": 0.8350977440202273, + "learning_rate": 1.0027836860979539e-05, + "loss": 0.8806, + "step": 8375 + }, + { + "epoch": 0.5141962613953774, + "grad_norm": 0.768126773969631, + "learning_rate": 1.0025848518365401e-05, + "loss": 0.8363, + "step": 8376 + }, + { + "epoch": 0.5142576506338439, + "grad_norm": 0.7929425886207884, + "learning_rate": 1.0023860174729336e-05, + "loss": 0.8489, + "step": 8377 + }, + { + "epoch": 0.5143190398723104, + "grad_norm": 0.8296591563753337, + "learning_rate": 1.002187183014995e-05, + "loss": 0.8703, + "step": 8378 + }, + { + "epoch": 0.5143804291107769, + "grad_norm": 0.7574922091366043, + "learning_rate": 1.0019883484705853e-05, + "loss": 0.8817, + "step": 8379 + }, + { + "epoch": 0.5144418183492434, + "grad_norm": 0.6860163423079187, + "learning_rate": 1.0017895138475652e-05, + "loss": 0.7942, + "step": 8380 + }, + { + "epoch": 0.5145032075877098, + "grad_norm": 0.7480610458880995, + "learning_rate": 1.0015906791537964e-05, + "loss": 0.811, + "step": 8381 + }, + { + "epoch": 0.5145645968261764, + "grad_norm": 0.7739751894132462, + "learning_rate": 1.0013918443971396e-05, + "loss": 0.8794, + "step": 8382 + }, + { + "epoch": 0.5146259860646428, + "grad_norm": 0.7686136250690371, + "learning_rate": 1.0011930095854557e-05, + "loss": 0.8064, + "step": 8383 + }, + { + "epoch": 0.5146873753031094, + "grad_norm": 0.7824542636615367, + "learning_rate": 1.0009941747266057e-05, + "loss": 0.8781, + "step": 8384 + }, + { + "epoch": 0.5147487645415758, + "grad_norm": 0.7460293246443053, + "learning_rate": 1.0007953398284505e-05, + "loss": 0.8691, + "step": 8385 + }, + { + "epoch": 0.5148101537800424, + "grad_norm": 0.7512704003177544, + "learning_rate": 1.0005965048988514e-05, + "loss": 0.8257, + "step": 8386 + }, + { + "epoch": 0.5148715430185089, + "grad_norm": 0.7479471277754763, + "learning_rate": 1.0003976699456693e-05, + "loss": 0.805, + "step": 8387 + }, + { + "epoch": 0.5149329322569753, + "grad_norm": 0.8381821016044667, + "learning_rate": 1.0001988349767653e-05, + "loss": 0.7947, + "step": 8388 + }, + { + "epoch": 0.5149943214954419, + "grad_norm": 0.7784782426657455, + "learning_rate": 1e-05, + "loss": 0.85, + "step": 8389 + }, + { + "epoch": 0.5150557107339083, + "grad_norm": 0.8014385778323838, + "learning_rate": 9.99801165023235e-06, + "loss": 0.8526, + "step": 8390 + }, + { + "epoch": 0.5151170999723749, + "grad_norm": 0.7850615920333962, + "learning_rate": 9.996023300543307e-06, + "loss": 0.861, + "step": 8391 + }, + { + "epoch": 0.5151784892108413, + "grad_norm": 0.8136835764451885, + "learning_rate": 9.994034951011489e-06, + "loss": 0.8532, + "step": 8392 + }, + { + "epoch": 0.5152398784493079, + "grad_norm": 0.8452955500698358, + "learning_rate": 9.992046601715498e-06, + "loss": 0.8204, + "step": 8393 + }, + { + "epoch": 0.5153012676877743, + "grad_norm": 0.7849641581832711, + "learning_rate": 9.990058252733946e-06, + "loss": 0.8469, + "step": 8394 + }, + { + "epoch": 0.5153626569262408, + "grad_norm": 0.7943998764541511, + "learning_rate": 9.988069904145447e-06, + "loss": 0.8246, + "step": 8395 + }, + { + "epoch": 0.5154240461647073, + "grad_norm": 0.9021721044017221, + "learning_rate": 9.986081556028606e-06, + "loss": 0.7969, + "step": 8396 + }, + { + "epoch": 0.5154854354031738, + "grad_norm": 0.7583603188160777, + "learning_rate": 9.98409320846204e-06, + "loss": 0.877, + "step": 8397 + }, + { + "epoch": 0.5155468246416404, + "grad_norm": 0.7848325262652437, + "learning_rate": 9.982104861524351e-06, + "loss": 0.8019, + "step": 8398 + }, + { + "epoch": 0.5156082138801068, + "grad_norm": 0.8706937167999148, + "learning_rate": 9.980116515294152e-06, + "loss": 0.8446, + "step": 8399 + }, + { + "epoch": 0.5156696031185733, + "grad_norm": 0.790130064891413, + "learning_rate": 9.978128169850054e-06, + "loss": 0.8681, + "step": 8400 + }, + { + "epoch": 0.5157309923570398, + "grad_norm": 0.7687971478850986, + "learning_rate": 9.976139825270666e-06, + "loss": 0.8509, + "step": 8401 + }, + { + "epoch": 0.5157923815955063, + "grad_norm": 0.7583370407161729, + "learning_rate": 9.974151481634604e-06, + "loss": 0.7756, + "step": 8402 + }, + { + "epoch": 0.5158537708339728, + "grad_norm": 0.8009631529654901, + "learning_rate": 9.972163139020466e-06, + "loss": 0.7797, + "step": 8403 + }, + { + "epoch": 0.5159151600724393, + "grad_norm": 0.7796336669059032, + "learning_rate": 9.97017479750687e-06, + "loss": 0.8401, + "step": 8404 + }, + { + "epoch": 0.5159765493109058, + "grad_norm": 0.8452746559317031, + "learning_rate": 9.96818645717242e-06, + "loss": 0.8281, + "step": 8405 + }, + { + "epoch": 0.5160379385493723, + "grad_norm": 0.7697619869227795, + "learning_rate": 9.966198118095733e-06, + "loss": 0.8788, + "step": 8406 + }, + { + "epoch": 0.5160993277878388, + "grad_norm": 0.8341690893478189, + "learning_rate": 9.964209780355418e-06, + "loss": 0.881, + "step": 8407 + }, + { + "epoch": 0.5161607170263053, + "grad_norm": 0.733369489541739, + "learning_rate": 9.962221444030077e-06, + "loss": 0.8233, + "step": 8408 + }, + { + "epoch": 0.5162221062647718, + "grad_norm": 0.7326601383486546, + "learning_rate": 9.960233109198327e-06, + "loss": 0.8447, + "step": 8409 + }, + { + "epoch": 0.5162834955032383, + "grad_norm": 0.7696323463358337, + "learning_rate": 9.958244775938773e-06, + "loss": 0.8549, + "step": 8410 + }, + { + "epoch": 0.5163448847417048, + "grad_norm": 0.8688235392715677, + "learning_rate": 9.956256444330028e-06, + "loss": 0.8486, + "step": 8411 + }, + { + "epoch": 0.5164062739801712, + "grad_norm": 0.7662926243047635, + "learning_rate": 9.9542681144507e-06, + "loss": 0.8363, + "step": 8412 + }, + { + "epoch": 0.5164676632186378, + "grad_norm": 0.7662742523959525, + "learning_rate": 9.952279786379397e-06, + "loss": 0.84, + "step": 8413 + }, + { + "epoch": 0.5165290524571042, + "grad_norm": 0.7026773885650911, + "learning_rate": 9.950291460194729e-06, + "loss": 0.7733, + "step": 8414 + }, + { + "epoch": 0.5165904416955708, + "grad_norm": 0.7760240267998588, + "learning_rate": 9.948303135975303e-06, + "loss": 0.8098, + "step": 8415 + }, + { + "epoch": 0.5166518309340372, + "grad_norm": 0.7308300141518874, + "learning_rate": 9.946314813799735e-06, + "loss": 0.8588, + "step": 8416 + }, + { + "epoch": 0.5167132201725038, + "grad_norm": 0.7395242070920799, + "learning_rate": 9.94432649374663e-06, + "loss": 0.8314, + "step": 8417 + }, + { + "epoch": 0.5167746094109703, + "grad_norm": 0.7832007911303461, + "learning_rate": 9.942338175894594e-06, + "loss": 0.8467, + "step": 8418 + }, + { + "epoch": 0.5168359986494367, + "grad_norm": 0.7768631003777899, + "learning_rate": 9.940349860322236e-06, + "loss": 0.8392, + "step": 8419 + }, + { + "epoch": 0.5168973878879033, + "grad_norm": 0.854547780213391, + "learning_rate": 9.938361547108172e-06, + "loss": 0.8426, + "step": 8420 + }, + { + "epoch": 0.5169587771263697, + "grad_norm": 0.7060721468451178, + "learning_rate": 9.936373236331001e-06, + "loss": 0.8147, + "step": 8421 + }, + { + "epoch": 0.5170201663648363, + "grad_norm": 0.7523161420381963, + "learning_rate": 9.934384928069342e-06, + "loss": 0.8194, + "step": 8422 + }, + { + "epoch": 0.5170815556033027, + "grad_norm": 0.7792850689208921, + "learning_rate": 9.932396622401794e-06, + "loss": 0.7756, + "step": 8423 + }, + { + "epoch": 0.5171429448417693, + "grad_norm": 0.8431589427305027, + "learning_rate": 9.930408319406967e-06, + "loss": 0.8264, + "step": 8424 + }, + { + "epoch": 0.5172043340802357, + "grad_norm": 0.8174493329551074, + "learning_rate": 9.928420019163474e-06, + "loss": 0.854, + "step": 8425 + }, + { + "epoch": 0.5172657233187022, + "grad_norm": 0.8771915438577914, + "learning_rate": 9.926431721749924e-06, + "loss": 0.8774, + "step": 8426 + }, + { + "epoch": 0.5173271125571687, + "grad_norm": 0.7982968825577164, + "learning_rate": 9.924443427244916e-06, + "loss": 0.8369, + "step": 8427 + }, + { + "epoch": 0.5173885017956352, + "grad_norm": 0.6916261492760096, + "learning_rate": 9.922455135727066e-06, + "loss": 0.8293, + "step": 8428 + }, + { + "epoch": 0.5174498910341018, + "grad_norm": 0.6420883499316111, + "learning_rate": 9.920466847274978e-06, + "loss": 0.7333, + "step": 8429 + }, + { + "epoch": 0.5175112802725682, + "grad_norm": 0.7940878231107829, + "learning_rate": 9.91847856196726e-06, + "loss": 0.8492, + "step": 8430 + }, + { + "epoch": 0.5175726695110348, + "grad_norm": 0.745987505611191, + "learning_rate": 9.916490279882525e-06, + "loss": 0.7939, + "step": 8431 + }, + { + "epoch": 0.5176340587495012, + "grad_norm": 0.7486019565826418, + "learning_rate": 9.914502001099373e-06, + "loss": 0.8617, + "step": 8432 + }, + { + "epoch": 0.5176954479879677, + "grad_norm": 0.7756431451943144, + "learning_rate": 9.91251372569641e-06, + "loss": 0.8452, + "step": 8433 + }, + { + "epoch": 0.5177568372264342, + "grad_norm": 0.8165431721094899, + "learning_rate": 9.910525453752253e-06, + "loss": 0.8658, + "step": 8434 + }, + { + "epoch": 0.5178182264649007, + "grad_norm": 0.8388920762190895, + "learning_rate": 9.9085371853455e-06, + "loss": 0.8677, + "step": 8435 + }, + { + "epoch": 0.5178796157033672, + "grad_norm": 0.7866956853072661, + "learning_rate": 9.906548920554765e-06, + "loss": 0.7795, + "step": 8436 + }, + { + "epoch": 0.5179410049418337, + "grad_norm": 0.778787626457435, + "learning_rate": 9.90456065945865e-06, + "loss": 0.8292, + "step": 8437 + }, + { + "epoch": 0.5180023941803001, + "grad_norm": 0.7003700761873233, + "learning_rate": 9.902572402135759e-06, + "loss": 0.7595, + "step": 8438 + }, + { + "epoch": 0.5180637834187667, + "grad_norm": 0.8413279147639091, + "learning_rate": 9.900584148664705e-06, + "loss": 0.8411, + "step": 8439 + }, + { + "epoch": 0.5181251726572332, + "grad_norm": 0.8242532248715391, + "learning_rate": 9.898595899124088e-06, + "loss": 0.8593, + "step": 8440 + }, + { + "epoch": 0.5181865618956997, + "grad_norm": 0.7495624363620292, + "learning_rate": 9.896607653592527e-06, + "loss": 0.8284, + "step": 8441 + }, + { + "epoch": 0.5182479511341662, + "grad_norm": 0.8015137139800005, + "learning_rate": 9.894619412148607e-06, + "loss": 0.8637, + "step": 8442 + }, + { + "epoch": 0.5183093403726327, + "grad_norm": 0.8888287893005085, + "learning_rate": 9.892631174870952e-06, + "loss": 0.8567, + "step": 8443 + }, + { + "epoch": 0.5183707296110992, + "grad_norm": 0.7791398032386874, + "learning_rate": 9.890642941838156e-06, + "loss": 0.8273, + "step": 8444 + }, + { + "epoch": 0.5184321188495656, + "grad_norm": 0.8083519964614387, + "learning_rate": 9.888654713128832e-06, + "loss": 0.8369, + "step": 8445 + }, + { + "epoch": 0.5184935080880322, + "grad_norm": 0.7719188163945782, + "learning_rate": 9.886666488821587e-06, + "loss": 0.8984, + "step": 8446 + }, + { + "epoch": 0.5185548973264986, + "grad_norm": 0.7082316011570717, + "learning_rate": 9.884678268995015e-06, + "loss": 0.8433, + "step": 8447 + }, + { + "epoch": 0.5186162865649652, + "grad_norm": 0.7908298355317556, + "learning_rate": 9.882690053727732e-06, + "loss": 0.8468, + "step": 8448 + }, + { + "epoch": 0.5186776758034316, + "grad_norm": 0.7900280918587819, + "learning_rate": 9.880701843098335e-06, + "loss": 0.8265, + "step": 8449 + }, + { + "epoch": 0.5187390650418982, + "grad_norm": 0.8181023026642156, + "learning_rate": 9.878713637185433e-06, + "loss": 0.8101, + "step": 8450 + }, + { + "epoch": 0.5188004542803647, + "grad_norm": 0.761664936720759, + "learning_rate": 9.876725436067635e-06, + "loss": 0.845, + "step": 8451 + }, + { + "epoch": 0.5188618435188311, + "grad_norm": 0.8184818141577213, + "learning_rate": 9.874737239823533e-06, + "loss": 0.8156, + "step": 8452 + }, + { + "epoch": 0.5189232327572977, + "grad_norm": 0.8257752614742682, + "learning_rate": 9.87274904853174e-06, + "loss": 0.8191, + "step": 8453 + }, + { + "epoch": 0.5189846219957641, + "grad_norm": 0.8456289802526527, + "learning_rate": 9.87076086227086e-06, + "loss": 0.8302, + "step": 8454 + }, + { + "epoch": 0.5190460112342307, + "grad_norm": 0.5652203810209505, + "learning_rate": 9.86877268111949e-06, + "loss": 0.6458, + "step": 8455 + }, + { + "epoch": 0.5191074004726971, + "grad_norm": 0.7923402209420644, + "learning_rate": 9.866784505156245e-06, + "loss": 0.856, + "step": 8456 + }, + { + "epoch": 0.5191687897111636, + "grad_norm": 0.7756561981484582, + "learning_rate": 9.864796334459716e-06, + "loss": 0.8111, + "step": 8457 + }, + { + "epoch": 0.5192301789496301, + "grad_norm": 0.8090327920914963, + "learning_rate": 9.862808169108508e-06, + "loss": 0.8999, + "step": 8458 + }, + { + "epoch": 0.5192915681880966, + "grad_norm": 0.85914856210285, + "learning_rate": 9.860820009181233e-06, + "loss": 0.8638, + "step": 8459 + }, + { + "epoch": 0.5193529574265632, + "grad_norm": 0.8065593538134836, + "learning_rate": 9.858831854756483e-06, + "loss": 0.8354, + "step": 8460 + }, + { + "epoch": 0.5194143466650296, + "grad_norm": 0.7552661536803352, + "learning_rate": 9.856843705912867e-06, + "loss": 0.8524, + "step": 8461 + }, + { + "epoch": 0.5194757359034962, + "grad_norm": 0.833672791135916, + "learning_rate": 9.854855562728986e-06, + "loss": 0.8422, + "step": 8462 + }, + { + "epoch": 0.5195371251419626, + "grad_norm": 0.8243375280660823, + "learning_rate": 9.852867425283437e-06, + "loss": 0.8275, + "step": 8463 + }, + { + "epoch": 0.5195985143804291, + "grad_norm": 0.7489696244967017, + "learning_rate": 9.850879293654829e-06, + "loss": 0.843, + "step": 8464 + }, + { + "epoch": 0.5196599036188956, + "grad_norm": 0.7485207401295612, + "learning_rate": 9.848891167921756e-06, + "loss": 0.8135, + "step": 8465 + }, + { + "epoch": 0.5197212928573621, + "grad_norm": 0.7951698950680047, + "learning_rate": 9.846903048162829e-06, + "loss": 0.846, + "step": 8466 + }, + { + "epoch": 0.5197826820958286, + "grad_norm": 0.8379370262198691, + "learning_rate": 9.844914934456642e-06, + "loss": 0.8509, + "step": 8467 + }, + { + "epoch": 0.5198440713342951, + "grad_norm": 0.768394252549955, + "learning_rate": 9.842926826881796e-06, + "loss": 0.8043, + "step": 8468 + }, + { + "epoch": 0.5199054605727615, + "grad_norm": 0.8521344783938336, + "learning_rate": 9.840938725516889e-06, + "loss": 0.8905, + "step": 8469 + }, + { + "epoch": 0.5199668498112281, + "grad_norm": 0.8234231882028171, + "learning_rate": 9.83895063044053e-06, + "loss": 0.8564, + "step": 8470 + }, + { + "epoch": 0.5200282390496946, + "grad_norm": 0.9034952801306622, + "learning_rate": 9.836962541731314e-06, + "loss": 0.9169, + "step": 8471 + }, + { + "epoch": 0.5200896282881611, + "grad_norm": 0.8145138632717976, + "learning_rate": 9.834974459467837e-06, + "loss": 0.815, + "step": 8472 + }, + { + "epoch": 0.5201510175266276, + "grad_norm": 0.7540326096198269, + "learning_rate": 9.832986383728706e-06, + "loss": 0.8491, + "step": 8473 + }, + { + "epoch": 0.5202124067650941, + "grad_norm": 0.881265199875064, + "learning_rate": 9.830998314592511e-06, + "loss": 0.8553, + "step": 8474 + }, + { + "epoch": 0.5202737960035606, + "grad_norm": 0.7352575885906989, + "learning_rate": 9.829010252137862e-06, + "loss": 0.8095, + "step": 8475 + }, + { + "epoch": 0.520335185242027, + "grad_norm": 0.7673046254886229, + "learning_rate": 9.827022196443352e-06, + "loss": 0.8498, + "step": 8476 + }, + { + "epoch": 0.5203965744804936, + "grad_norm": 0.8148445091490528, + "learning_rate": 9.825034147587576e-06, + "loss": 0.8611, + "step": 8477 + }, + { + "epoch": 0.52045796371896, + "grad_norm": 0.7985861155699298, + "learning_rate": 9.823046105649139e-06, + "loss": 0.8501, + "step": 8478 + }, + { + "epoch": 0.5205193529574266, + "grad_norm": 0.8238960842548176, + "learning_rate": 9.821058070706633e-06, + "loss": 0.8174, + "step": 8479 + }, + { + "epoch": 0.520580742195893, + "grad_norm": 0.8113782575358496, + "learning_rate": 9.819070042838661e-06, + "loss": 0.839, + "step": 8480 + }, + { + "epoch": 0.5206421314343596, + "grad_norm": 0.8339954521193189, + "learning_rate": 9.81708202212382e-06, + "loss": 0.8328, + "step": 8481 + }, + { + "epoch": 0.5207035206728261, + "grad_norm": 0.8181497209940134, + "learning_rate": 9.815094008640702e-06, + "loss": 0.8559, + "step": 8482 + }, + { + "epoch": 0.5207649099112925, + "grad_norm": 0.7110190021150984, + "learning_rate": 9.813106002467906e-06, + "loss": 0.8389, + "step": 8483 + }, + { + "epoch": 0.5208262991497591, + "grad_norm": 0.5842523601716842, + "learning_rate": 9.81111800368403e-06, + "loss": 0.7033, + "step": 8484 + }, + { + "epoch": 0.5208876883882255, + "grad_norm": 0.7842885828212165, + "learning_rate": 9.809130012367668e-06, + "loss": 0.8777, + "step": 8485 + }, + { + "epoch": 0.5209490776266921, + "grad_norm": 0.7868969237242718, + "learning_rate": 9.807142028597423e-06, + "loss": 0.8631, + "step": 8486 + }, + { + "epoch": 0.5210104668651585, + "grad_norm": 0.719249609646741, + "learning_rate": 9.805154052451881e-06, + "loss": 0.833, + "step": 8487 + }, + { + "epoch": 0.521071856103625, + "grad_norm": 0.8103881956688397, + "learning_rate": 9.803166084009639e-06, + "loss": 0.822, + "step": 8488 + }, + { + "epoch": 0.5211332453420915, + "grad_norm": 0.7750441622110487, + "learning_rate": 9.801178123349298e-06, + "loss": 0.8624, + "step": 8489 + }, + { + "epoch": 0.521194634580558, + "grad_norm": 0.7384634517333521, + "learning_rate": 9.799190170549452e-06, + "loss": 0.7967, + "step": 8490 + }, + { + "epoch": 0.5212560238190245, + "grad_norm": 0.8269109494131027, + "learning_rate": 9.797202225688687e-06, + "loss": 0.8147, + "step": 8491 + }, + { + "epoch": 0.521317413057491, + "grad_norm": 0.8715533740131977, + "learning_rate": 9.795214288845607e-06, + "loss": 0.8472, + "step": 8492 + }, + { + "epoch": 0.5213788022959576, + "grad_norm": 0.7668975320333614, + "learning_rate": 9.793226360098796e-06, + "loss": 0.8669, + "step": 8493 + }, + { + "epoch": 0.521440191534424, + "grad_norm": 0.8439827589250424, + "learning_rate": 9.791238439526856e-06, + "loss": 0.8255, + "step": 8494 + }, + { + "epoch": 0.5215015807728905, + "grad_norm": 0.8895359815227967, + "learning_rate": 9.78925052720838e-06, + "loss": 0.8729, + "step": 8495 + }, + { + "epoch": 0.521562970011357, + "grad_norm": 0.82509412842164, + "learning_rate": 9.787262623221955e-06, + "loss": 0.821, + "step": 8496 + }, + { + "epoch": 0.5216243592498235, + "grad_norm": 0.7546163397474112, + "learning_rate": 9.785274727646174e-06, + "loss": 0.7694, + "step": 8497 + }, + { + "epoch": 0.52168574848829, + "grad_norm": 0.5988757982894648, + "learning_rate": 9.783286840559634e-06, + "loss": 0.6746, + "step": 8498 + }, + { + "epoch": 0.5217471377267565, + "grad_norm": 0.6117229735550902, + "learning_rate": 9.781298962040923e-06, + "loss": 0.7014, + "step": 8499 + }, + { + "epoch": 0.521808526965223, + "grad_norm": 0.8122240123023513, + "learning_rate": 9.779311092168636e-06, + "loss": 0.808, + "step": 8500 + }, + { + "epoch": 0.5218699162036895, + "grad_norm": 0.8070342123439382, + "learning_rate": 9.777323231021362e-06, + "loss": 0.8281, + "step": 8501 + }, + { + "epoch": 0.5219313054421559, + "grad_norm": 0.8100740395152618, + "learning_rate": 9.775335378677687e-06, + "loss": 0.8339, + "step": 8502 + }, + { + "epoch": 0.5219926946806225, + "grad_norm": 0.7928810056312391, + "learning_rate": 9.77334753521621e-06, + "loss": 0.8142, + "step": 8503 + }, + { + "epoch": 0.522054083919089, + "grad_norm": 0.7637655817352794, + "learning_rate": 9.771359700715514e-06, + "loss": 0.8359, + "step": 8504 + }, + { + "epoch": 0.5221154731575555, + "grad_norm": 0.8893022253748998, + "learning_rate": 9.769371875254197e-06, + "loss": 0.8122, + "step": 8505 + }, + { + "epoch": 0.522176862396022, + "grad_norm": 0.7764872831615799, + "learning_rate": 9.767384058910842e-06, + "loss": 0.8273, + "step": 8506 + }, + { + "epoch": 0.5222382516344884, + "grad_norm": 0.8144636236912001, + "learning_rate": 9.765396251764037e-06, + "loss": 0.8719, + "step": 8507 + }, + { + "epoch": 0.522299640872955, + "grad_norm": 0.8226880119390559, + "learning_rate": 9.763408453892372e-06, + "loss": 0.8452, + "step": 8508 + }, + { + "epoch": 0.5223610301114214, + "grad_norm": 0.7583724695339367, + "learning_rate": 9.761420665374439e-06, + "loss": 0.8071, + "step": 8509 + }, + { + "epoch": 0.522422419349888, + "grad_norm": 0.7584630768857713, + "learning_rate": 9.759432886288824e-06, + "loss": 0.7759, + "step": 8510 + }, + { + "epoch": 0.5224838085883544, + "grad_norm": 0.8222821808580791, + "learning_rate": 9.757445116714109e-06, + "loss": 0.8813, + "step": 8511 + }, + { + "epoch": 0.522545197826821, + "grad_norm": 0.8462797164401686, + "learning_rate": 9.755457356728889e-06, + "loss": 0.8932, + "step": 8512 + }, + { + "epoch": 0.5226065870652875, + "grad_norm": 0.8193407839798728, + "learning_rate": 9.753469606411745e-06, + "loss": 0.8734, + "step": 8513 + }, + { + "epoch": 0.522667976303754, + "grad_norm": 0.7595106702202143, + "learning_rate": 9.75148186584127e-06, + "loss": 0.8135, + "step": 8514 + }, + { + "epoch": 0.5227293655422205, + "grad_norm": 0.8158810604141461, + "learning_rate": 9.749494135096045e-06, + "loss": 0.8451, + "step": 8515 + }, + { + "epoch": 0.5227907547806869, + "grad_norm": 0.840034538493809, + "learning_rate": 9.747506414254654e-06, + "loss": 0.8364, + "step": 8516 + }, + { + "epoch": 0.5228521440191535, + "grad_norm": 0.7254641661115089, + "learning_rate": 9.745518703395686e-06, + "loss": 0.8014, + "step": 8517 + }, + { + "epoch": 0.5229135332576199, + "grad_norm": 0.7315703395421449, + "learning_rate": 9.743531002597725e-06, + "loss": 0.7749, + "step": 8518 + }, + { + "epoch": 0.5229749224960865, + "grad_norm": 0.8779356954935456, + "learning_rate": 9.741543311939355e-06, + "loss": 0.8551, + "step": 8519 + }, + { + "epoch": 0.5230363117345529, + "grad_norm": 0.8017947560393847, + "learning_rate": 9.739555631499164e-06, + "loss": 0.8387, + "step": 8520 + }, + { + "epoch": 0.5230977009730194, + "grad_norm": 0.840901181316453, + "learning_rate": 9.737567961355728e-06, + "loss": 0.872, + "step": 8521 + }, + { + "epoch": 0.5231590902114859, + "grad_norm": 0.825693577032963, + "learning_rate": 9.735580301587633e-06, + "loss": 0.8345, + "step": 8522 + }, + { + "epoch": 0.5232204794499524, + "grad_norm": 0.7922035263890064, + "learning_rate": 9.733592652273465e-06, + "loss": 0.8003, + "step": 8523 + }, + { + "epoch": 0.523281868688419, + "grad_norm": 0.7634849482329626, + "learning_rate": 9.731605013491802e-06, + "loss": 0.8286, + "step": 8524 + }, + { + "epoch": 0.5233432579268854, + "grad_norm": 0.7999258716693206, + "learning_rate": 9.729617385321231e-06, + "loss": 0.814, + "step": 8525 + }, + { + "epoch": 0.523404647165352, + "grad_norm": 0.8852209136899694, + "learning_rate": 9.727629767840331e-06, + "loss": 0.8649, + "step": 8526 + }, + { + "epoch": 0.5234660364038184, + "grad_norm": 0.801177938016377, + "learning_rate": 9.725642161127681e-06, + "loss": 0.851, + "step": 8527 + }, + { + "epoch": 0.5235274256422849, + "grad_norm": 0.8847336592845801, + "learning_rate": 9.723654565261864e-06, + "loss": 0.8415, + "step": 8528 + }, + { + "epoch": 0.5235888148807514, + "grad_norm": 0.7591008976542767, + "learning_rate": 9.72166698032146e-06, + "loss": 0.8329, + "step": 8529 + }, + { + "epoch": 0.5236502041192179, + "grad_norm": 0.881755539640166, + "learning_rate": 9.719679406385051e-06, + "loss": 0.861, + "step": 8530 + }, + { + "epoch": 0.5237115933576844, + "grad_norm": 0.771965954477612, + "learning_rate": 9.717691843531214e-06, + "loss": 0.8561, + "step": 8531 + }, + { + "epoch": 0.5237729825961509, + "grad_norm": 0.8003626089524059, + "learning_rate": 9.715704291838527e-06, + "loss": 0.8514, + "step": 8532 + }, + { + "epoch": 0.5238343718346173, + "grad_norm": 0.8989066032907351, + "learning_rate": 9.713716751385569e-06, + "loss": 0.8386, + "step": 8533 + }, + { + "epoch": 0.5238957610730839, + "grad_norm": 0.8482692377058987, + "learning_rate": 9.71172922225092e-06, + "loss": 0.842, + "step": 8534 + }, + { + "epoch": 0.5239571503115504, + "grad_norm": 0.852801722694873, + "learning_rate": 9.709741704513159e-06, + "loss": 0.7985, + "step": 8535 + }, + { + "epoch": 0.5240185395500169, + "grad_norm": 0.7850192692476807, + "learning_rate": 9.707754198250856e-06, + "loss": 0.8401, + "step": 8536 + }, + { + "epoch": 0.5240799287884834, + "grad_norm": 0.8386415067670866, + "learning_rate": 9.705766703542596e-06, + "loss": 0.8658, + "step": 8537 + }, + { + "epoch": 0.5241413180269499, + "grad_norm": 0.7699930519214297, + "learning_rate": 9.70377922046695e-06, + "loss": 0.8636, + "step": 8538 + }, + { + "epoch": 0.5242027072654164, + "grad_norm": 0.7665630166499338, + "learning_rate": 9.701791749102496e-06, + "loss": 0.811, + "step": 8539 + }, + { + "epoch": 0.5242640965038828, + "grad_norm": 0.8125922739367497, + "learning_rate": 9.699804289527812e-06, + "loss": 0.924, + "step": 8540 + }, + { + "epoch": 0.5243254857423494, + "grad_norm": 0.6999381733958354, + "learning_rate": 9.697816841821466e-06, + "loss": 0.8391, + "step": 8541 + }, + { + "epoch": 0.5243868749808158, + "grad_norm": 0.7997673030507554, + "learning_rate": 9.695829406062039e-06, + "loss": 0.8338, + "step": 8542 + }, + { + "epoch": 0.5244482642192824, + "grad_norm": 0.8039714620207763, + "learning_rate": 9.6938419823281e-06, + "loss": 0.8421, + "step": 8543 + }, + { + "epoch": 0.5245096534577488, + "grad_norm": 0.8081151799749272, + "learning_rate": 9.691854570698227e-06, + "loss": 0.8788, + "step": 8544 + }, + { + "epoch": 0.5245710426962154, + "grad_norm": 0.7390102156203516, + "learning_rate": 9.689867171250993e-06, + "loss": 0.8192, + "step": 8545 + }, + { + "epoch": 0.5246324319346819, + "grad_norm": 0.8384041174032955, + "learning_rate": 9.687879784064965e-06, + "loss": 0.8699, + "step": 8546 + }, + { + "epoch": 0.5246938211731483, + "grad_norm": 0.7606429864396035, + "learning_rate": 9.685892409218718e-06, + "loss": 0.8078, + "step": 8547 + }, + { + "epoch": 0.5247552104116149, + "grad_norm": 0.8591344527564408, + "learning_rate": 9.683905046790826e-06, + "loss": 0.856, + "step": 8548 + }, + { + "epoch": 0.5248165996500813, + "grad_norm": 0.8161030766968849, + "learning_rate": 9.681917696859855e-06, + "loss": 0.8253, + "step": 8549 + }, + { + "epoch": 0.5248779888885479, + "grad_norm": 0.780919313101046, + "learning_rate": 9.679930359504384e-06, + "loss": 0.8018, + "step": 8550 + }, + { + "epoch": 0.5249393781270143, + "grad_norm": 0.785504080576859, + "learning_rate": 9.677943034802975e-06, + "loss": 0.8267, + "step": 8551 + }, + { + "epoch": 0.5250007673654808, + "grad_norm": 0.7262096990464634, + "learning_rate": 9.675955722834199e-06, + "loss": 0.7853, + "step": 8552 + }, + { + "epoch": 0.5250621566039473, + "grad_norm": 0.7709519509872427, + "learning_rate": 9.673968423676627e-06, + "loss": 0.8311, + "step": 8553 + }, + { + "epoch": 0.5251235458424138, + "grad_norm": 0.7866084508399548, + "learning_rate": 9.67198113740883e-06, + "loss": 0.8207, + "step": 8554 + }, + { + "epoch": 0.5251849350808803, + "grad_norm": 0.8176249091127733, + "learning_rate": 9.669993864109368e-06, + "loss": 0.8172, + "step": 8555 + }, + { + "epoch": 0.5252463243193468, + "grad_norm": 0.7224835723211016, + "learning_rate": 9.668006603856818e-06, + "loss": 0.813, + "step": 8556 + }, + { + "epoch": 0.5253077135578134, + "grad_norm": 0.8276216428302569, + "learning_rate": 9.666019356729737e-06, + "loss": 0.8306, + "step": 8557 + }, + { + "epoch": 0.5253691027962798, + "grad_norm": 0.8194605373662314, + "learning_rate": 9.664032122806703e-06, + "loss": 0.8733, + "step": 8558 + }, + { + "epoch": 0.5254304920347463, + "grad_norm": 0.7870151420415841, + "learning_rate": 9.662044902166275e-06, + "loss": 0.8407, + "step": 8559 + }, + { + "epoch": 0.5254918812732128, + "grad_norm": 0.8209465895266107, + "learning_rate": 9.660057694887019e-06, + "loss": 0.7719, + "step": 8560 + }, + { + "epoch": 0.5255532705116793, + "grad_norm": 0.7335259235508673, + "learning_rate": 9.658070501047498e-06, + "loss": 0.8447, + "step": 8561 + }, + { + "epoch": 0.5256146597501458, + "grad_norm": 0.7268086020723682, + "learning_rate": 9.65608332072628e-06, + "loss": 0.8221, + "step": 8562 + }, + { + "epoch": 0.5256760489886123, + "grad_norm": 0.8782127728435899, + "learning_rate": 9.654096154001927e-06, + "loss": 0.8838, + "step": 8563 + }, + { + "epoch": 0.5257374382270787, + "grad_norm": 0.878073995659049, + "learning_rate": 9.652109000953007e-06, + "loss": 0.8595, + "step": 8564 + }, + { + "epoch": 0.5257988274655453, + "grad_norm": 0.7735227652629472, + "learning_rate": 9.650121861658077e-06, + "loss": 0.8106, + "step": 8565 + }, + { + "epoch": 0.5258602167040118, + "grad_norm": 0.7255917460530332, + "learning_rate": 9.648134736195697e-06, + "loss": 0.8447, + "step": 8566 + }, + { + "epoch": 0.5259216059424783, + "grad_norm": 0.8762527019462881, + "learning_rate": 9.646147624644438e-06, + "loss": 0.8114, + "step": 8567 + }, + { + "epoch": 0.5259829951809448, + "grad_norm": 0.8969801109581926, + "learning_rate": 9.644160527082852e-06, + "loss": 0.8297, + "step": 8568 + }, + { + "epoch": 0.5260443844194113, + "grad_norm": 0.7794430127366929, + "learning_rate": 9.642173443589508e-06, + "loss": 0.8041, + "step": 8569 + }, + { + "epoch": 0.5261057736578778, + "grad_norm": 0.835505731551431, + "learning_rate": 9.640186374242959e-06, + "loss": 0.8509, + "step": 8570 + }, + { + "epoch": 0.5261671628963442, + "grad_norm": 0.8787696630595909, + "learning_rate": 9.638199319121768e-06, + "loss": 0.8467, + "step": 8571 + }, + { + "epoch": 0.5262285521348108, + "grad_norm": 0.9338083446993519, + "learning_rate": 9.63621227830449e-06, + "loss": 0.8823, + "step": 8572 + }, + { + "epoch": 0.5262899413732772, + "grad_norm": 0.8309176017809285, + "learning_rate": 9.634225251869689e-06, + "loss": 0.828, + "step": 8573 + }, + { + "epoch": 0.5263513306117438, + "grad_norm": 0.7971669443986686, + "learning_rate": 9.632238239895922e-06, + "loss": 0.846, + "step": 8574 + }, + { + "epoch": 0.5264127198502102, + "grad_norm": 0.7866300396914275, + "learning_rate": 9.63025124246174e-06, + "loss": 0.8223, + "step": 8575 + }, + { + "epoch": 0.5264741090886768, + "grad_norm": 0.6866837788596509, + "learning_rate": 9.628264259645706e-06, + "loss": 0.7897, + "step": 8576 + }, + { + "epoch": 0.5265354983271433, + "grad_norm": 0.7591929251819158, + "learning_rate": 9.626277291526372e-06, + "loss": 0.7997, + "step": 8577 + }, + { + "epoch": 0.5265968875656097, + "grad_norm": 0.7372018114991279, + "learning_rate": 9.624290338182297e-06, + "loss": 0.7533, + "step": 8578 + }, + { + "epoch": 0.5266582768040763, + "grad_norm": 0.8432013605045436, + "learning_rate": 9.622303399692038e-06, + "loss": 0.8749, + "step": 8579 + }, + { + "epoch": 0.5267196660425427, + "grad_norm": 0.788285006816946, + "learning_rate": 9.62031647613414e-06, + "loss": 0.8037, + "step": 8580 + }, + { + "epoch": 0.5267810552810093, + "grad_norm": 0.7822153275813802, + "learning_rate": 9.618329567587166e-06, + "loss": 0.802, + "step": 8581 + }, + { + "epoch": 0.5268424445194757, + "grad_norm": 0.8040367066026819, + "learning_rate": 9.616342674129661e-06, + "loss": 0.876, + "step": 8582 + }, + { + "epoch": 0.5269038337579423, + "grad_norm": 0.9318871617890114, + "learning_rate": 9.614355795840186e-06, + "loss": 0.9033, + "step": 8583 + }, + { + "epoch": 0.5269652229964087, + "grad_norm": 0.7844742067547642, + "learning_rate": 9.612368932797292e-06, + "loss": 0.8246, + "step": 8584 + }, + { + "epoch": 0.5270266122348752, + "grad_norm": 0.9188285238775465, + "learning_rate": 9.610382085079522e-06, + "loss": 0.9023, + "step": 8585 + }, + { + "epoch": 0.5270880014733417, + "grad_norm": 0.759707891071139, + "learning_rate": 9.608395252765432e-06, + "loss": 0.8146, + "step": 8586 + }, + { + "epoch": 0.5271493907118082, + "grad_norm": 0.8756685836431508, + "learning_rate": 9.606408435933574e-06, + "loss": 0.8516, + "step": 8587 + }, + { + "epoch": 0.5272107799502748, + "grad_norm": 0.8506904316716456, + "learning_rate": 9.604421634662494e-06, + "loss": 0.825, + "step": 8588 + }, + { + "epoch": 0.5272721691887412, + "grad_norm": 0.8176055468629938, + "learning_rate": 9.602434849030747e-06, + "loss": 0.8824, + "step": 8589 + }, + { + "epoch": 0.5273335584272077, + "grad_norm": 0.8665195803409717, + "learning_rate": 9.600448079116874e-06, + "loss": 0.8926, + "step": 8590 + }, + { + "epoch": 0.5273949476656742, + "grad_norm": 0.7589672422980087, + "learning_rate": 9.598461324999421e-06, + "loss": 0.8319, + "step": 8591 + }, + { + "epoch": 0.5274563369041407, + "grad_norm": 0.8240045192206188, + "learning_rate": 9.596474586756944e-06, + "loss": 0.8064, + "step": 8592 + }, + { + "epoch": 0.5275177261426072, + "grad_norm": 0.7802482784707554, + "learning_rate": 9.594487864467983e-06, + "loss": 0.8201, + "step": 8593 + }, + { + "epoch": 0.5275791153810737, + "grad_norm": 0.7457438782875425, + "learning_rate": 9.592501158211088e-06, + "loss": 0.824, + "step": 8594 + }, + { + "epoch": 0.5276405046195402, + "grad_norm": 0.8263128504886132, + "learning_rate": 9.590514468064802e-06, + "loss": 0.8728, + "step": 8595 + }, + { + "epoch": 0.5277018938580067, + "grad_norm": 0.8442574481733686, + "learning_rate": 9.588527794107664e-06, + "loss": 0.7912, + "step": 8596 + }, + { + "epoch": 0.5277632830964731, + "grad_norm": 0.8477755223278709, + "learning_rate": 9.586541136418227e-06, + "loss": 0.852, + "step": 8597 + }, + { + "epoch": 0.5278246723349397, + "grad_norm": 0.8248461019816637, + "learning_rate": 9.58455449507503e-06, + "loss": 0.8644, + "step": 8598 + }, + { + "epoch": 0.5278860615734062, + "grad_norm": 0.9487606953087095, + "learning_rate": 9.582567870156618e-06, + "loss": 0.8915, + "step": 8599 + }, + { + "epoch": 0.5279474508118727, + "grad_norm": 0.7959767992989454, + "learning_rate": 9.580581261741526e-06, + "loss": 0.8341, + "step": 8600 + }, + { + "epoch": 0.5280088400503392, + "grad_norm": 0.7457030787588914, + "learning_rate": 9.578594669908304e-06, + "loss": 0.8402, + "step": 8601 + }, + { + "epoch": 0.5280702292888056, + "grad_norm": 0.8332747723659809, + "learning_rate": 9.576608094735483e-06, + "loss": 0.8339, + "step": 8602 + }, + { + "epoch": 0.5281316185272722, + "grad_norm": 0.8190808109868231, + "learning_rate": 9.574621536301613e-06, + "loss": 0.8041, + "step": 8603 + }, + { + "epoch": 0.5281930077657386, + "grad_norm": 0.844115362430583, + "learning_rate": 9.57263499468523e-06, + "loss": 0.8926, + "step": 8604 + }, + { + "epoch": 0.5282543970042052, + "grad_norm": 0.8283929321212247, + "learning_rate": 9.570648469964868e-06, + "loss": 0.8029, + "step": 8605 + }, + { + "epoch": 0.5283157862426716, + "grad_norm": 0.7965273405155008, + "learning_rate": 9.56866196221907e-06, + "loss": 0.8373, + "step": 8606 + }, + { + "epoch": 0.5283771754811382, + "grad_norm": 0.7560008764435499, + "learning_rate": 9.566675471526368e-06, + "loss": 0.8117, + "step": 8607 + }, + { + "epoch": 0.5284385647196047, + "grad_norm": 0.7651112495539972, + "learning_rate": 9.564688997965305e-06, + "loss": 0.8567, + "step": 8608 + }, + { + "epoch": 0.5284999539580711, + "grad_norm": 0.7125032593483905, + "learning_rate": 9.562702541614416e-06, + "loss": 0.8117, + "step": 8609 + }, + { + "epoch": 0.5285613431965377, + "grad_norm": 0.7476496665396871, + "learning_rate": 9.560716102552234e-06, + "loss": 0.794, + "step": 8610 + }, + { + "epoch": 0.5286227324350041, + "grad_norm": 0.7751317397376862, + "learning_rate": 9.558729680857292e-06, + "loss": 0.8443, + "step": 8611 + }, + { + "epoch": 0.5286841216734707, + "grad_norm": 0.7923649826867456, + "learning_rate": 9.556743276608127e-06, + "loss": 0.8241, + "step": 8612 + }, + { + "epoch": 0.5287455109119371, + "grad_norm": 0.7398889225587879, + "learning_rate": 9.554756889883268e-06, + "loss": 0.8369, + "step": 8613 + }, + { + "epoch": 0.5288069001504037, + "grad_norm": 0.8719898169292843, + "learning_rate": 9.552770520761256e-06, + "loss": 0.8275, + "step": 8614 + }, + { + "epoch": 0.5288682893888701, + "grad_norm": 0.7931300707972866, + "learning_rate": 9.550784169320614e-06, + "loss": 0.8172, + "step": 8615 + }, + { + "epoch": 0.5289296786273366, + "grad_norm": 0.8094246971113258, + "learning_rate": 9.548797835639874e-06, + "loss": 0.8345, + "step": 8616 + }, + { + "epoch": 0.5289910678658031, + "grad_norm": 0.766896165680242, + "learning_rate": 9.546811519797572e-06, + "loss": 0.8212, + "step": 8617 + }, + { + "epoch": 0.5290524571042696, + "grad_norm": 0.8525743894704751, + "learning_rate": 9.544825221872231e-06, + "loss": 0.8329, + "step": 8618 + }, + { + "epoch": 0.5291138463427362, + "grad_norm": 0.871194068473741, + "learning_rate": 9.54283894194239e-06, + "loss": 0.8733, + "step": 8619 + }, + { + "epoch": 0.5291752355812026, + "grad_norm": 0.8403298782350798, + "learning_rate": 9.540852680086566e-06, + "loss": 0.8262, + "step": 8620 + }, + { + "epoch": 0.5292366248196692, + "grad_norm": 0.7975842640746099, + "learning_rate": 9.53886643638329e-06, + "loss": 0.8075, + "step": 8621 + }, + { + "epoch": 0.5292980140581356, + "grad_norm": 0.8024596972813133, + "learning_rate": 9.536880210911092e-06, + "loss": 0.8085, + "step": 8622 + }, + { + "epoch": 0.5293594032966021, + "grad_norm": 0.8011576563410987, + "learning_rate": 9.534894003748501e-06, + "loss": 0.7994, + "step": 8623 + }, + { + "epoch": 0.5294207925350686, + "grad_norm": 0.6731065348054456, + "learning_rate": 9.532907814974032e-06, + "loss": 0.6671, + "step": 8624 + }, + { + "epoch": 0.5294821817735351, + "grad_norm": 0.7541953418016326, + "learning_rate": 9.530921644666215e-06, + "loss": 0.8192, + "step": 8625 + }, + { + "epoch": 0.5295435710120016, + "grad_norm": 0.8136979746188054, + "learning_rate": 9.528935492903575e-06, + "loss": 0.8371, + "step": 8626 + }, + { + "epoch": 0.5296049602504681, + "grad_norm": 0.8030241115098387, + "learning_rate": 9.526949359764633e-06, + "loss": 0.8359, + "step": 8627 + }, + { + "epoch": 0.5296663494889345, + "grad_norm": 0.5851438826900244, + "learning_rate": 9.524963245327918e-06, + "loss": 0.7242, + "step": 8628 + }, + { + "epoch": 0.5297277387274011, + "grad_norm": 0.8744415304005224, + "learning_rate": 9.522977149671942e-06, + "loss": 0.8997, + "step": 8629 + }, + { + "epoch": 0.5297891279658676, + "grad_norm": 0.784120173981169, + "learning_rate": 9.520991072875231e-06, + "loss": 0.8815, + "step": 8630 + }, + { + "epoch": 0.5298505172043341, + "grad_norm": 0.8411641203877891, + "learning_rate": 9.519005015016305e-06, + "loss": 0.819, + "step": 8631 + }, + { + "epoch": 0.5299119064428006, + "grad_norm": 0.8647187804426102, + "learning_rate": 9.517018976173682e-06, + "loss": 0.8268, + "step": 8632 + }, + { + "epoch": 0.529973295681267, + "grad_norm": 0.7278275452963267, + "learning_rate": 9.515032956425887e-06, + "loss": 0.8413, + "step": 8633 + }, + { + "epoch": 0.5300346849197336, + "grad_norm": 0.7677985136957461, + "learning_rate": 9.51304695585143e-06, + "loss": 0.7895, + "step": 8634 + }, + { + "epoch": 0.5300960741582, + "grad_norm": 0.8559053108041936, + "learning_rate": 9.51106097452883e-06, + "loss": 0.878, + "step": 8635 + }, + { + "epoch": 0.5301574633966666, + "grad_norm": 0.9241702271008554, + "learning_rate": 9.509075012536606e-06, + "loss": 0.8139, + "step": 8636 + }, + { + "epoch": 0.530218852635133, + "grad_norm": 0.8064992103965407, + "learning_rate": 9.507089069953272e-06, + "loss": 0.8316, + "step": 8637 + }, + { + "epoch": 0.5302802418735996, + "grad_norm": 0.803904886335778, + "learning_rate": 9.505103146857347e-06, + "loss": 0.7736, + "step": 8638 + }, + { + "epoch": 0.530341631112066, + "grad_norm": 0.7343571404521488, + "learning_rate": 9.503117243327336e-06, + "loss": 0.7721, + "step": 8639 + }, + { + "epoch": 0.5304030203505326, + "grad_norm": 0.8373350629357855, + "learning_rate": 9.501131359441761e-06, + "loss": 0.8007, + "step": 8640 + }, + { + "epoch": 0.5304644095889991, + "grad_norm": 0.8169628111607298, + "learning_rate": 9.499145495279128e-06, + "loss": 0.8305, + "step": 8641 + }, + { + "epoch": 0.5305257988274655, + "grad_norm": 0.8569009966453931, + "learning_rate": 9.497159650917956e-06, + "loss": 0.7995, + "step": 8642 + }, + { + "epoch": 0.5305871880659321, + "grad_norm": 0.9075178333959825, + "learning_rate": 9.495173826436753e-06, + "loss": 0.8374, + "step": 8643 + }, + { + "epoch": 0.5306485773043985, + "grad_norm": 0.8070884849363265, + "learning_rate": 9.493188021914026e-06, + "loss": 0.8443, + "step": 8644 + }, + { + "epoch": 0.5307099665428651, + "grad_norm": 0.7990426293780847, + "learning_rate": 9.491202237428287e-06, + "loss": 0.806, + "step": 8645 + }, + { + "epoch": 0.5307713557813315, + "grad_norm": 0.8421563235548294, + "learning_rate": 9.489216473058044e-06, + "loss": 0.8032, + "step": 8646 + }, + { + "epoch": 0.530832745019798, + "grad_norm": 0.8189674564715639, + "learning_rate": 9.487230728881809e-06, + "loss": 0.8305, + "step": 8647 + }, + { + "epoch": 0.5308941342582645, + "grad_norm": 0.8073641390431119, + "learning_rate": 9.485245004978087e-06, + "loss": 0.839, + "step": 8648 + }, + { + "epoch": 0.530955523496731, + "grad_norm": 0.8414573982849637, + "learning_rate": 9.48325930142538e-06, + "loss": 0.8107, + "step": 8649 + }, + { + "epoch": 0.5310169127351975, + "grad_norm": 0.9008917287596608, + "learning_rate": 9.481273618302194e-06, + "loss": 0.8626, + "step": 8650 + }, + { + "epoch": 0.531078301973664, + "grad_norm": 0.7573155219724564, + "learning_rate": 9.47928795568704e-06, + "loss": 0.8601, + "step": 8651 + }, + { + "epoch": 0.5311396912121306, + "grad_norm": 0.8520745800528744, + "learning_rate": 9.477302313658415e-06, + "loss": 0.8577, + "step": 8652 + }, + { + "epoch": 0.531201080450597, + "grad_norm": 1.024109875592914, + "learning_rate": 9.47531669229483e-06, + "loss": 0.8769, + "step": 8653 + }, + { + "epoch": 0.5312624696890635, + "grad_norm": 0.8407233384877533, + "learning_rate": 9.47333109167478e-06, + "loss": 0.8897, + "step": 8654 + }, + { + "epoch": 0.53132385892753, + "grad_norm": 0.8373768183950195, + "learning_rate": 9.471345511876767e-06, + "loss": 0.8684, + "step": 8655 + }, + { + "epoch": 0.5313852481659965, + "grad_norm": 0.8883952804051681, + "learning_rate": 9.469359952979295e-06, + "loss": 0.8575, + "step": 8656 + }, + { + "epoch": 0.531446637404463, + "grad_norm": 0.8047255733844039, + "learning_rate": 9.467374415060861e-06, + "loss": 0.8497, + "step": 8657 + }, + { + "epoch": 0.5315080266429295, + "grad_norm": 0.7828212574495658, + "learning_rate": 9.465388898199968e-06, + "loss": 0.8592, + "step": 8658 + }, + { + "epoch": 0.531569415881396, + "grad_norm": 0.8288780383803329, + "learning_rate": 9.46340340247511e-06, + "loss": 0.8748, + "step": 8659 + }, + { + "epoch": 0.5316308051198625, + "grad_norm": 0.8537343646541942, + "learning_rate": 9.461417927964782e-06, + "loss": 0.8242, + "step": 8660 + }, + { + "epoch": 0.531692194358329, + "grad_norm": 0.8452333679600611, + "learning_rate": 9.459432474747487e-06, + "loss": 0.8253, + "step": 8661 + }, + { + "epoch": 0.5317535835967955, + "grad_norm": 0.8186813929093242, + "learning_rate": 9.457447042901714e-06, + "loss": 0.8482, + "step": 8662 + }, + { + "epoch": 0.531814972835262, + "grad_norm": 0.7999807344533084, + "learning_rate": 9.45546163250597e-06, + "loss": 0.8423, + "step": 8663 + }, + { + "epoch": 0.5318763620737285, + "grad_norm": 0.8488841070597926, + "learning_rate": 9.45347624363873e-06, + "loss": 0.8461, + "step": 8664 + }, + { + "epoch": 0.531937751312195, + "grad_norm": 0.7451104468714786, + "learning_rate": 9.451490876378502e-06, + "loss": 0.8225, + "step": 8665 + }, + { + "epoch": 0.5319991405506614, + "grad_norm": 0.8886474767463457, + "learning_rate": 9.449505530803771e-06, + "loss": 0.9095, + "step": 8666 + }, + { + "epoch": 0.532060529789128, + "grad_norm": 0.7735173609276823, + "learning_rate": 9.447520206993033e-06, + "loss": 0.8464, + "step": 8667 + }, + { + "epoch": 0.5321219190275944, + "grad_norm": 0.865036561923678, + "learning_rate": 9.445534905024776e-06, + "loss": 0.8422, + "step": 8668 + }, + { + "epoch": 0.532183308266061, + "grad_norm": 0.7896766576262655, + "learning_rate": 9.443549624977488e-06, + "loss": 0.8349, + "step": 8669 + }, + { + "epoch": 0.5322446975045274, + "grad_norm": 0.7664739337851356, + "learning_rate": 9.441564366929661e-06, + "loss": 0.8337, + "step": 8670 + }, + { + "epoch": 0.532306086742994, + "grad_norm": 0.7483786109936073, + "learning_rate": 9.439579130959779e-06, + "loss": 0.8719, + "step": 8671 + }, + { + "epoch": 0.5323674759814605, + "grad_norm": 0.7232761199747495, + "learning_rate": 9.437593917146333e-06, + "loss": 0.7825, + "step": 8672 + }, + { + "epoch": 0.5324288652199269, + "grad_norm": 0.7536792413262073, + "learning_rate": 9.43560872556781e-06, + "loss": 0.8012, + "step": 8673 + }, + { + "epoch": 0.5324902544583935, + "grad_norm": 0.860251532632621, + "learning_rate": 9.433623556302686e-06, + "loss": 0.8535, + "step": 8674 + }, + { + "epoch": 0.5325516436968599, + "grad_norm": 0.8291055776869788, + "learning_rate": 9.431638409429457e-06, + "loss": 0.7897, + "step": 8675 + }, + { + "epoch": 0.5326130329353265, + "grad_norm": 0.8352679811345142, + "learning_rate": 9.4296532850266e-06, + "loss": 0.8926, + "step": 8676 + }, + { + "epoch": 0.5326744221737929, + "grad_norm": 0.872982478435084, + "learning_rate": 9.4276681831726e-06, + "loss": 0.838, + "step": 8677 + }, + { + "epoch": 0.5327358114122595, + "grad_norm": 0.7022353468902104, + "learning_rate": 9.425683103945939e-06, + "loss": 0.826, + "step": 8678 + }, + { + "epoch": 0.5327972006507259, + "grad_norm": 0.8633063521513032, + "learning_rate": 9.423698047425096e-06, + "loss": 0.8359, + "step": 8679 + }, + { + "epoch": 0.5328585898891924, + "grad_norm": 0.7895639695642455, + "learning_rate": 9.421713013688548e-06, + "loss": 0.8152, + "step": 8680 + }, + { + "epoch": 0.5329199791276589, + "grad_norm": 0.869585143375045, + "learning_rate": 9.419728002814779e-06, + "loss": 0.8088, + "step": 8681 + }, + { + "epoch": 0.5329813683661254, + "grad_norm": 0.8991004266476738, + "learning_rate": 9.417743014882264e-06, + "loss": 0.8669, + "step": 8682 + }, + { + "epoch": 0.533042757604592, + "grad_norm": 0.7754588086642042, + "learning_rate": 9.415758049969488e-06, + "loss": 0.8149, + "step": 8683 + }, + { + "epoch": 0.5331041468430584, + "grad_norm": 0.8186627937306946, + "learning_rate": 9.413773108154917e-06, + "loss": 0.8299, + "step": 8684 + }, + { + "epoch": 0.533165536081525, + "grad_norm": 0.8028508956393623, + "learning_rate": 9.411788189517028e-06, + "loss": 0.7965, + "step": 8685 + }, + { + "epoch": 0.5332269253199914, + "grad_norm": 0.8556344520786834, + "learning_rate": 9.409803294134301e-06, + "loss": 0.8687, + "step": 8686 + }, + { + "epoch": 0.5332883145584579, + "grad_norm": 0.8229398815326111, + "learning_rate": 9.407818422085209e-06, + "loss": 0.8601, + "step": 8687 + }, + { + "epoch": 0.5333497037969244, + "grad_norm": 0.7666055481956346, + "learning_rate": 9.405833573448218e-06, + "loss": 0.792, + "step": 8688 + }, + { + "epoch": 0.5334110930353909, + "grad_norm": 0.8556709341507555, + "learning_rate": 9.403848748301802e-06, + "loss": 0.8036, + "step": 8689 + }, + { + "epoch": 0.5334724822738574, + "grad_norm": 0.9175562651439442, + "learning_rate": 9.401863946724437e-06, + "loss": 0.8504, + "step": 8690 + }, + { + "epoch": 0.5335338715123239, + "grad_norm": 0.7938160569494078, + "learning_rate": 9.399879168794585e-06, + "loss": 0.8235, + "step": 8691 + }, + { + "epoch": 0.5335952607507903, + "grad_norm": 0.9023480302629755, + "learning_rate": 9.397894414590726e-06, + "loss": 0.8748, + "step": 8692 + }, + { + "epoch": 0.5336566499892569, + "grad_norm": 0.8388422020185916, + "learning_rate": 9.395909684191318e-06, + "loss": 0.8068, + "step": 8693 + }, + { + "epoch": 0.5337180392277234, + "grad_norm": 0.833959581677384, + "learning_rate": 9.393924977674827e-06, + "loss": 0.8442, + "step": 8694 + }, + { + "epoch": 0.5337794284661899, + "grad_norm": 0.8555452472530088, + "learning_rate": 9.391940295119726e-06, + "loss": 0.8598, + "step": 8695 + }, + { + "epoch": 0.5338408177046564, + "grad_norm": 0.8900179222869768, + "learning_rate": 9.389955636604478e-06, + "loss": 0.8332, + "step": 8696 + }, + { + "epoch": 0.5339022069431228, + "grad_norm": 0.8655781845181174, + "learning_rate": 9.387971002207547e-06, + "loss": 0.8341, + "step": 8697 + }, + { + "epoch": 0.5339635961815894, + "grad_norm": 0.8211275995977297, + "learning_rate": 9.385986392007396e-06, + "loss": 0.8398, + "step": 8698 + }, + { + "epoch": 0.5340249854200558, + "grad_norm": 0.7788363930988889, + "learning_rate": 9.384001806082483e-06, + "loss": 0.7974, + "step": 8699 + }, + { + "epoch": 0.5340863746585224, + "grad_norm": 0.9019861362383317, + "learning_rate": 9.382017244511277e-06, + "loss": 0.854, + "step": 8700 + }, + { + "epoch": 0.5341477638969888, + "grad_norm": 0.9164093414445438, + "learning_rate": 9.380032707372231e-06, + "loss": 0.8017, + "step": 8701 + }, + { + "epoch": 0.5342091531354554, + "grad_norm": 0.7301454606729884, + "learning_rate": 9.378048194743817e-06, + "loss": 0.8238, + "step": 8702 + }, + { + "epoch": 0.5342705423739218, + "grad_norm": 0.7844381873713457, + "learning_rate": 9.376063706704474e-06, + "loss": 0.7901, + "step": 8703 + }, + { + "epoch": 0.5343319316123883, + "grad_norm": 0.7524769240467679, + "learning_rate": 9.374079243332674e-06, + "loss": 0.865, + "step": 8704 + }, + { + "epoch": 0.5343933208508549, + "grad_norm": 0.7763433171943859, + "learning_rate": 9.372094804706867e-06, + "loss": 0.8078, + "step": 8705 + }, + { + "epoch": 0.5344547100893213, + "grad_norm": 0.7974780026065564, + "learning_rate": 9.370110390905513e-06, + "loss": 0.7987, + "step": 8706 + }, + { + "epoch": 0.5345160993277879, + "grad_norm": 0.7975934167062819, + "learning_rate": 9.368126002007065e-06, + "loss": 0.8432, + "step": 8707 + }, + { + "epoch": 0.5345774885662543, + "grad_norm": 0.9246315250517674, + "learning_rate": 9.366141638089972e-06, + "loss": 0.858, + "step": 8708 + }, + { + "epoch": 0.5346388778047209, + "grad_norm": 0.8296370999489013, + "learning_rate": 9.364157299232693e-06, + "loss": 0.855, + "step": 8709 + }, + { + "epoch": 0.5347002670431873, + "grad_norm": 0.8546470320724572, + "learning_rate": 9.362172985513673e-06, + "loss": 0.7881, + "step": 8710 + }, + { + "epoch": 0.5347616562816538, + "grad_norm": 0.8447902308494415, + "learning_rate": 9.36018869701137e-06, + "loss": 0.8564, + "step": 8711 + }, + { + "epoch": 0.5348230455201203, + "grad_norm": 0.7996931300780517, + "learning_rate": 9.358204433804231e-06, + "loss": 0.8485, + "step": 8712 + }, + { + "epoch": 0.5348844347585868, + "grad_norm": 0.796167725173167, + "learning_rate": 9.356220195970698e-06, + "loss": 0.8151, + "step": 8713 + }, + { + "epoch": 0.5349458239970534, + "grad_norm": 0.8362924235142154, + "learning_rate": 9.354235983589229e-06, + "loss": 0.9027, + "step": 8714 + }, + { + "epoch": 0.5350072132355198, + "grad_norm": 0.8388207552717543, + "learning_rate": 9.352251796738263e-06, + "loss": 0.8255, + "step": 8715 + }, + { + "epoch": 0.5350686024739864, + "grad_norm": 0.8546781636728403, + "learning_rate": 9.350267635496246e-06, + "loss": 0.8228, + "step": 8716 + }, + { + "epoch": 0.5351299917124528, + "grad_norm": 0.810196148461132, + "learning_rate": 9.348283499941629e-06, + "loss": 0.8455, + "step": 8717 + }, + { + "epoch": 0.5351913809509193, + "grad_norm": 0.9055899918546019, + "learning_rate": 9.346299390152848e-06, + "loss": 0.7678, + "step": 8718 + }, + { + "epoch": 0.5352527701893858, + "grad_norm": 0.7637572034247341, + "learning_rate": 9.344315306208349e-06, + "loss": 0.8233, + "step": 8719 + }, + { + "epoch": 0.5353141594278523, + "grad_norm": 0.8077981132911348, + "learning_rate": 9.342331248186571e-06, + "loss": 0.8259, + "step": 8720 + }, + { + "epoch": 0.5353755486663188, + "grad_norm": 0.8486669509256229, + "learning_rate": 9.340347216165957e-06, + "loss": 0.809, + "step": 8721 + }, + { + "epoch": 0.5354369379047853, + "grad_norm": 0.8442899287738452, + "learning_rate": 9.338363210224947e-06, + "loss": 0.8194, + "step": 8722 + }, + { + "epoch": 0.5354983271432517, + "grad_norm": 0.8030502260927405, + "learning_rate": 9.336379230441978e-06, + "loss": 0.8649, + "step": 8723 + }, + { + "epoch": 0.5355597163817183, + "grad_norm": 0.8550806776675214, + "learning_rate": 9.334395276895487e-06, + "loss": 0.8218, + "step": 8724 + }, + { + "epoch": 0.5356211056201848, + "grad_norm": 0.85375962506505, + "learning_rate": 9.332411349663909e-06, + "loss": 0.8508, + "step": 8725 + }, + { + "epoch": 0.5356824948586513, + "grad_norm": 0.7631831152015498, + "learning_rate": 9.330427448825681e-06, + "loss": 0.8259, + "step": 8726 + }, + { + "epoch": 0.5357438840971178, + "grad_norm": 0.8241517960356061, + "learning_rate": 9.328443574459242e-06, + "loss": 0.8654, + "step": 8727 + }, + { + "epoch": 0.5358052733355843, + "grad_norm": 0.785658317252857, + "learning_rate": 9.326459726643015e-06, + "loss": 0.7758, + "step": 8728 + }, + { + "epoch": 0.5358666625740508, + "grad_norm": 0.7476466048068956, + "learning_rate": 9.324475905455439e-06, + "loss": 0.8016, + "step": 8729 + }, + { + "epoch": 0.5359280518125172, + "grad_norm": 0.8311360109087521, + "learning_rate": 9.32249211097494e-06, + "loss": 0.8452, + "step": 8730 + }, + { + "epoch": 0.5359894410509838, + "grad_norm": 0.7602737711527919, + "learning_rate": 9.320508343279957e-06, + "loss": 0.7967, + "step": 8731 + }, + { + "epoch": 0.5360508302894502, + "grad_norm": 0.7841690316887396, + "learning_rate": 9.318524602448912e-06, + "loss": 0.8199, + "step": 8732 + }, + { + "epoch": 0.5361122195279168, + "grad_norm": 0.829266361176246, + "learning_rate": 9.316540888560232e-06, + "loss": 0.8351, + "step": 8733 + }, + { + "epoch": 0.5361736087663832, + "grad_norm": 0.77362813331226, + "learning_rate": 9.314557201692348e-06, + "loss": 0.8314, + "step": 8734 + }, + { + "epoch": 0.5362349980048497, + "grad_norm": 0.8472668128305635, + "learning_rate": 9.312573541923681e-06, + "loss": 0.8692, + "step": 8735 + }, + { + "epoch": 0.5362963872433163, + "grad_norm": 0.7066029268544614, + "learning_rate": 9.310589909332661e-06, + "loss": 0.8305, + "step": 8736 + }, + { + "epoch": 0.5363577764817827, + "grad_norm": 0.7561427919031254, + "learning_rate": 9.308606303997711e-06, + "loss": 0.7668, + "step": 8737 + }, + { + "epoch": 0.5364191657202493, + "grad_norm": 0.8405765812581163, + "learning_rate": 9.306622725997247e-06, + "loss": 0.9064, + "step": 8738 + }, + { + "epoch": 0.5364805549587157, + "grad_norm": 0.9045622218217222, + "learning_rate": 9.304639175409699e-06, + "loss": 0.8568, + "step": 8739 + }, + { + "epoch": 0.5365419441971823, + "grad_norm": 0.9042478167931617, + "learning_rate": 9.30265565231348e-06, + "loss": 0.8365, + "step": 8740 + }, + { + "epoch": 0.5366033334356487, + "grad_norm": 0.7840983692565722, + "learning_rate": 9.300672156787014e-06, + "loss": 0.7999, + "step": 8741 + }, + { + "epoch": 0.5366647226741152, + "grad_norm": 0.788710622480814, + "learning_rate": 9.298688688908722e-06, + "loss": 0.8425, + "step": 8742 + }, + { + "epoch": 0.5367261119125817, + "grad_norm": 0.7761045457248685, + "learning_rate": 9.296705248757013e-06, + "loss": 0.8448, + "step": 8743 + }, + { + "epoch": 0.5367875011510482, + "grad_norm": 0.7976129316641186, + "learning_rate": 9.294721836410305e-06, + "loss": 0.8198, + "step": 8744 + }, + { + "epoch": 0.5368488903895147, + "grad_norm": 0.7716148620927065, + "learning_rate": 9.292738451947018e-06, + "loss": 0.8589, + "step": 8745 + }, + { + "epoch": 0.5369102796279812, + "grad_norm": 0.8131689169675841, + "learning_rate": 9.29075509544556e-06, + "loss": 0.8313, + "step": 8746 + }, + { + "epoch": 0.5369716688664478, + "grad_norm": 0.7707499936515865, + "learning_rate": 9.288771766984353e-06, + "loss": 0.8488, + "step": 8747 + }, + { + "epoch": 0.5370330581049142, + "grad_norm": 0.7560995802692734, + "learning_rate": 9.286788466641797e-06, + "loss": 0.781, + "step": 8748 + }, + { + "epoch": 0.5370944473433807, + "grad_norm": 0.8403100354040189, + "learning_rate": 9.284805194496305e-06, + "loss": 0.8289, + "step": 8749 + }, + { + "epoch": 0.5371558365818472, + "grad_norm": 0.8649178642695499, + "learning_rate": 9.282821950626292e-06, + "loss": 0.8556, + "step": 8750 + }, + { + "epoch": 0.5372172258203137, + "grad_norm": 0.7596609610485691, + "learning_rate": 9.28083873511016e-06, + "loss": 0.9083, + "step": 8751 + }, + { + "epoch": 0.5372786150587802, + "grad_norm": 0.8775990854616262, + "learning_rate": 9.278855548026326e-06, + "loss": 0.8118, + "step": 8752 + }, + { + "epoch": 0.5373400042972467, + "grad_norm": 0.8608495730497489, + "learning_rate": 9.276872389453185e-06, + "loss": 0.8311, + "step": 8753 + }, + { + "epoch": 0.5374013935357131, + "grad_norm": 0.8568130547106589, + "learning_rate": 9.274889259469146e-06, + "loss": 0.87, + "step": 8754 + }, + { + "epoch": 0.5374627827741797, + "grad_norm": 0.8048173776435495, + "learning_rate": 9.272906158152612e-06, + "loss": 0.8214, + "step": 8755 + }, + { + "epoch": 0.5375241720126461, + "grad_norm": 0.842654657743163, + "learning_rate": 9.270923085581989e-06, + "loss": 0.8389, + "step": 8756 + }, + { + "epoch": 0.5375855612511127, + "grad_norm": 0.8278439134443641, + "learning_rate": 9.268940041835675e-06, + "loss": 0.8465, + "step": 8757 + }, + { + "epoch": 0.5376469504895792, + "grad_norm": 0.9460493187691899, + "learning_rate": 9.266957026992067e-06, + "loss": 0.834, + "step": 8758 + }, + { + "epoch": 0.5377083397280457, + "grad_norm": 0.7500264921193844, + "learning_rate": 9.264974041129573e-06, + "loss": 0.819, + "step": 8759 + }, + { + "epoch": 0.5377697289665122, + "grad_norm": 0.8420381016026124, + "learning_rate": 9.262991084326583e-06, + "loss": 0.8886, + "step": 8760 + }, + { + "epoch": 0.5378311182049786, + "grad_norm": 0.8059827998827285, + "learning_rate": 9.2610081566615e-06, + "loss": 0.8274, + "step": 8761 + }, + { + "epoch": 0.5378925074434452, + "grad_norm": 0.8571367950162339, + "learning_rate": 9.259025258212718e-06, + "loss": 0.8367, + "step": 8762 + }, + { + "epoch": 0.5379538966819116, + "grad_norm": 0.8576420391720855, + "learning_rate": 9.257042389058626e-06, + "loss": 0.8565, + "step": 8763 + }, + { + "epoch": 0.5380152859203782, + "grad_norm": 0.856749592639198, + "learning_rate": 9.255059549277624e-06, + "loss": 0.8085, + "step": 8764 + }, + { + "epoch": 0.5380766751588446, + "grad_norm": 0.7852156981893446, + "learning_rate": 9.253076738948101e-06, + "loss": 0.805, + "step": 8765 + }, + { + "epoch": 0.5381380643973112, + "grad_norm": 0.8419442367241494, + "learning_rate": 9.251093958148457e-06, + "loss": 0.8242, + "step": 8766 + }, + { + "epoch": 0.5381994536357777, + "grad_norm": 0.8623694617620219, + "learning_rate": 9.249111206957065e-06, + "loss": 0.8711, + "step": 8767 + }, + { + "epoch": 0.5382608428742441, + "grad_norm": 0.7194877565342105, + "learning_rate": 9.247128485452327e-06, + "loss": 0.8021, + "step": 8768 + }, + { + "epoch": 0.5383222321127107, + "grad_norm": 0.8427572986371413, + "learning_rate": 9.245145793712625e-06, + "loss": 0.7899, + "step": 8769 + }, + { + "epoch": 0.5383836213511771, + "grad_norm": 0.873101784416187, + "learning_rate": 9.243163131816347e-06, + "loss": 0.8064, + "step": 8770 + }, + { + "epoch": 0.5384450105896437, + "grad_norm": 0.8168540635177224, + "learning_rate": 9.241180499841882e-06, + "loss": 0.8232, + "step": 8771 + }, + { + "epoch": 0.5385063998281101, + "grad_norm": 0.8776555950961619, + "learning_rate": 9.239197897867606e-06, + "loss": 0.8483, + "step": 8772 + }, + { + "epoch": 0.5385677890665767, + "grad_norm": 0.8686020753869211, + "learning_rate": 9.237215325971908e-06, + "loss": 0.756, + "step": 8773 + }, + { + "epoch": 0.5386291783050431, + "grad_norm": 0.8316172845775472, + "learning_rate": 9.235232784233164e-06, + "loss": 0.8493, + "step": 8774 + }, + { + "epoch": 0.5386905675435096, + "grad_norm": 0.7673918043770108, + "learning_rate": 9.233250272729764e-06, + "loss": 0.8718, + "step": 8775 + }, + { + "epoch": 0.5387519567819761, + "grad_norm": 0.8488818757019612, + "learning_rate": 9.23126779154008e-06, + "loss": 0.8077, + "step": 8776 + }, + { + "epoch": 0.5388133460204426, + "grad_norm": 0.9279397093700251, + "learning_rate": 9.22928534074249e-06, + "loss": 0.8611, + "step": 8777 + }, + { + "epoch": 0.5388747352589092, + "grad_norm": 0.7922282872111774, + "learning_rate": 9.227302920415375e-06, + "loss": 0.8044, + "step": 8778 + }, + { + "epoch": 0.5389361244973756, + "grad_norm": 0.8252449166708353, + "learning_rate": 9.225320530637104e-06, + "loss": 0.8279, + "step": 8779 + }, + { + "epoch": 0.5389975137358421, + "grad_norm": 0.7993051934539696, + "learning_rate": 9.223338171486058e-06, + "loss": 0.8464, + "step": 8780 + }, + { + "epoch": 0.5390589029743086, + "grad_norm": 0.830959332811738, + "learning_rate": 9.221355843040611e-06, + "loss": 0.8081, + "step": 8781 + }, + { + "epoch": 0.5391202922127751, + "grad_norm": 0.7998361809839699, + "learning_rate": 9.21937354537913e-06, + "loss": 0.863, + "step": 8782 + }, + { + "epoch": 0.5391816814512416, + "grad_norm": 0.8275806518519485, + "learning_rate": 9.217391278579986e-06, + "loss": 0.846, + "step": 8783 + }, + { + "epoch": 0.5392430706897081, + "grad_norm": 0.8098705091909857, + "learning_rate": 9.215409042721553e-06, + "loss": 0.8266, + "step": 8784 + }, + { + "epoch": 0.5393044599281746, + "grad_norm": 0.738325917834541, + "learning_rate": 9.213426837882193e-06, + "loss": 0.7699, + "step": 8785 + }, + { + "epoch": 0.5393658491666411, + "grad_norm": 0.7648968166890747, + "learning_rate": 9.211444664140282e-06, + "loss": 0.8474, + "step": 8786 + }, + { + "epoch": 0.5394272384051075, + "grad_norm": 0.8401641208964047, + "learning_rate": 9.209462521574178e-06, + "loss": 0.8121, + "step": 8787 + }, + { + "epoch": 0.5394886276435741, + "grad_norm": 0.8466889034723101, + "learning_rate": 9.207480410262248e-06, + "loss": 0.8121, + "step": 8788 + }, + { + "epoch": 0.5395500168820406, + "grad_norm": 0.7742362208395043, + "learning_rate": 9.205498330282857e-06, + "loss": 0.7907, + "step": 8789 + }, + { + "epoch": 0.5396114061205071, + "grad_norm": 0.857677390841062, + "learning_rate": 9.203516281714364e-06, + "loss": 0.848, + "step": 8790 + }, + { + "epoch": 0.5396727953589736, + "grad_norm": 0.8308867786118221, + "learning_rate": 9.201534264635137e-06, + "loss": 0.8325, + "step": 8791 + }, + { + "epoch": 0.53973418459744, + "grad_norm": 0.73851278950327, + "learning_rate": 9.19955227912353e-06, + "loss": 0.777, + "step": 8792 + }, + { + "epoch": 0.5397955738359066, + "grad_norm": 0.8259490128880855, + "learning_rate": 9.197570325257902e-06, + "loss": 0.8328, + "step": 8793 + }, + { + "epoch": 0.539856963074373, + "grad_norm": 0.8628546693489509, + "learning_rate": 9.195588403116608e-06, + "loss": 0.8759, + "step": 8794 + }, + { + "epoch": 0.5399183523128396, + "grad_norm": 0.8599341082018751, + "learning_rate": 9.193606512778008e-06, + "loss": 0.8318, + "step": 8795 + }, + { + "epoch": 0.539979741551306, + "grad_norm": 0.8105566341058821, + "learning_rate": 9.191624654320459e-06, + "loss": 0.835, + "step": 8796 + }, + { + "epoch": 0.5400411307897726, + "grad_norm": 0.8378601645386476, + "learning_rate": 9.189642827822307e-06, + "loss": 0.8202, + "step": 8797 + }, + { + "epoch": 0.540102520028239, + "grad_norm": 0.8588064004594868, + "learning_rate": 9.187661033361909e-06, + "loss": 0.8342, + "step": 8798 + }, + { + "epoch": 0.5401639092667055, + "grad_norm": 0.8271577502297395, + "learning_rate": 9.185679271017614e-06, + "loss": 0.8247, + "step": 8799 + }, + { + "epoch": 0.5402252985051721, + "grad_norm": 0.7871683175063745, + "learning_rate": 9.183697540867774e-06, + "loss": 0.7653, + "step": 8800 + }, + { + "epoch": 0.5402866877436385, + "grad_norm": 0.7981219876172047, + "learning_rate": 9.181715842990738e-06, + "loss": 0.7746, + "step": 8801 + }, + { + "epoch": 0.5403480769821051, + "grad_norm": 0.7518102083844579, + "learning_rate": 9.179734177464847e-06, + "loss": 0.8296, + "step": 8802 + }, + { + "epoch": 0.5404094662205715, + "grad_norm": 0.8628519405500218, + "learning_rate": 9.177752544368455e-06, + "loss": 0.8419, + "step": 8803 + }, + { + "epoch": 0.5404708554590381, + "grad_norm": 0.8098413530962263, + "learning_rate": 9.175770943779898e-06, + "loss": 0.8268, + "step": 8804 + }, + { + "epoch": 0.5405322446975045, + "grad_norm": 0.815363965704805, + "learning_rate": 9.173789375777527e-06, + "loss": 0.8649, + "step": 8805 + }, + { + "epoch": 0.540593633935971, + "grad_norm": 0.8533650518829086, + "learning_rate": 9.171807840439683e-06, + "loss": 0.8227, + "step": 8806 + }, + { + "epoch": 0.5406550231744375, + "grad_norm": 0.8815393336777565, + "learning_rate": 9.169826337844703e-06, + "loss": 0.8785, + "step": 8807 + }, + { + "epoch": 0.540716412412904, + "grad_norm": 0.8056986037767818, + "learning_rate": 9.167844868070926e-06, + "loss": 0.8604, + "step": 8808 + }, + { + "epoch": 0.5407778016513705, + "grad_norm": 0.7404837799707492, + "learning_rate": 9.165863431196693e-06, + "loss": 0.8068, + "step": 8809 + }, + { + "epoch": 0.540839190889837, + "grad_norm": 0.9439593660890611, + "learning_rate": 9.163882027300339e-06, + "loss": 0.8632, + "step": 8810 + }, + { + "epoch": 0.5409005801283036, + "grad_norm": 0.7775426655780907, + "learning_rate": 9.161900656460203e-06, + "loss": 0.8384, + "step": 8811 + }, + { + "epoch": 0.54096196936677, + "grad_norm": 0.8018020837058012, + "learning_rate": 9.159919318754616e-06, + "loss": 0.8096, + "step": 8812 + }, + { + "epoch": 0.5410233586052365, + "grad_norm": 0.7930192780694373, + "learning_rate": 9.157938014261909e-06, + "loss": 0.8892, + "step": 8813 + }, + { + "epoch": 0.541084747843703, + "grad_norm": 0.6659249747016311, + "learning_rate": 9.155956743060417e-06, + "loss": 0.8185, + "step": 8814 + }, + { + "epoch": 0.5411461370821695, + "grad_norm": 0.7202667863379518, + "learning_rate": 9.153975505228467e-06, + "loss": 0.7768, + "step": 8815 + }, + { + "epoch": 0.541207526320636, + "grad_norm": 0.8668905644525005, + "learning_rate": 9.151994300844395e-06, + "loss": 0.883, + "step": 8816 + }, + { + "epoch": 0.5412689155591025, + "grad_norm": 0.872096490890682, + "learning_rate": 9.15001312998652e-06, + "loss": 0.847, + "step": 8817 + }, + { + "epoch": 0.5413303047975689, + "grad_norm": 0.7509812230109587, + "learning_rate": 9.148031992733174e-06, + "loss": 0.8046, + "step": 8818 + }, + { + "epoch": 0.5413916940360355, + "grad_norm": 0.8138500587210653, + "learning_rate": 9.146050889162679e-06, + "loss": 0.8067, + "step": 8819 + }, + { + "epoch": 0.541453083274502, + "grad_norm": 0.7633164317303643, + "learning_rate": 9.144069819353362e-06, + "loss": 0.7981, + "step": 8820 + }, + { + "epoch": 0.5415144725129685, + "grad_norm": 0.8352578701241835, + "learning_rate": 9.142088783383541e-06, + "loss": 0.9024, + "step": 8821 + }, + { + "epoch": 0.541575861751435, + "grad_norm": 0.8006058272016368, + "learning_rate": 9.140107781331537e-06, + "loss": 0.853, + "step": 8822 + }, + { + "epoch": 0.5416372509899015, + "grad_norm": 0.781357344299194, + "learning_rate": 9.138126813275673e-06, + "loss": 0.8239, + "step": 8823 + }, + { + "epoch": 0.541698640228368, + "grad_norm": 0.7944243342640306, + "learning_rate": 9.136145879294264e-06, + "loss": 0.8474, + "step": 8824 + }, + { + "epoch": 0.5417600294668344, + "grad_norm": 0.8000229669825563, + "learning_rate": 9.134164979465633e-06, + "loss": 0.8847, + "step": 8825 + }, + { + "epoch": 0.541821418705301, + "grad_norm": 0.8164625750172869, + "learning_rate": 9.13218411386809e-06, + "loss": 0.8567, + "step": 8826 + }, + { + "epoch": 0.5418828079437674, + "grad_norm": 0.7417901428007533, + "learning_rate": 9.130203282579947e-06, + "loss": 0.8384, + "step": 8827 + }, + { + "epoch": 0.541944197182234, + "grad_norm": 0.7510070731640262, + "learning_rate": 9.12822248567952e-06, + "loss": 0.8398, + "step": 8828 + }, + { + "epoch": 0.5420055864207004, + "grad_norm": 0.9039466868379015, + "learning_rate": 9.126241723245123e-06, + "loss": 0.8713, + "step": 8829 + }, + { + "epoch": 0.542066975659167, + "grad_norm": 0.8019742461360303, + "learning_rate": 9.124260995355068e-06, + "loss": 0.7937, + "step": 8830 + }, + { + "epoch": 0.5421283648976335, + "grad_norm": 0.809002742978914, + "learning_rate": 9.122280302087654e-06, + "loss": 0.8647, + "step": 8831 + }, + { + "epoch": 0.5421897541360999, + "grad_norm": 0.8207680662593705, + "learning_rate": 9.120299643521195e-06, + "loss": 0.8665, + "step": 8832 + }, + { + "epoch": 0.5422511433745665, + "grad_norm": 0.7234917477253898, + "learning_rate": 9.118319019733995e-06, + "loss": 0.7675, + "step": 8833 + }, + { + "epoch": 0.5423125326130329, + "grad_norm": 0.7861386566952129, + "learning_rate": 9.11633843080436e-06, + "loss": 0.7977, + "step": 8834 + }, + { + "epoch": 0.5423739218514995, + "grad_norm": 0.7944575487886922, + "learning_rate": 9.114357876810598e-06, + "loss": 0.8364, + "step": 8835 + }, + { + "epoch": 0.5424353110899659, + "grad_norm": 0.7835093692780224, + "learning_rate": 9.112377357831e-06, + "loss": 0.8519, + "step": 8836 + }, + { + "epoch": 0.5424967003284324, + "grad_norm": 0.8765227761778385, + "learning_rate": 9.110396873943876e-06, + "loss": 0.8249, + "step": 8837 + }, + { + "epoch": 0.5425580895668989, + "grad_norm": 0.7802470592529529, + "learning_rate": 9.108416425227517e-06, + "loss": 0.8074, + "step": 8838 + }, + { + "epoch": 0.5426194788053654, + "grad_norm": 0.7719818155826433, + "learning_rate": 9.106436011760229e-06, + "loss": 0.8135, + "step": 8839 + }, + { + "epoch": 0.5426808680438319, + "grad_norm": 0.8440162734118851, + "learning_rate": 9.104455633620305e-06, + "loss": 0.8251, + "step": 8840 + }, + { + "epoch": 0.5427422572822984, + "grad_norm": 0.89506143042581, + "learning_rate": 9.102475290886037e-06, + "loss": 0.8009, + "step": 8841 + }, + { + "epoch": 0.542803646520765, + "grad_norm": 0.7568291547633254, + "learning_rate": 9.100494983635723e-06, + "loss": 0.7793, + "step": 8842 + }, + { + "epoch": 0.5428650357592314, + "grad_norm": 0.8568203333506313, + "learning_rate": 9.098514711947651e-06, + "loss": 0.812, + "step": 8843 + }, + { + "epoch": 0.5429264249976979, + "grad_norm": 0.8458476283988124, + "learning_rate": 9.096534475900115e-06, + "loss": 0.8, + "step": 8844 + }, + { + "epoch": 0.5429878142361644, + "grad_norm": 0.8680975808770404, + "learning_rate": 9.094554275571407e-06, + "loss": 0.8672, + "step": 8845 + }, + { + "epoch": 0.5430492034746309, + "grad_norm": 0.8157913993619722, + "learning_rate": 9.092574111039808e-06, + "loss": 0.8238, + "step": 8846 + }, + { + "epoch": 0.5431105927130974, + "grad_norm": 0.776658709191601, + "learning_rate": 9.090593982383605e-06, + "loss": 0.8046, + "step": 8847 + }, + { + "epoch": 0.5431719819515639, + "grad_norm": 0.8502173572879843, + "learning_rate": 9.088613889681089e-06, + "loss": 0.8116, + "step": 8848 + }, + { + "epoch": 0.5432333711900303, + "grad_norm": 0.7809903516323151, + "learning_rate": 9.086633833010538e-06, + "loss": 0.8509, + "step": 8849 + }, + { + "epoch": 0.5432947604284969, + "grad_norm": 0.780745369352836, + "learning_rate": 9.08465381245024e-06, + "loss": 0.8297, + "step": 8850 + }, + { + "epoch": 0.5433561496669633, + "grad_norm": 0.8364645763938817, + "learning_rate": 9.08267382807847e-06, + "loss": 0.8287, + "step": 8851 + }, + { + "epoch": 0.5434175389054299, + "grad_norm": 0.9182292109469188, + "learning_rate": 9.080693879973508e-06, + "loss": 0.8187, + "step": 8852 + }, + { + "epoch": 0.5434789281438964, + "grad_norm": 0.7814214581278779, + "learning_rate": 9.078713968213638e-06, + "loss": 0.8402, + "step": 8853 + }, + { + "epoch": 0.5435403173823629, + "grad_norm": 0.7248962916925374, + "learning_rate": 9.076734092877129e-06, + "loss": 0.7595, + "step": 8854 + }, + { + "epoch": 0.5436017066208294, + "grad_norm": 0.7864286543335058, + "learning_rate": 9.074754254042261e-06, + "loss": 0.7695, + "step": 8855 + }, + { + "epoch": 0.5436630958592958, + "grad_norm": 0.7441923786956068, + "learning_rate": 9.072774451787307e-06, + "loss": 0.768, + "step": 8856 + }, + { + "epoch": 0.5437244850977624, + "grad_norm": 0.9145135571235334, + "learning_rate": 9.070794686190537e-06, + "loss": 0.8433, + "step": 8857 + }, + { + "epoch": 0.5437858743362288, + "grad_norm": 0.8243690913255608, + "learning_rate": 9.06881495733022e-06, + "loss": 0.8071, + "step": 8858 + }, + { + "epoch": 0.5438472635746954, + "grad_norm": 0.7262812314425452, + "learning_rate": 9.06683526528463e-06, + "loss": 0.8135, + "step": 8859 + }, + { + "epoch": 0.5439086528131618, + "grad_norm": 0.8446227507298383, + "learning_rate": 9.064855610132037e-06, + "loss": 0.831, + "step": 8860 + }, + { + "epoch": 0.5439700420516284, + "grad_norm": 0.8410575891765576, + "learning_rate": 9.062875991950697e-06, + "loss": 0.7973, + "step": 8861 + }, + { + "epoch": 0.5440314312900948, + "grad_norm": 0.8471470305468548, + "learning_rate": 9.060896410818885e-06, + "loss": 0.8255, + "step": 8862 + }, + { + "epoch": 0.5440928205285613, + "grad_norm": 0.9325028424695969, + "learning_rate": 9.058916866814857e-06, + "loss": 0.8321, + "step": 8863 + }, + { + "epoch": 0.5441542097670279, + "grad_norm": 0.9132163010363998, + "learning_rate": 9.056937360016881e-06, + "loss": 0.7955, + "step": 8864 + }, + { + "epoch": 0.5442155990054943, + "grad_norm": 0.7812542316026103, + "learning_rate": 9.054957890503218e-06, + "loss": 0.8034, + "step": 8865 + }, + { + "epoch": 0.5442769882439609, + "grad_norm": 0.8206503178072229, + "learning_rate": 9.05297845835212e-06, + "loss": 0.8063, + "step": 8866 + }, + { + "epoch": 0.5443383774824273, + "grad_norm": 0.8305713383372639, + "learning_rate": 9.050999063641848e-06, + "loss": 0.8095, + "step": 8867 + }, + { + "epoch": 0.5443997667208939, + "grad_norm": 0.8632365362348172, + "learning_rate": 9.049019706450658e-06, + "loss": 0.9108, + "step": 8868 + }, + { + "epoch": 0.5444611559593603, + "grad_norm": 0.8285193914641386, + "learning_rate": 9.047040386856807e-06, + "loss": 0.8124, + "step": 8869 + }, + { + "epoch": 0.5445225451978268, + "grad_norm": 0.8693051471950015, + "learning_rate": 9.04506110493855e-06, + "loss": 0.8377, + "step": 8870 + }, + { + "epoch": 0.5445839344362933, + "grad_norm": 0.8251570314505666, + "learning_rate": 9.043081860774132e-06, + "loss": 0.8179, + "step": 8871 + }, + { + "epoch": 0.5446453236747598, + "grad_norm": 0.8408643713204773, + "learning_rate": 9.041102654441802e-06, + "loss": 0.8469, + "step": 8872 + }, + { + "epoch": 0.5447067129132264, + "grad_norm": 0.8493031539689214, + "learning_rate": 9.039123486019817e-06, + "loss": 0.8273, + "step": 8873 + }, + { + "epoch": 0.5447681021516928, + "grad_norm": 0.7756875417018065, + "learning_rate": 9.037144355586417e-06, + "loss": 0.8377, + "step": 8874 + }, + { + "epoch": 0.5448294913901593, + "grad_norm": 0.8245990557004877, + "learning_rate": 9.035165263219854e-06, + "loss": 0.7853, + "step": 8875 + }, + { + "epoch": 0.5448908806286258, + "grad_norm": 0.840904206264734, + "learning_rate": 9.033186208998367e-06, + "loss": 0.8305, + "step": 8876 + }, + { + "epoch": 0.5449522698670923, + "grad_norm": 0.8508384180715597, + "learning_rate": 9.031207193000198e-06, + "loss": 0.7997, + "step": 8877 + }, + { + "epoch": 0.5450136591055588, + "grad_norm": 0.8064341893374111, + "learning_rate": 9.029228215303591e-06, + "loss": 0.8162, + "step": 8878 + }, + { + "epoch": 0.5450750483440253, + "grad_norm": 0.7775669049053713, + "learning_rate": 9.027249275986783e-06, + "loss": 0.7863, + "step": 8879 + }, + { + "epoch": 0.5451364375824918, + "grad_norm": 0.6341718532849796, + "learning_rate": 9.025270375128018e-06, + "loss": 0.6617, + "step": 8880 + }, + { + "epoch": 0.5451978268209583, + "grad_norm": 0.8117774391179665, + "learning_rate": 9.02329151280553e-06, + "loss": 0.8366, + "step": 8881 + }, + { + "epoch": 0.5452592160594247, + "grad_norm": 0.9254425058762655, + "learning_rate": 9.021312689097546e-06, + "loss": 0.8835, + "step": 8882 + }, + { + "epoch": 0.5453206052978913, + "grad_norm": 0.7732876332880297, + "learning_rate": 9.019333904082307e-06, + "loss": 0.8256, + "step": 8883 + }, + { + "epoch": 0.5453819945363578, + "grad_norm": 0.7838356968863462, + "learning_rate": 9.017355157838049e-06, + "loss": 0.7685, + "step": 8884 + }, + { + "epoch": 0.5454433837748243, + "grad_norm": 0.7715501546887331, + "learning_rate": 9.015376450442995e-06, + "loss": 0.8577, + "step": 8885 + }, + { + "epoch": 0.5455047730132908, + "grad_norm": 0.7997414778905241, + "learning_rate": 9.013397781975371e-06, + "loss": 0.8455, + "step": 8886 + }, + { + "epoch": 0.5455661622517572, + "grad_norm": 0.8301519521614392, + "learning_rate": 9.011419152513414e-06, + "loss": 0.7661, + "step": 8887 + }, + { + "epoch": 0.5456275514902238, + "grad_norm": 0.8258811030156157, + "learning_rate": 9.009440562135342e-06, + "loss": 0.8379, + "step": 8888 + }, + { + "epoch": 0.5456889407286902, + "grad_norm": 0.8366302517143868, + "learning_rate": 9.007462010919387e-06, + "loss": 0.8128, + "step": 8889 + }, + { + "epoch": 0.5457503299671568, + "grad_norm": 0.8209190717235351, + "learning_rate": 9.005483498943764e-06, + "loss": 0.8646, + "step": 8890 + }, + { + "epoch": 0.5458117192056232, + "grad_norm": 0.7679165273090501, + "learning_rate": 9.003505026286697e-06, + "loss": 0.7966, + "step": 8891 + }, + { + "epoch": 0.5458731084440898, + "grad_norm": 0.8694157024041967, + "learning_rate": 9.001526593026407e-06, + "loss": 0.8099, + "step": 8892 + }, + { + "epoch": 0.5459344976825562, + "grad_norm": 0.8421929299824027, + "learning_rate": 8.99954819924111e-06, + "loss": 0.7912, + "step": 8893 + }, + { + "epoch": 0.5459958869210227, + "grad_norm": 0.8179250441302316, + "learning_rate": 8.997569845009027e-06, + "loss": 0.8054, + "step": 8894 + }, + { + "epoch": 0.5460572761594893, + "grad_norm": 0.8241003848664562, + "learning_rate": 8.995591530408367e-06, + "loss": 0.7879, + "step": 8895 + }, + { + "epoch": 0.5461186653979557, + "grad_norm": 0.798051747560385, + "learning_rate": 8.993613255517345e-06, + "loss": 0.8409, + "step": 8896 + }, + { + "epoch": 0.5461800546364223, + "grad_norm": 0.8236741721982673, + "learning_rate": 8.991635020414173e-06, + "loss": 0.8743, + "step": 8897 + }, + { + "epoch": 0.5462414438748887, + "grad_norm": 0.8618491307068364, + "learning_rate": 8.989656825177062e-06, + "loss": 0.8387, + "step": 8898 + }, + { + "epoch": 0.5463028331133553, + "grad_norm": 0.7717143697637974, + "learning_rate": 8.987678669884224e-06, + "loss": 0.8019, + "step": 8899 + }, + { + "epoch": 0.5463642223518217, + "grad_norm": 0.8834361186602747, + "learning_rate": 8.98570055461386e-06, + "loss": 0.8646, + "step": 8900 + }, + { + "epoch": 0.5464256115902882, + "grad_norm": 0.7836295920293034, + "learning_rate": 8.983722479444176e-06, + "loss": 0.8252, + "step": 8901 + }, + { + "epoch": 0.5464870008287547, + "grad_norm": 0.8242100323581234, + "learning_rate": 8.981744444453378e-06, + "loss": 0.7914, + "step": 8902 + }, + { + "epoch": 0.5465483900672212, + "grad_norm": 0.869038894495724, + "learning_rate": 8.97976644971967e-06, + "loss": 0.869, + "step": 8903 + }, + { + "epoch": 0.5466097793056877, + "grad_norm": 0.8624821466564885, + "learning_rate": 8.977788495321252e-06, + "loss": 0.8118, + "step": 8904 + }, + { + "epoch": 0.5466711685441542, + "grad_norm": 0.7838759510019688, + "learning_rate": 8.97581058133632e-06, + "loss": 0.8392, + "step": 8905 + }, + { + "epoch": 0.5467325577826208, + "grad_norm": 0.8065471374245969, + "learning_rate": 8.973832707843074e-06, + "loss": 0.7845, + "step": 8906 + }, + { + "epoch": 0.5467939470210872, + "grad_norm": 0.8370055827218583, + "learning_rate": 8.971854874919707e-06, + "loss": 0.8798, + "step": 8907 + }, + { + "epoch": 0.5468553362595537, + "grad_norm": 0.9462075395112882, + "learning_rate": 8.969877082644418e-06, + "loss": 0.8079, + "step": 8908 + }, + { + "epoch": 0.5469167254980202, + "grad_norm": 0.9076575694642363, + "learning_rate": 8.967899331095399e-06, + "loss": 0.8731, + "step": 8909 + }, + { + "epoch": 0.5469781147364867, + "grad_norm": 0.8433085584564335, + "learning_rate": 8.96592162035084e-06, + "loss": 0.8459, + "step": 8910 + }, + { + "epoch": 0.5470395039749532, + "grad_norm": 0.8209343260490025, + "learning_rate": 8.963943950488925e-06, + "loss": 0.839, + "step": 8911 + }, + { + "epoch": 0.5471008932134197, + "grad_norm": 0.8631630279852174, + "learning_rate": 8.961966321587851e-06, + "loss": 0.8271, + "step": 8912 + }, + { + "epoch": 0.5471622824518861, + "grad_norm": 0.8325412826298247, + "learning_rate": 8.959988733725797e-06, + "loss": 0.7919, + "step": 8913 + }, + { + "epoch": 0.5472236716903527, + "grad_norm": 0.79740613977284, + "learning_rate": 8.958011186980954e-06, + "loss": 0.8306, + "step": 8914 + }, + { + "epoch": 0.5472850609288191, + "grad_norm": 0.8752979881300691, + "learning_rate": 8.956033681431501e-06, + "loss": 0.819, + "step": 8915 + }, + { + "epoch": 0.5473464501672857, + "grad_norm": 0.7511878770245182, + "learning_rate": 8.954056217155618e-06, + "loss": 0.8406, + "step": 8916 + }, + { + "epoch": 0.5474078394057522, + "grad_norm": 0.743133183862007, + "learning_rate": 8.952078794231488e-06, + "loss": 0.8132, + "step": 8917 + }, + { + "epoch": 0.5474692286442187, + "grad_norm": 0.8496643658173374, + "learning_rate": 8.950101412737287e-06, + "loss": 0.8285, + "step": 8918 + }, + { + "epoch": 0.5475306178826852, + "grad_norm": 0.7607792656549102, + "learning_rate": 8.948124072751195e-06, + "loss": 0.8203, + "step": 8919 + }, + { + "epoch": 0.5475920071211516, + "grad_norm": 0.8745095146562385, + "learning_rate": 8.946146774351383e-06, + "loss": 0.7931, + "step": 8920 + }, + { + "epoch": 0.5476533963596182, + "grad_norm": 0.7839892204236675, + "learning_rate": 8.944169517616023e-06, + "loss": 0.8006, + "step": 8921 + }, + { + "epoch": 0.5477147855980846, + "grad_norm": 0.8711195934107759, + "learning_rate": 8.942192302623292e-06, + "loss": 0.8403, + "step": 8922 + }, + { + "epoch": 0.5477761748365512, + "grad_norm": 0.7842296651717646, + "learning_rate": 8.940215129451356e-06, + "loss": 0.8291, + "step": 8923 + }, + { + "epoch": 0.5478375640750176, + "grad_norm": 0.8195251685264063, + "learning_rate": 8.938237998178387e-06, + "loss": 0.859, + "step": 8924 + }, + { + "epoch": 0.5478989533134841, + "grad_norm": 0.8044941098537705, + "learning_rate": 8.936260908882544e-06, + "loss": 0.8614, + "step": 8925 + }, + { + "epoch": 0.5479603425519507, + "grad_norm": 0.8227464546667014, + "learning_rate": 8.934283861641998e-06, + "loss": 0.8446, + "step": 8926 + }, + { + "epoch": 0.5480217317904171, + "grad_norm": 0.8136632216044305, + "learning_rate": 8.93230685653491e-06, + "loss": 0.755, + "step": 8927 + }, + { + "epoch": 0.5480831210288837, + "grad_norm": 0.8441077698805538, + "learning_rate": 8.930329893639444e-06, + "loss": 0.8694, + "step": 8928 + }, + { + "epoch": 0.5481445102673501, + "grad_norm": 0.8107745919460663, + "learning_rate": 8.92835297303376e-06, + "loss": 0.817, + "step": 8929 + }, + { + "epoch": 0.5482058995058167, + "grad_norm": 0.7825391431167006, + "learning_rate": 8.92637609479601e-06, + "loss": 0.7822, + "step": 8930 + }, + { + "epoch": 0.5482672887442831, + "grad_norm": 0.7358991595518923, + "learning_rate": 8.924399259004357e-06, + "loss": 0.8483, + "step": 8931 + }, + { + "epoch": 0.5483286779827496, + "grad_norm": 0.8253292253251051, + "learning_rate": 8.922422465736953e-06, + "loss": 0.8585, + "step": 8932 + }, + { + "epoch": 0.5483900672212161, + "grad_norm": 0.8205760850203289, + "learning_rate": 8.920445715071953e-06, + "loss": 0.8618, + "step": 8933 + }, + { + "epoch": 0.5484514564596826, + "grad_norm": 0.8108921605185492, + "learning_rate": 8.91846900708751e-06, + "loss": 0.8586, + "step": 8934 + }, + { + "epoch": 0.5485128456981491, + "grad_norm": 0.78881531606204, + "learning_rate": 8.916492341861772e-06, + "loss": 0.7686, + "step": 8935 + }, + { + "epoch": 0.5485742349366156, + "grad_norm": 0.5986534059222294, + "learning_rate": 8.914515719472882e-06, + "loss": 0.6756, + "step": 8936 + }, + { + "epoch": 0.5486356241750822, + "grad_norm": 0.7991085333294909, + "learning_rate": 8.912539139998994e-06, + "loss": 0.7872, + "step": 8937 + }, + { + "epoch": 0.5486970134135486, + "grad_norm": 0.7656701477735613, + "learning_rate": 8.91056260351825e-06, + "loss": 0.8074, + "step": 8938 + }, + { + "epoch": 0.5487584026520151, + "grad_norm": 0.7726068558317315, + "learning_rate": 8.908586110108794e-06, + "loss": 0.8484, + "step": 8939 + }, + { + "epoch": 0.5488197918904816, + "grad_norm": 0.8328504171462293, + "learning_rate": 8.906609659848766e-06, + "loss": 0.8269, + "step": 8940 + }, + { + "epoch": 0.5488811811289481, + "grad_norm": 0.7444507330977616, + "learning_rate": 8.904633252816302e-06, + "loss": 0.8311, + "step": 8941 + }, + { + "epoch": 0.5489425703674146, + "grad_norm": 0.8416810477661198, + "learning_rate": 8.902656889089548e-06, + "loss": 0.8333, + "step": 8942 + }, + { + "epoch": 0.5490039596058811, + "grad_norm": 0.8484836881399123, + "learning_rate": 8.900680568746633e-06, + "loss": 0.8116, + "step": 8943 + }, + { + "epoch": 0.5490653488443475, + "grad_norm": 0.7766564800606028, + "learning_rate": 8.898704291865701e-06, + "loss": 0.8499, + "step": 8944 + }, + { + "epoch": 0.5491267380828141, + "grad_norm": 0.8272008869774126, + "learning_rate": 8.896728058524873e-06, + "loss": 0.8316, + "step": 8945 + }, + { + "epoch": 0.5491881273212805, + "grad_norm": 0.7154420149605639, + "learning_rate": 8.894751868802286e-06, + "loss": 0.7908, + "step": 8946 + }, + { + "epoch": 0.5492495165597471, + "grad_norm": 0.766683092707077, + "learning_rate": 8.89277572277607e-06, + "loss": 0.8068, + "step": 8947 + }, + { + "epoch": 0.5493109057982136, + "grad_norm": 0.9214529022494622, + "learning_rate": 8.89079962052435e-06, + "loss": 0.8783, + "step": 8948 + }, + { + "epoch": 0.5493722950366801, + "grad_norm": 0.8279965427918404, + "learning_rate": 8.88882356212526e-06, + "loss": 0.8639, + "step": 8949 + }, + { + "epoch": 0.5494336842751466, + "grad_norm": 0.90161168413021, + "learning_rate": 8.88684754765691e-06, + "loss": 0.8556, + "step": 8950 + }, + { + "epoch": 0.549495073513613, + "grad_norm": 0.6865906022853794, + "learning_rate": 8.884871577197433e-06, + "loss": 0.8587, + "step": 8951 + }, + { + "epoch": 0.5495564627520796, + "grad_norm": 0.8532423939899121, + "learning_rate": 8.882895650824943e-06, + "loss": 0.8052, + "step": 8952 + }, + { + "epoch": 0.549617851990546, + "grad_norm": 0.8844921647075825, + "learning_rate": 8.88091976861757e-06, + "loss": 0.8043, + "step": 8953 + }, + { + "epoch": 0.5496792412290126, + "grad_norm": 0.841381663459697, + "learning_rate": 8.87894393065342e-06, + "loss": 0.8221, + "step": 8954 + }, + { + "epoch": 0.549740630467479, + "grad_norm": 0.8200902577954632, + "learning_rate": 8.87696813701061e-06, + "loss": 0.8249, + "step": 8955 + }, + { + "epoch": 0.5498020197059456, + "grad_norm": 0.8506545776922783, + "learning_rate": 8.874992387767257e-06, + "loss": 0.8562, + "step": 8956 + }, + { + "epoch": 0.549863408944412, + "grad_norm": 0.7874292724983233, + "learning_rate": 8.873016683001471e-06, + "loss": 0.8433, + "step": 8957 + }, + { + "epoch": 0.5499247981828785, + "grad_norm": 0.8142869147087446, + "learning_rate": 8.871041022791367e-06, + "loss": 0.8204, + "step": 8958 + }, + { + "epoch": 0.5499861874213451, + "grad_norm": 0.6447425435635128, + "learning_rate": 8.869065407215047e-06, + "loss": 0.7162, + "step": 8959 + }, + { + "epoch": 0.5500475766598115, + "grad_norm": 0.8971201472922824, + "learning_rate": 8.86708983635062e-06, + "loss": 0.8666, + "step": 8960 + }, + { + "epoch": 0.5501089658982781, + "grad_norm": 0.8488228789718644, + "learning_rate": 8.86511431027619e-06, + "loss": 0.8445, + "step": 8961 + }, + { + "epoch": 0.5501703551367445, + "grad_norm": 0.8849313345106379, + "learning_rate": 8.863138829069864e-06, + "loss": 0.879, + "step": 8962 + }, + { + "epoch": 0.550231744375211, + "grad_norm": 0.8007135042004933, + "learning_rate": 8.86116339280974e-06, + "loss": 0.8765, + "step": 8963 + }, + { + "epoch": 0.5502931336136775, + "grad_norm": 0.8686803985514931, + "learning_rate": 8.859188001573916e-06, + "loss": 0.89, + "step": 8964 + }, + { + "epoch": 0.550354522852144, + "grad_norm": 0.7944509454594493, + "learning_rate": 8.857212655440493e-06, + "loss": 0.8107, + "step": 8965 + }, + { + "epoch": 0.5504159120906105, + "grad_norm": 0.8185115101413719, + "learning_rate": 8.855237354487563e-06, + "loss": 0.8323, + "step": 8966 + }, + { + "epoch": 0.550477301329077, + "grad_norm": 0.8038905159726529, + "learning_rate": 8.853262098793227e-06, + "loss": 0.7889, + "step": 8967 + }, + { + "epoch": 0.5505386905675436, + "grad_norm": 0.822038499769518, + "learning_rate": 8.851286888435573e-06, + "loss": 0.8317, + "step": 8968 + }, + { + "epoch": 0.55060007980601, + "grad_norm": 0.8204895898042164, + "learning_rate": 8.849311723492689e-06, + "loss": 0.8524, + "step": 8969 + }, + { + "epoch": 0.5506614690444765, + "grad_norm": 0.8302859162238441, + "learning_rate": 8.847336604042669e-06, + "loss": 0.8068, + "step": 8970 + }, + { + "epoch": 0.550722858282943, + "grad_norm": 0.8476709802262608, + "learning_rate": 8.845361530163597e-06, + "loss": 0.8601, + "step": 8971 + }, + { + "epoch": 0.5507842475214095, + "grad_norm": 0.794418591674026, + "learning_rate": 8.84338650193356e-06, + "loss": 0.8158, + "step": 8972 + }, + { + "epoch": 0.550845636759876, + "grad_norm": 0.9039760847696623, + "learning_rate": 8.841411519430642e-06, + "loss": 0.838, + "step": 8973 + }, + { + "epoch": 0.5509070259983425, + "grad_norm": 0.9055160623018829, + "learning_rate": 8.839436582732922e-06, + "loss": 0.8597, + "step": 8974 + }, + { + "epoch": 0.550968415236809, + "grad_norm": 0.8784556501728015, + "learning_rate": 8.837461691918478e-06, + "loss": 0.8559, + "step": 8975 + }, + { + "epoch": 0.5510298044752755, + "grad_norm": 0.8570052346136944, + "learning_rate": 8.835486847065396e-06, + "loss": 0.8244, + "step": 8976 + }, + { + "epoch": 0.5510911937137419, + "grad_norm": 0.8115027039412634, + "learning_rate": 8.833512048251742e-06, + "loss": 0.8369, + "step": 8977 + }, + { + "epoch": 0.5511525829522085, + "grad_norm": 0.8201696356529152, + "learning_rate": 8.8315372955556e-06, + "loss": 0.822, + "step": 8978 + }, + { + "epoch": 0.551213972190675, + "grad_norm": 0.9062894352238864, + "learning_rate": 8.829562589055037e-06, + "loss": 0.8262, + "step": 8979 + }, + { + "epoch": 0.5512753614291415, + "grad_norm": 0.897861594708466, + "learning_rate": 8.827587928828123e-06, + "loss": 0.7914, + "step": 8980 + }, + { + "epoch": 0.551336750667608, + "grad_norm": 0.840205258216971, + "learning_rate": 8.82561331495293e-06, + "loss": 0.8112, + "step": 8981 + }, + { + "epoch": 0.5513981399060744, + "grad_norm": 0.7539523261825885, + "learning_rate": 8.823638747507523e-06, + "loss": 0.7717, + "step": 8982 + }, + { + "epoch": 0.551459529144541, + "grad_norm": 0.8157727018354178, + "learning_rate": 8.82166422656997e-06, + "loss": 0.8252, + "step": 8983 + }, + { + "epoch": 0.5515209183830074, + "grad_norm": 0.8083269882087336, + "learning_rate": 8.819689752218332e-06, + "loss": 0.8488, + "step": 8984 + }, + { + "epoch": 0.551582307621474, + "grad_norm": 0.7795618436290636, + "learning_rate": 8.817715324530667e-06, + "loss": 0.8004, + "step": 8985 + }, + { + "epoch": 0.5516436968599404, + "grad_norm": 0.9136490778669477, + "learning_rate": 8.815740943585042e-06, + "loss": 0.8469, + "step": 8986 + }, + { + "epoch": 0.551705086098407, + "grad_norm": 0.63691805576282, + "learning_rate": 8.813766609459508e-06, + "loss": 0.6457, + "step": 8987 + }, + { + "epoch": 0.5517664753368734, + "grad_norm": 0.8436782833411215, + "learning_rate": 8.811792322232132e-06, + "loss": 0.8223, + "step": 8988 + }, + { + "epoch": 0.5518278645753399, + "grad_norm": 0.787236285928035, + "learning_rate": 8.809818081980954e-06, + "loss": 0.8139, + "step": 8989 + }, + { + "epoch": 0.5518892538138065, + "grad_norm": 0.7887881901708677, + "learning_rate": 8.807843888784035e-06, + "loss": 0.7925, + "step": 8990 + }, + { + "epoch": 0.5519506430522729, + "grad_norm": 0.8115526450130119, + "learning_rate": 8.80586974271942e-06, + "loss": 0.872, + "step": 8991 + }, + { + "epoch": 0.5520120322907395, + "grad_norm": 0.8996266879111375, + "learning_rate": 8.803895643865163e-06, + "loss": 0.8107, + "step": 8992 + }, + { + "epoch": 0.5520734215292059, + "grad_norm": 0.8422967060483963, + "learning_rate": 8.801921592299312e-06, + "loss": 0.791, + "step": 8993 + }, + { + "epoch": 0.5521348107676725, + "grad_norm": 0.8211918601260807, + "learning_rate": 8.799947588099902e-06, + "loss": 0.8332, + "step": 8994 + }, + { + "epoch": 0.5521962000061389, + "grad_norm": 0.8124268474224013, + "learning_rate": 8.797973631344986e-06, + "loss": 0.8124, + "step": 8995 + }, + { + "epoch": 0.5522575892446054, + "grad_norm": 0.7737842546748479, + "learning_rate": 8.795999722112598e-06, + "loss": 0.8095, + "step": 8996 + }, + { + "epoch": 0.5523189784830719, + "grad_norm": 0.8008490177345812, + "learning_rate": 8.794025860480782e-06, + "loss": 0.8535, + "step": 8997 + }, + { + "epoch": 0.5523803677215384, + "grad_norm": 0.8288468596371392, + "learning_rate": 8.792052046527578e-06, + "loss": 0.8681, + "step": 8998 + }, + { + "epoch": 0.5524417569600049, + "grad_norm": 0.8263780325946155, + "learning_rate": 8.790078280331011e-06, + "loss": 0.845, + "step": 8999 + }, + { + "epoch": 0.5525031461984714, + "grad_norm": 0.798966674934247, + "learning_rate": 8.788104561969124e-06, + "loss": 0.8328, + "step": 9000 + }, + { + "epoch": 0.552564535436938, + "grad_norm": 0.8121772998891701, + "learning_rate": 8.786130891519945e-06, + "loss": 0.841, + "step": 9001 + }, + { + "epoch": 0.5526259246754044, + "grad_norm": 0.7574667016571636, + "learning_rate": 8.784157269061502e-06, + "loss": 0.8216, + "step": 9002 + }, + { + "epoch": 0.5526873139138709, + "grad_norm": 0.7346879289072066, + "learning_rate": 8.78218369467183e-06, + "loss": 0.8285, + "step": 9003 + }, + { + "epoch": 0.5527487031523374, + "grad_norm": 0.8825857702078134, + "learning_rate": 8.780210168428946e-06, + "loss": 0.8218, + "step": 9004 + }, + { + "epoch": 0.5528100923908039, + "grad_norm": 0.7968197915556894, + "learning_rate": 8.778236690410877e-06, + "loss": 0.8991, + "step": 9005 + }, + { + "epoch": 0.5528714816292704, + "grad_norm": 0.8499101003937427, + "learning_rate": 8.776263260695646e-06, + "loss": 0.8213, + "step": 9006 + }, + { + "epoch": 0.5529328708677369, + "grad_norm": 0.8948698762797446, + "learning_rate": 8.774289879361274e-06, + "loss": 0.8296, + "step": 9007 + }, + { + "epoch": 0.5529942601062033, + "grad_norm": 0.8013663817637668, + "learning_rate": 8.772316546485782e-06, + "loss": 0.7977, + "step": 9008 + }, + { + "epoch": 0.5530556493446699, + "grad_norm": 0.857963466367716, + "learning_rate": 8.77034326214718e-06, + "loss": 0.8012, + "step": 9009 + }, + { + "epoch": 0.5531170385831363, + "grad_norm": 0.7987716397833317, + "learning_rate": 8.768370026423484e-06, + "loss": 0.8246, + "step": 9010 + }, + { + "epoch": 0.5531784278216029, + "grad_norm": 0.9017440656660654, + "learning_rate": 8.76639683939271e-06, + "loss": 0.832, + "step": 9011 + }, + { + "epoch": 0.5532398170600694, + "grad_norm": 0.8561718429365947, + "learning_rate": 8.764423701132865e-06, + "loss": 0.831, + "step": 9012 + }, + { + "epoch": 0.5533012062985359, + "grad_norm": 0.816960781113737, + "learning_rate": 8.762450611721966e-06, + "loss": 0.8167, + "step": 9013 + }, + { + "epoch": 0.5533625955370024, + "grad_norm": 0.6953761224250632, + "learning_rate": 8.760477571238006e-06, + "loss": 0.7323, + "step": 9014 + }, + { + "epoch": 0.5534239847754688, + "grad_norm": 0.8579617327251585, + "learning_rate": 8.758504579759e-06, + "loss": 0.8415, + "step": 9015 + }, + { + "epoch": 0.5534853740139354, + "grad_norm": 0.6746007175270803, + "learning_rate": 8.756531637362946e-06, + "loss": 0.7172, + "step": 9016 + }, + { + "epoch": 0.5535467632524018, + "grad_norm": 0.8768504243906355, + "learning_rate": 8.75455874412785e-06, + "loss": 0.8188, + "step": 9017 + }, + { + "epoch": 0.5536081524908684, + "grad_norm": 0.8398985949925768, + "learning_rate": 8.752585900131707e-06, + "loss": 0.798, + "step": 9018 + }, + { + "epoch": 0.5536695417293348, + "grad_norm": 0.8432400256432948, + "learning_rate": 8.750613105452513e-06, + "loss": 0.8144, + "step": 9019 + }, + { + "epoch": 0.5537309309678013, + "grad_norm": 0.7757078607284852, + "learning_rate": 8.748640360168268e-06, + "loss": 0.8202, + "step": 9020 + }, + { + "epoch": 0.5537923202062679, + "grad_norm": 0.8086465279257173, + "learning_rate": 8.746667664356957e-06, + "loss": 0.8134, + "step": 9021 + }, + { + "epoch": 0.5538537094447343, + "grad_norm": 0.8459554431884352, + "learning_rate": 8.744695018096584e-06, + "loss": 0.8569, + "step": 9022 + }, + { + "epoch": 0.5539150986832009, + "grad_norm": 0.7889186182166147, + "learning_rate": 8.742722421465126e-06, + "loss": 0.8107, + "step": 9023 + }, + { + "epoch": 0.5539764879216673, + "grad_norm": 0.8654052045985551, + "learning_rate": 8.740749874540574e-06, + "loss": 0.796, + "step": 9024 + }, + { + "epoch": 0.5540378771601339, + "grad_norm": 0.8825812403462853, + "learning_rate": 8.738777377400917e-06, + "loss": 0.8954, + "step": 9025 + }, + { + "epoch": 0.5540992663986003, + "grad_norm": 0.9387371491340664, + "learning_rate": 8.736804930124133e-06, + "loss": 0.8561, + "step": 9026 + }, + { + "epoch": 0.5541606556370668, + "grad_norm": 0.9594497207394614, + "learning_rate": 8.734832532788214e-06, + "loss": 0.8538, + "step": 9027 + }, + { + "epoch": 0.5542220448755333, + "grad_norm": 0.8096528976239754, + "learning_rate": 8.732860185471123e-06, + "loss": 0.8167, + "step": 9028 + }, + { + "epoch": 0.5542834341139998, + "grad_norm": 0.766079477434021, + "learning_rate": 8.73088788825085e-06, + "loss": 0.8272, + "step": 9029 + }, + { + "epoch": 0.5543448233524663, + "grad_norm": 0.8188736035299414, + "learning_rate": 8.728915641205364e-06, + "loss": 0.8245, + "step": 9030 + }, + { + "epoch": 0.5544062125909328, + "grad_norm": 0.8255388788089529, + "learning_rate": 8.726943444412641e-06, + "loss": 0.8467, + "step": 9031 + }, + { + "epoch": 0.5544676018293994, + "grad_norm": 0.819338386903568, + "learning_rate": 8.724971297950657e-06, + "loss": 0.7991, + "step": 9032 + }, + { + "epoch": 0.5545289910678658, + "grad_norm": 0.8565865024135958, + "learning_rate": 8.722999201897372e-06, + "loss": 0.8044, + "step": 9033 + }, + { + "epoch": 0.5545903803063323, + "grad_norm": 0.8666062222483478, + "learning_rate": 8.72102715633076e-06, + "loss": 0.8203, + "step": 9034 + }, + { + "epoch": 0.5546517695447988, + "grad_norm": 0.8409616742626767, + "learning_rate": 8.719055161328783e-06, + "loss": 0.7912, + "step": 9035 + }, + { + "epoch": 0.5547131587832653, + "grad_norm": 0.7810523519737564, + "learning_rate": 8.717083216969409e-06, + "loss": 0.8214, + "step": 9036 + }, + { + "epoch": 0.5547745480217318, + "grad_norm": 0.7664012054776056, + "learning_rate": 8.715111323330598e-06, + "loss": 0.8496, + "step": 9037 + }, + { + "epoch": 0.5548359372601983, + "grad_norm": 0.7822163682181182, + "learning_rate": 8.713139480490306e-06, + "loss": 0.7573, + "step": 9038 + }, + { + "epoch": 0.5548973264986647, + "grad_norm": 0.7404884843449034, + "learning_rate": 8.711167688526495e-06, + "loss": 0.8452, + "step": 9039 + }, + { + "epoch": 0.5549587157371313, + "grad_norm": 0.8237346325187603, + "learning_rate": 8.709195947517117e-06, + "loss": 0.8575, + "step": 9040 + }, + { + "epoch": 0.5550201049755977, + "grad_norm": 0.7920198937556332, + "learning_rate": 8.707224257540126e-06, + "loss": 0.7713, + "step": 9041 + }, + { + "epoch": 0.5550814942140643, + "grad_norm": 0.764113097329438, + "learning_rate": 8.705252618673476e-06, + "loss": 0.8085, + "step": 9042 + }, + { + "epoch": 0.5551428834525308, + "grad_norm": 0.7858619376531314, + "learning_rate": 8.703281030995116e-06, + "loss": 0.8195, + "step": 9043 + }, + { + "epoch": 0.5552042726909973, + "grad_norm": 0.9152996007711817, + "learning_rate": 8.701309494582987e-06, + "loss": 0.879, + "step": 9044 + }, + { + "epoch": 0.5552656619294638, + "grad_norm": 0.8449309812896983, + "learning_rate": 8.699338009515045e-06, + "loss": 0.8093, + "step": 9045 + }, + { + "epoch": 0.5553270511679302, + "grad_norm": 0.8802180304202375, + "learning_rate": 8.697366575869223e-06, + "loss": 0.856, + "step": 9046 + }, + { + "epoch": 0.5553884404063968, + "grad_norm": 0.9128694136284555, + "learning_rate": 8.695395193723473e-06, + "loss": 0.8855, + "step": 9047 + }, + { + "epoch": 0.5554498296448632, + "grad_norm": 0.8831011658982536, + "learning_rate": 8.693423863155726e-06, + "loss": 0.8534, + "step": 9048 + }, + { + "epoch": 0.5555112188833298, + "grad_norm": 0.7768113554125542, + "learning_rate": 8.69145258424392e-06, + "loss": 0.8473, + "step": 9049 + }, + { + "epoch": 0.5555726081217962, + "grad_norm": 0.8887882525178666, + "learning_rate": 8.689481357065994e-06, + "loss": 0.8146, + "step": 9050 + }, + { + "epoch": 0.5556339973602628, + "grad_norm": 0.7307882828285784, + "learning_rate": 8.687510181699877e-06, + "loss": 0.813, + "step": 9051 + }, + { + "epoch": 0.5556953865987292, + "grad_norm": 0.7927657296044164, + "learning_rate": 8.685539058223508e-06, + "loss": 0.7841, + "step": 9052 + }, + { + "epoch": 0.5557567758371957, + "grad_norm": 0.8019603247563503, + "learning_rate": 8.683567986714803e-06, + "loss": 0.8019, + "step": 9053 + }, + { + "epoch": 0.5558181650756623, + "grad_norm": 0.8409430081034941, + "learning_rate": 8.6815969672517e-06, + "loss": 0.8185, + "step": 9054 + }, + { + "epoch": 0.5558795543141287, + "grad_norm": 0.8120627441896963, + "learning_rate": 8.679625999912119e-06, + "loss": 0.7988, + "step": 9055 + }, + { + "epoch": 0.5559409435525953, + "grad_norm": 0.7926287903533464, + "learning_rate": 8.677655084773983e-06, + "loss": 0.8077, + "step": 9056 + }, + { + "epoch": 0.5560023327910617, + "grad_norm": 0.771575619046475, + "learning_rate": 8.675684221915219e-06, + "loss": 0.8421, + "step": 9057 + }, + { + "epoch": 0.5560637220295283, + "grad_norm": 0.8598087628408696, + "learning_rate": 8.673713411413735e-06, + "loss": 0.8599, + "step": 9058 + }, + { + "epoch": 0.5561251112679947, + "grad_norm": 0.941236174239578, + "learning_rate": 8.671742653347456e-06, + "loss": 0.7939, + "step": 9059 + }, + { + "epoch": 0.5561865005064612, + "grad_norm": 0.8764082108905348, + "learning_rate": 8.669771947794291e-06, + "loss": 0.8314, + "step": 9060 + }, + { + "epoch": 0.5562478897449277, + "grad_norm": 0.849146083489923, + "learning_rate": 8.667801294832158e-06, + "loss": 0.8279, + "step": 9061 + }, + { + "epoch": 0.5563092789833942, + "grad_norm": 0.8388763128742138, + "learning_rate": 8.665830694538968e-06, + "loss": 0.8199, + "step": 9062 + }, + { + "epoch": 0.5563706682218607, + "grad_norm": 0.7698656606663931, + "learning_rate": 8.66386014699262e-06, + "loss": 0.7963, + "step": 9063 + }, + { + "epoch": 0.5564320574603272, + "grad_norm": 0.7451628147903171, + "learning_rate": 8.66188965227103e-06, + "loss": 0.8315, + "step": 9064 + }, + { + "epoch": 0.5564934466987937, + "grad_norm": 0.8727004977504873, + "learning_rate": 8.659919210452097e-06, + "loss": 0.8113, + "step": 9065 + }, + { + "epoch": 0.5565548359372602, + "grad_norm": 0.7582774608139287, + "learning_rate": 8.657948821613726e-06, + "loss": 0.8242, + "step": 9066 + }, + { + "epoch": 0.5566162251757267, + "grad_norm": 0.8351862119616915, + "learning_rate": 8.655978485833819e-06, + "loss": 0.8437, + "step": 9067 + }, + { + "epoch": 0.5566776144141932, + "grad_norm": 0.9012267049800179, + "learning_rate": 8.654008203190267e-06, + "loss": 0.799, + "step": 9068 + }, + { + "epoch": 0.5567390036526597, + "grad_norm": 0.810032887882938, + "learning_rate": 8.65203797376097e-06, + "loss": 0.7764, + "step": 9069 + }, + { + "epoch": 0.5568003928911262, + "grad_norm": 0.810647818075856, + "learning_rate": 8.650067797623822e-06, + "loss": 0.8148, + "step": 9070 + }, + { + "epoch": 0.5568617821295927, + "grad_norm": 0.8243597638182534, + "learning_rate": 8.648097674856712e-06, + "loss": 0.8245, + "step": 9071 + }, + { + "epoch": 0.5569231713680591, + "grad_norm": 0.7887110613723638, + "learning_rate": 8.646127605537536e-06, + "loss": 0.8291, + "step": 9072 + }, + { + "epoch": 0.5569845606065257, + "grad_norm": 0.8302945041811679, + "learning_rate": 8.644157589744174e-06, + "loss": 0.8246, + "step": 9073 + }, + { + "epoch": 0.5570459498449922, + "grad_norm": 0.7423993543327275, + "learning_rate": 8.64218762755451e-06, + "loss": 0.7834, + "step": 9074 + }, + { + "epoch": 0.5571073390834587, + "grad_norm": 0.8840655293307043, + "learning_rate": 8.640217719046437e-06, + "loss": 0.8508, + "step": 9075 + }, + { + "epoch": 0.5571687283219252, + "grad_norm": 0.8351604395932657, + "learning_rate": 8.638247864297827e-06, + "loss": 0.8316, + "step": 9076 + }, + { + "epoch": 0.5572301175603916, + "grad_norm": 0.8730692464640221, + "learning_rate": 8.636278063386566e-06, + "loss": 0.8033, + "step": 9077 + }, + { + "epoch": 0.5572915067988582, + "grad_norm": 0.9205563796912288, + "learning_rate": 8.634308316390523e-06, + "loss": 0.8842, + "step": 9078 + }, + { + "epoch": 0.5573528960373246, + "grad_norm": 0.7618127899300797, + "learning_rate": 8.632338623387576e-06, + "loss": 0.7845, + "step": 9079 + }, + { + "epoch": 0.5574142852757912, + "grad_norm": 0.8257775719403989, + "learning_rate": 8.6303689844556e-06, + "loss": 0.846, + "step": 9080 + }, + { + "epoch": 0.5574756745142576, + "grad_norm": 0.8117799777412424, + "learning_rate": 8.628399399672465e-06, + "loss": 0.8301, + "step": 9081 + }, + { + "epoch": 0.5575370637527242, + "grad_norm": 0.8273166738202843, + "learning_rate": 8.626429869116035e-06, + "loss": 0.7961, + "step": 9082 + }, + { + "epoch": 0.5575984529911906, + "grad_norm": 0.7570053108089265, + "learning_rate": 8.624460392864178e-06, + "loss": 0.8512, + "step": 9083 + }, + { + "epoch": 0.5576598422296571, + "grad_norm": 0.8209058255929792, + "learning_rate": 8.62249097099476e-06, + "loss": 0.8115, + "step": 9084 + }, + { + "epoch": 0.5577212314681237, + "grad_norm": 0.8550675184331313, + "learning_rate": 8.620521603585638e-06, + "loss": 0.8287, + "step": 9085 + }, + { + "epoch": 0.5577826207065901, + "grad_norm": 0.8672852669049058, + "learning_rate": 8.618552290714682e-06, + "loss": 0.8137, + "step": 9086 + }, + { + "epoch": 0.5578440099450567, + "grad_norm": 0.8188897954404564, + "learning_rate": 8.616583032459739e-06, + "loss": 0.8141, + "step": 9087 + }, + { + "epoch": 0.5579053991835231, + "grad_norm": 0.8601658034708815, + "learning_rate": 8.614613828898666e-06, + "loss": 0.9374, + "step": 9088 + }, + { + "epoch": 0.5579667884219897, + "grad_norm": 0.7853191142850129, + "learning_rate": 8.61264468010932e-06, + "loss": 0.7579, + "step": 9089 + }, + { + "epoch": 0.5580281776604561, + "grad_norm": 0.849139751852574, + "learning_rate": 8.610675586169546e-06, + "loss": 0.7995, + "step": 9090 + }, + { + "epoch": 0.5580895668989226, + "grad_norm": 0.8106909253754644, + "learning_rate": 8.608706547157205e-06, + "loss": 0.7971, + "step": 9091 + }, + { + "epoch": 0.5581509561373891, + "grad_norm": 0.7790430925524789, + "learning_rate": 8.606737563150127e-06, + "loss": 0.8316, + "step": 9092 + }, + { + "epoch": 0.5582123453758556, + "grad_norm": 0.9291432924729189, + "learning_rate": 8.60476863422617e-06, + "loss": 0.7919, + "step": 9093 + }, + { + "epoch": 0.5582737346143221, + "grad_norm": 0.9096618049209357, + "learning_rate": 8.602799760463167e-06, + "loss": 0.7809, + "step": 9094 + }, + { + "epoch": 0.5583351238527886, + "grad_norm": 0.8464553710686257, + "learning_rate": 8.600830941938963e-06, + "loss": 0.8411, + "step": 9095 + }, + { + "epoch": 0.5583965130912552, + "grad_norm": 0.8844618706923257, + "learning_rate": 8.5988621787314e-06, + "loss": 0.8097, + "step": 9096 + }, + { + "epoch": 0.5584579023297216, + "grad_norm": 0.7820144647349473, + "learning_rate": 8.596893470918304e-06, + "loss": 0.8115, + "step": 9097 + }, + { + "epoch": 0.5585192915681881, + "grad_norm": 0.8145025621597357, + "learning_rate": 8.594924818577514e-06, + "loss": 0.7787, + "step": 9098 + }, + { + "epoch": 0.5585806808066546, + "grad_norm": 0.806567903787521, + "learning_rate": 8.59295622178686e-06, + "loss": 0.8393, + "step": 9099 + }, + { + "epoch": 0.5586420700451211, + "grad_norm": 0.8323357613551348, + "learning_rate": 8.590987680624174e-06, + "loss": 0.807, + "step": 9100 + }, + { + "epoch": 0.5587034592835876, + "grad_norm": 0.9124329772116492, + "learning_rate": 8.589019195167283e-06, + "loss": 0.8344, + "step": 9101 + }, + { + "epoch": 0.5587648485220541, + "grad_norm": 0.8939668363344553, + "learning_rate": 8.587050765494004e-06, + "loss": 0.8364, + "step": 9102 + }, + { + "epoch": 0.5588262377605205, + "grad_norm": 0.7649115850567179, + "learning_rate": 8.58508239168217e-06, + "loss": 0.8088, + "step": 9103 + }, + { + "epoch": 0.5588876269989871, + "grad_norm": 0.8129891665806658, + "learning_rate": 8.583114073809595e-06, + "loss": 0.7992, + "step": 9104 + }, + { + "epoch": 0.5589490162374535, + "grad_norm": 0.8843609667317953, + "learning_rate": 8.581145811954097e-06, + "loss": 0.865, + "step": 9105 + }, + { + "epoch": 0.5590104054759201, + "grad_norm": 0.8497901199454359, + "learning_rate": 8.579177606193497e-06, + "loss": 0.8176, + "step": 9106 + }, + { + "epoch": 0.5590717947143866, + "grad_norm": 0.887477598505288, + "learning_rate": 8.577209456605603e-06, + "loss": 0.8345, + "step": 9107 + }, + { + "epoch": 0.559133183952853, + "grad_norm": 0.771202645187754, + "learning_rate": 8.575241363268229e-06, + "loss": 0.8167, + "step": 9108 + }, + { + "epoch": 0.5591945731913196, + "grad_norm": 0.8169591786977418, + "learning_rate": 8.573273326259184e-06, + "loss": 0.792, + "step": 9109 + }, + { + "epoch": 0.559255962429786, + "grad_norm": 0.796590392493047, + "learning_rate": 8.571305345656274e-06, + "loss": 0.8101, + "step": 9110 + }, + { + "epoch": 0.5593173516682526, + "grad_norm": 0.6505814924773682, + "learning_rate": 8.569337421537309e-06, + "loss": 0.7323, + "step": 9111 + }, + { + "epoch": 0.559378740906719, + "grad_norm": 0.7752980465975476, + "learning_rate": 8.567369553980085e-06, + "loss": 0.7744, + "step": 9112 + }, + { + "epoch": 0.5594401301451856, + "grad_norm": 0.8334396082347627, + "learning_rate": 8.565401743062403e-06, + "loss": 0.8491, + "step": 9113 + }, + { + "epoch": 0.559501519383652, + "grad_norm": 0.8362213310481453, + "learning_rate": 8.563433988862064e-06, + "loss": 0.8101, + "step": 9114 + }, + { + "epoch": 0.5595629086221185, + "grad_norm": 0.8504404970076138, + "learning_rate": 8.56146629145686e-06, + "loss": 0.8228, + "step": 9115 + }, + { + "epoch": 0.559624297860585, + "grad_norm": 0.8628197175048331, + "learning_rate": 8.559498650924597e-06, + "loss": 0.8238, + "step": 9116 + }, + { + "epoch": 0.5596856870990515, + "grad_norm": 0.7889935753322518, + "learning_rate": 8.557531067343048e-06, + "loss": 0.7747, + "step": 9117 + }, + { + "epoch": 0.5597470763375181, + "grad_norm": 0.6422475625181118, + "learning_rate": 8.555563540790013e-06, + "loss": 0.6912, + "step": 9118 + }, + { + "epoch": 0.5598084655759845, + "grad_norm": 0.8995765738704946, + "learning_rate": 8.553596071343276e-06, + "loss": 0.8407, + "step": 9119 + }, + { + "epoch": 0.5598698548144511, + "grad_norm": 0.8327746513366125, + "learning_rate": 8.551628659080622e-06, + "loss": 0.785, + "step": 9120 + }, + { + "epoch": 0.5599312440529175, + "grad_norm": 0.8252505376824085, + "learning_rate": 8.549661304079838e-06, + "loss": 0.8488, + "step": 9121 + }, + { + "epoch": 0.559992633291384, + "grad_norm": 0.9342871542550393, + "learning_rate": 8.547694006418693e-06, + "loss": 0.8539, + "step": 9122 + }, + { + "epoch": 0.5600540225298505, + "grad_norm": 0.8532543558054545, + "learning_rate": 8.545726766174975e-06, + "loss": 0.8026, + "step": 9123 + }, + { + "epoch": 0.560115411768317, + "grad_norm": 0.9066866194108758, + "learning_rate": 8.543759583426454e-06, + "loss": 0.8159, + "step": 9124 + }, + { + "epoch": 0.5601768010067835, + "grad_norm": 0.7802845728682143, + "learning_rate": 8.541792458250906e-06, + "loss": 0.8357, + "step": 9125 + }, + { + "epoch": 0.56023819024525, + "grad_norm": 0.7476481234786364, + "learning_rate": 8.539825390726105e-06, + "loss": 0.8348, + "step": 9126 + }, + { + "epoch": 0.5602995794837166, + "grad_norm": 0.8032836739705129, + "learning_rate": 8.537858380929809e-06, + "loss": 0.7826, + "step": 9127 + }, + { + "epoch": 0.560360968722183, + "grad_norm": 0.8541012780657031, + "learning_rate": 8.535891428939795e-06, + "loss": 0.8253, + "step": 9128 + }, + { + "epoch": 0.5604223579606495, + "grad_norm": 0.8345136408217008, + "learning_rate": 8.533924534833822e-06, + "loss": 0.8468, + "step": 9129 + }, + { + "epoch": 0.560483747199116, + "grad_norm": 0.7552495166953852, + "learning_rate": 8.531957698689655e-06, + "loss": 0.8039, + "step": 9130 + }, + { + "epoch": 0.5605451364375825, + "grad_norm": 0.7905084670549748, + "learning_rate": 8.529990920585052e-06, + "loss": 0.7581, + "step": 9131 + }, + { + "epoch": 0.560606525676049, + "grad_norm": 0.7746921357263402, + "learning_rate": 8.52802420059777e-06, + "loss": 0.8009, + "step": 9132 + }, + { + "epoch": 0.5606679149145155, + "grad_norm": 0.8892257000088042, + "learning_rate": 8.526057538805563e-06, + "loss": 0.8469, + "step": 9133 + }, + { + "epoch": 0.5607293041529819, + "grad_norm": 0.7773119258995383, + "learning_rate": 8.524090935286184e-06, + "loss": 0.7936, + "step": 9134 + }, + { + "epoch": 0.5607906933914485, + "grad_norm": 0.8806364642017837, + "learning_rate": 8.522124390117383e-06, + "loss": 0.8311, + "step": 9135 + }, + { + "epoch": 0.5608520826299149, + "grad_norm": 0.7969023066825612, + "learning_rate": 8.520157903376914e-06, + "loss": 0.805, + "step": 9136 + }, + { + "epoch": 0.5609134718683815, + "grad_norm": 0.8263239468145582, + "learning_rate": 8.518191475142515e-06, + "loss": 0.806, + "step": 9137 + }, + { + "epoch": 0.560974861106848, + "grad_norm": 0.8377218865329976, + "learning_rate": 8.516225105491931e-06, + "loss": 0.836, + "step": 9138 + }, + { + "epoch": 0.5610362503453145, + "grad_norm": 0.8068000924946391, + "learning_rate": 8.514258794502906e-06, + "loss": 0.8424, + "step": 9139 + }, + { + "epoch": 0.561097639583781, + "grad_norm": 0.7890775747566414, + "learning_rate": 8.512292542253176e-06, + "loss": 0.7868, + "step": 9140 + }, + { + "epoch": 0.5611590288222474, + "grad_norm": 0.8675289789379138, + "learning_rate": 8.510326348820482e-06, + "loss": 0.8179, + "step": 9141 + }, + { + "epoch": 0.561220418060714, + "grad_norm": 0.8110379076725569, + "learning_rate": 8.508360214282551e-06, + "loss": 0.852, + "step": 9142 + }, + { + "epoch": 0.5612818072991804, + "grad_norm": 0.7522779581509265, + "learning_rate": 8.50639413871712e-06, + "loss": 0.7636, + "step": 9143 + }, + { + "epoch": 0.561343196537647, + "grad_norm": 0.8123989506464203, + "learning_rate": 8.504428122201915e-06, + "loss": 0.8192, + "step": 9144 + }, + { + "epoch": 0.5614045857761134, + "grad_norm": 0.803624863856145, + "learning_rate": 8.502462164814668e-06, + "loss": 0.8096, + "step": 9145 + }, + { + "epoch": 0.56146597501458, + "grad_norm": 0.87666663452451, + "learning_rate": 8.500496266633102e-06, + "loss": 0.8225, + "step": 9146 + }, + { + "epoch": 0.5615273642530464, + "grad_norm": 0.7985707539036679, + "learning_rate": 8.498530427734935e-06, + "loss": 0.7721, + "step": 9147 + }, + { + "epoch": 0.5615887534915129, + "grad_norm": 0.7825276912572389, + "learning_rate": 8.496564648197893e-06, + "loss": 0.7746, + "step": 9148 + }, + { + "epoch": 0.5616501427299795, + "grad_norm": 0.8384231644248724, + "learning_rate": 8.494598928099688e-06, + "loss": 0.8096, + "step": 9149 + }, + { + "epoch": 0.5617115319684459, + "grad_norm": 0.7840465201962573, + "learning_rate": 8.492633267518044e-06, + "loss": 0.7938, + "step": 9150 + }, + { + "epoch": 0.5617729212069125, + "grad_norm": 0.8666161377019972, + "learning_rate": 8.490667666530666e-06, + "loss": 0.7945, + "step": 9151 + }, + { + "epoch": 0.5618343104453789, + "grad_norm": 0.8901666101707345, + "learning_rate": 8.488702125215267e-06, + "loss": 0.8018, + "step": 9152 + }, + { + "epoch": 0.5618956996838455, + "grad_norm": 0.8628786721415481, + "learning_rate": 8.486736643649557e-06, + "loss": 0.8093, + "step": 9153 + }, + { + "epoch": 0.5619570889223119, + "grad_norm": 0.9111711767462214, + "learning_rate": 8.484771221911239e-06, + "loss": 0.8507, + "step": 9154 + }, + { + "epoch": 0.5620184781607784, + "grad_norm": 0.7895360133829251, + "learning_rate": 8.482805860078025e-06, + "loss": 0.7899, + "step": 9155 + }, + { + "epoch": 0.5620798673992449, + "grad_norm": 0.9002837336826957, + "learning_rate": 8.480840558227604e-06, + "loss": 0.8223, + "step": 9156 + }, + { + "epoch": 0.5621412566377114, + "grad_norm": 0.8372334464374249, + "learning_rate": 8.478875316437681e-06, + "loss": 0.8181, + "step": 9157 + }, + { + "epoch": 0.5622026458761779, + "grad_norm": 0.8602310163340823, + "learning_rate": 8.476910134785952e-06, + "loss": 0.8477, + "step": 9158 + }, + { + "epoch": 0.5622640351146444, + "grad_norm": 0.9088704152850576, + "learning_rate": 8.474945013350114e-06, + "loss": 0.8322, + "step": 9159 + }, + { + "epoch": 0.562325424353111, + "grad_norm": 0.8694490259477328, + "learning_rate": 8.472979952207857e-06, + "loss": 0.7932, + "step": 9160 + }, + { + "epoch": 0.5623868135915774, + "grad_norm": 0.8550643044390416, + "learning_rate": 8.471014951436865e-06, + "loss": 0.7808, + "step": 9161 + }, + { + "epoch": 0.5624482028300439, + "grad_norm": 0.857308095392372, + "learning_rate": 8.469050011114832e-06, + "loss": 0.7692, + "step": 9162 + }, + { + "epoch": 0.5625095920685104, + "grad_norm": 0.8396467151988483, + "learning_rate": 8.46708513131944e-06, + "loss": 0.8261, + "step": 9163 + }, + { + "epoch": 0.5625709813069769, + "grad_norm": 0.9052877636296889, + "learning_rate": 8.465120312128371e-06, + "loss": 0.8549, + "step": 9164 + }, + { + "epoch": 0.5626323705454433, + "grad_norm": 0.7916207830031098, + "learning_rate": 8.463155553619309e-06, + "loss": 0.8356, + "step": 9165 + }, + { + "epoch": 0.5626937597839099, + "grad_norm": 0.8923464210447208, + "learning_rate": 8.461190855869922e-06, + "loss": 0.8076, + "step": 9166 + }, + { + "epoch": 0.5627551490223763, + "grad_norm": 0.9100183885731788, + "learning_rate": 8.459226218957893e-06, + "loss": 0.8519, + "step": 9167 + }, + { + "epoch": 0.5628165382608429, + "grad_norm": 0.8106214316116983, + "learning_rate": 8.45726164296089e-06, + "loss": 0.7991, + "step": 9168 + }, + { + "epoch": 0.5628779274993093, + "grad_norm": 0.8999638363158612, + "learning_rate": 8.455297127956589e-06, + "loss": 0.8483, + "step": 9169 + }, + { + "epoch": 0.5629393167377759, + "grad_norm": 0.8763160592103578, + "learning_rate": 8.453332674022654e-06, + "loss": 0.8316, + "step": 9170 + }, + { + "epoch": 0.5630007059762424, + "grad_norm": 0.8536366630475083, + "learning_rate": 8.45136828123675e-06, + "loss": 0.8709, + "step": 9171 + }, + { + "epoch": 0.5630620952147088, + "grad_norm": 0.8292424542631974, + "learning_rate": 8.449403949676538e-06, + "loss": 0.8362, + "step": 9172 + }, + { + "epoch": 0.5631234844531754, + "grad_norm": 0.8550647580994367, + "learning_rate": 8.447439679419684e-06, + "loss": 0.7708, + "step": 9173 + }, + { + "epoch": 0.5631848736916418, + "grad_norm": 0.8714284050211171, + "learning_rate": 8.44547547054384e-06, + "loss": 0.8195, + "step": 9174 + }, + { + "epoch": 0.5632462629301084, + "grad_norm": 0.7517357121777444, + "learning_rate": 8.443511323126669e-06, + "loss": 0.7539, + "step": 9175 + }, + { + "epoch": 0.5633076521685748, + "grad_norm": 0.7549650161870859, + "learning_rate": 8.441547237245818e-06, + "loss": 0.8154, + "step": 9176 + }, + { + "epoch": 0.5633690414070414, + "grad_norm": 0.8050313470192324, + "learning_rate": 8.43958321297894e-06, + "loss": 0.8266, + "step": 9177 + }, + { + "epoch": 0.5634304306455078, + "grad_norm": 0.7195929660101947, + "learning_rate": 8.437619250403682e-06, + "loss": 0.7798, + "step": 9178 + }, + { + "epoch": 0.5634918198839743, + "grad_norm": 0.9485970897950404, + "learning_rate": 8.43565534959769e-06, + "loss": 0.9676, + "step": 9179 + }, + { + "epoch": 0.5635532091224409, + "grad_norm": 0.7894445374446903, + "learning_rate": 8.433691510638614e-06, + "loss": 0.7762, + "step": 9180 + }, + { + "epoch": 0.5636145983609073, + "grad_norm": 0.8160384422171603, + "learning_rate": 8.431727733604087e-06, + "loss": 0.8243, + "step": 9181 + }, + { + "epoch": 0.5636759875993739, + "grad_norm": 0.8611072646432131, + "learning_rate": 8.429764018571751e-06, + "loss": 0.8342, + "step": 9182 + }, + { + "epoch": 0.5637373768378403, + "grad_norm": 0.8454007672314238, + "learning_rate": 8.427800365619238e-06, + "loss": 0.8212, + "step": 9183 + }, + { + "epoch": 0.5637987660763069, + "grad_norm": 0.8156719736756863, + "learning_rate": 8.42583677482419e-06, + "loss": 0.8842, + "step": 9184 + }, + { + "epoch": 0.5638601553147733, + "grad_norm": 0.846580252952177, + "learning_rate": 8.423873246264233e-06, + "loss": 0.7982, + "step": 9185 + }, + { + "epoch": 0.5639215445532398, + "grad_norm": 0.6482421811557498, + "learning_rate": 8.421909780016994e-06, + "loss": 0.7847, + "step": 9186 + }, + { + "epoch": 0.5639829337917063, + "grad_norm": 0.8309935080868083, + "learning_rate": 8.419946376160101e-06, + "loss": 0.7901, + "step": 9187 + }, + { + "epoch": 0.5640443230301728, + "grad_norm": 0.8072777631632134, + "learning_rate": 8.41798303477118e-06, + "loss": 0.8597, + "step": 9188 + }, + { + "epoch": 0.5641057122686393, + "grad_norm": 0.7501129106630731, + "learning_rate": 8.416019755927851e-06, + "loss": 0.8201, + "step": 9189 + }, + { + "epoch": 0.5641671015071058, + "grad_norm": 0.7963202566588954, + "learning_rate": 8.414056539707735e-06, + "loss": 0.7952, + "step": 9190 + }, + { + "epoch": 0.5642284907455724, + "grad_norm": 0.904670797852059, + "learning_rate": 8.412093386188443e-06, + "loss": 0.8289, + "step": 9191 + }, + { + "epoch": 0.5642898799840388, + "grad_norm": 0.8391366133465509, + "learning_rate": 8.410130295447592e-06, + "loss": 0.8131, + "step": 9192 + }, + { + "epoch": 0.5643512692225053, + "grad_norm": 0.8400551942748938, + "learning_rate": 8.408167267562792e-06, + "loss": 0.7992, + "step": 9193 + }, + { + "epoch": 0.5644126584609718, + "grad_norm": 0.888416712741314, + "learning_rate": 8.406204302611658e-06, + "loss": 0.8141, + "step": 9194 + }, + { + "epoch": 0.5644740476994383, + "grad_norm": 0.8298635445088135, + "learning_rate": 8.404241400671792e-06, + "loss": 0.8108, + "step": 9195 + }, + { + "epoch": 0.5645354369379048, + "grad_norm": 0.8196775291227729, + "learning_rate": 8.402278561820797e-06, + "loss": 0.8016, + "step": 9196 + }, + { + "epoch": 0.5645968261763713, + "grad_norm": 0.9308149659955838, + "learning_rate": 8.400315786136273e-06, + "loss": 0.8599, + "step": 9197 + }, + { + "epoch": 0.5646582154148377, + "grad_norm": 0.9260487013112546, + "learning_rate": 8.398353073695826e-06, + "loss": 0.8884, + "step": 9198 + }, + { + "epoch": 0.5647196046533043, + "grad_norm": 0.8599830505814404, + "learning_rate": 8.396390424577043e-06, + "loss": 0.8199, + "step": 9199 + }, + { + "epoch": 0.5647809938917707, + "grad_norm": 0.8965129250765156, + "learning_rate": 8.394427838857529e-06, + "loss": 0.8296, + "step": 9200 + }, + { + "epoch": 0.5648423831302373, + "grad_norm": 0.9207654964255353, + "learning_rate": 8.392465316614867e-06, + "loss": 0.815, + "step": 9201 + }, + { + "epoch": 0.5649037723687038, + "grad_norm": 0.8597041147040646, + "learning_rate": 8.390502857926647e-06, + "loss": 0.8499, + "step": 9202 + }, + { + "epoch": 0.5649651616071703, + "grad_norm": 0.7477905861515106, + "learning_rate": 8.38854046287046e-06, + "loss": 0.7926, + "step": 9203 + }, + { + "epoch": 0.5650265508456368, + "grad_norm": 0.7198050459805626, + "learning_rate": 8.386578131523883e-06, + "loss": 0.7646, + "step": 9204 + }, + { + "epoch": 0.5650879400841032, + "grad_norm": 0.8610447025323432, + "learning_rate": 8.384615863964508e-06, + "loss": 0.8654, + "step": 9205 + }, + { + "epoch": 0.5651493293225698, + "grad_norm": 0.8250941581638532, + "learning_rate": 8.382653660269906e-06, + "loss": 0.8023, + "step": 9206 + }, + { + "epoch": 0.5652107185610362, + "grad_norm": 0.8392042791663976, + "learning_rate": 8.380691520517651e-06, + "loss": 0.8359, + "step": 9207 + }, + { + "epoch": 0.5652721077995028, + "grad_norm": 0.7467498540289691, + "learning_rate": 8.378729444785323e-06, + "loss": 0.8014, + "step": 9208 + }, + { + "epoch": 0.5653334970379692, + "grad_norm": 0.8394886621103325, + "learning_rate": 8.376767433150491e-06, + "loss": 0.7819, + "step": 9209 + }, + { + "epoch": 0.5653948862764357, + "grad_norm": 0.9075722343454226, + "learning_rate": 8.374805485690728e-06, + "loss": 0.8559, + "step": 9210 + }, + { + "epoch": 0.5654562755149022, + "grad_norm": 0.7625032027422766, + "learning_rate": 8.372843602483592e-06, + "loss": 0.8012, + "step": 9211 + }, + { + "epoch": 0.5655176647533687, + "grad_norm": 0.8843368995602597, + "learning_rate": 8.370881783606652e-06, + "loss": 0.8092, + "step": 9212 + }, + { + "epoch": 0.5655790539918353, + "grad_norm": 0.8353593567519665, + "learning_rate": 8.368920029137466e-06, + "loss": 0.797, + "step": 9213 + }, + { + "epoch": 0.5656404432303017, + "grad_norm": 0.9394827421759913, + "learning_rate": 8.3669583391536e-06, + "loss": 0.8736, + "step": 9214 + }, + { + "epoch": 0.5657018324687683, + "grad_norm": 0.8212307377011901, + "learning_rate": 8.364996713732602e-06, + "loss": 0.8454, + "step": 9215 + }, + { + "epoch": 0.5657632217072347, + "grad_norm": 0.7869523781616024, + "learning_rate": 8.363035152952026e-06, + "loss": 0.8065, + "step": 9216 + }, + { + "epoch": 0.5658246109457012, + "grad_norm": 0.8695565729389365, + "learning_rate": 8.361073656889427e-06, + "loss": 0.854, + "step": 9217 + }, + { + "epoch": 0.5658860001841677, + "grad_norm": 0.8015944630644812, + "learning_rate": 8.359112225622352e-06, + "loss": 0.8247, + "step": 9218 + }, + { + "epoch": 0.5659473894226342, + "grad_norm": 0.7548766012633477, + "learning_rate": 8.357150859228352e-06, + "loss": 0.8244, + "step": 9219 + }, + { + "epoch": 0.5660087786611007, + "grad_norm": 0.8445745206851928, + "learning_rate": 8.35518955778496e-06, + "loss": 0.8369, + "step": 9220 + }, + { + "epoch": 0.5660701678995672, + "grad_norm": 0.7810475130114659, + "learning_rate": 8.353228321369723e-06, + "loss": 0.846, + "step": 9221 + }, + { + "epoch": 0.5661315571380336, + "grad_norm": 0.7900924005387874, + "learning_rate": 8.351267150060176e-06, + "loss": 0.8268, + "step": 9222 + }, + { + "epoch": 0.5661929463765002, + "grad_norm": 0.8772189427437509, + "learning_rate": 8.349306043933859e-06, + "loss": 0.8801, + "step": 9223 + }, + { + "epoch": 0.5662543356149667, + "grad_norm": 0.8296496918437153, + "learning_rate": 8.347345003068303e-06, + "loss": 0.8172, + "step": 9224 + }, + { + "epoch": 0.5663157248534332, + "grad_norm": 0.7528095387171184, + "learning_rate": 8.345384027541035e-06, + "loss": 0.7873, + "step": 9225 + }, + { + "epoch": 0.5663771140918997, + "grad_norm": 0.8427126943690677, + "learning_rate": 8.343423117429588e-06, + "loss": 0.8355, + "step": 9226 + }, + { + "epoch": 0.5664385033303662, + "grad_norm": 0.7488599231766049, + "learning_rate": 8.341462272811485e-06, + "loss": 0.8154, + "step": 9227 + }, + { + "epoch": 0.5664998925688327, + "grad_norm": 0.7882044555225255, + "learning_rate": 8.339501493764248e-06, + "loss": 0.8353, + "step": 9228 + }, + { + "epoch": 0.5665612818072991, + "grad_norm": 0.7992623490822822, + "learning_rate": 8.337540780365402e-06, + "loss": 0.8364, + "step": 9229 + }, + { + "epoch": 0.5666226710457657, + "grad_norm": 0.7888268461461313, + "learning_rate": 8.335580132692455e-06, + "loss": 0.8162, + "step": 9230 + }, + { + "epoch": 0.5666840602842321, + "grad_norm": 0.8141114087595053, + "learning_rate": 8.33361955082293e-06, + "loss": 0.8128, + "step": 9231 + }, + { + "epoch": 0.5667454495226987, + "grad_norm": 0.7767058940547102, + "learning_rate": 8.331659034834335e-06, + "loss": 0.8098, + "step": 9232 + }, + { + "epoch": 0.5668068387611652, + "grad_norm": 0.8142726687076095, + "learning_rate": 8.329698584804182e-06, + "loss": 0.8371, + "step": 9233 + }, + { + "epoch": 0.5668682279996317, + "grad_norm": 0.8540915778906962, + "learning_rate": 8.327738200809979e-06, + "loss": 0.8309, + "step": 9234 + }, + { + "epoch": 0.5669296172380982, + "grad_norm": 0.8392416112697755, + "learning_rate": 8.325777882929229e-06, + "loss": 0.7611, + "step": 9235 + }, + { + "epoch": 0.5669910064765646, + "grad_norm": 0.8916416065280773, + "learning_rate": 8.32381763123943e-06, + "loss": 0.865, + "step": 9236 + }, + { + "epoch": 0.5670523957150312, + "grad_norm": 0.8858568269220152, + "learning_rate": 8.321857445818087e-06, + "loss": 0.8101, + "step": 9237 + }, + { + "epoch": 0.5671137849534976, + "grad_norm": 0.8134364770770401, + "learning_rate": 8.319897326742693e-06, + "loss": 0.8168, + "step": 9238 + }, + { + "epoch": 0.5671751741919642, + "grad_norm": 0.9021408700007526, + "learning_rate": 8.317937274090748e-06, + "loss": 0.8362, + "step": 9239 + }, + { + "epoch": 0.5672365634304306, + "grad_norm": 0.9545520478919682, + "learning_rate": 8.315977287939736e-06, + "loss": 0.8213, + "step": 9240 + }, + { + "epoch": 0.5672979526688972, + "grad_norm": 0.8182140386025716, + "learning_rate": 8.314017368367146e-06, + "loss": 0.8166, + "step": 9241 + }, + { + "epoch": 0.5673593419073636, + "grad_norm": 0.7792456358108805, + "learning_rate": 8.31205751545047e-06, + "loss": 0.7715, + "step": 9242 + }, + { + "epoch": 0.5674207311458301, + "grad_norm": 0.8152571219844948, + "learning_rate": 8.310097729267186e-06, + "loss": 0.7955, + "step": 9243 + }, + { + "epoch": 0.5674821203842967, + "grad_norm": 0.8550647466178153, + "learning_rate": 8.308138009894781e-06, + "loss": 0.8277, + "step": 9244 + }, + { + "epoch": 0.5675435096227631, + "grad_norm": 0.7703040001972049, + "learning_rate": 8.306178357410726e-06, + "loss": 0.8424, + "step": 9245 + }, + { + "epoch": 0.5676048988612297, + "grad_norm": 0.8372293251626541, + "learning_rate": 8.304218771892499e-06, + "loss": 0.8921, + "step": 9246 + }, + { + "epoch": 0.5676662880996961, + "grad_norm": 0.8990060133811443, + "learning_rate": 8.302259253417575e-06, + "loss": 0.7921, + "step": 9247 + }, + { + "epoch": 0.5677276773381627, + "grad_norm": 0.7948691397789652, + "learning_rate": 8.300299802063422e-06, + "loss": 0.8334, + "step": 9248 + }, + { + "epoch": 0.5677890665766291, + "grad_norm": 0.7518106089664354, + "learning_rate": 8.298340417907512e-06, + "loss": 0.7873, + "step": 9249 + }, + { + "epoch": 0.5678504558150956, + "grad_norm": 0.8942497759084236, + "learning_rate": 8.296381101027302e-06, + "loss": 0.8038, + "step": 9250 + }, + { + "epoch": 0.5679118450535621, + "grad_norm": 0.8239306337742607, + "learning_rate": 8.29442185150026e-06, + "loss": 0.8653, + "step": 9251 + }, + { + "epoch": 0.5679732342920286, + "grad_norm": 0.860321367768816, + "learning_rate": 8.292462669403843e-06, + "loss": 0.7703, + "step": 9252 + }, + { + "epoch": 0.568034623530495, + "grad_norm": 0.948159134272575, + "learning_rate": 8.290503554815513e-06, + "loss": 0.8611, + "step": 9253 + }, + { + "epoch": 0.5680960127689616, + "grad_norm": 0.8230085823613271, + "learning_rate": 8.288544507812719e-06, + "loss": 0.8388, + "step": 9254 + }, + { + "epoch": 0.5681574020074281, + "grad_norm": 0.7762761424551554, + "learning_rate": 8.286585528472912e-06, + "loss": 0.8084, + "step": 9255 + }, + { + "epoch": 0.5682187912458946, + "grad_norm": 0.8264764786277198, + "learning_rate": 8.284626616873544e-06, + "loss": 0.8137, + "step": 9256 + }, + { + "epoch": 0.5682801804843611, + "grad_norm": 0.8168393890140786, + "learning_rate": 8.282667773092059e-06, + "loss": 0.8254, + "step": 9257 + }, + { + "epoch": 0.5683415697228276, + "grad_norm": 0.8242064928389031, + "learning_rate": 8.280708997205904e-06, + "loss": 0.8218, + "step": 9258 + }, + { + "epoch": 0.5684029589612941, + "grad_norm": 0.8213540744537507, + "learning_rate": 8.27875028929252e-06, + "loss": 0.7809, + "step": 9259 + }, + { + "epoch": 0.5684643481997605, + "grad_norm": 0.8634746360013092, + "learning_rate": 8.276791649429341e-06, + "loss": 0.8433, + "step": 9260 + }, + { + "epoch": 0.5685257374382271, + "grad_norm": 0.85975446486151, + "learning_rate": 8.274833077693802e-06, + "loss": 0.8143, + "step": 9261 + }, + { + "epoch": 0.5685871266766935, + "grad_norm": 0.81935218531456, + "learning_rate": 8.27287457416334e-06, + "loss": 0.7902, + "step": 9262 + }, + { + "epoch": 0.5686485159151601, + "grad_norm": 0.7145265976103232, + "learning_rate": 8.270916138915381e-06, + "loss": 0.8052, + "step": 9263 + }, + { + "epoch": 0.5687099051536265, + "grad_norm": 0.9176753905280929, + "learning_rate": 8.26895777202736e-06, + "loss": 0.8477, + "step": 9264 + }, + { + "epoch": 0.5687712943920931, + "grad_norm": 0.8521597715588668, + "learning_rate": 8.266999473576696e-06, + "loss": 0.7934, + "step": 9265 + }, + { + "epoch": 0.5688326836305596, + "grad_norm": 0.8735144815579383, + "learning_rate": 8.265041243640806e-06, + "loss": 0.8412, + "step": 9266 + }, + { + "epoch": 0.568894072869026, + "grad_norm": 0.8348540965713078, + "learning_rate": 8.263083082297119e-06, + "loss": 0.8034, + "step": 9267 + }, + { + "epoch": 0.5689554621074926, + "grad_norm": 0.8662816927294097, + "learning_rate": 8.261124989623045e-06, + "loss": 0.8376, + "step": 9268 + }, + { + "epoch": 0.569016851345959, + "grad_norm": 0.8657442826995568, + "learning_rate": 8.259166965696004e-06, + "loss": 0.856, + "step": 9269 + }, + { + "epoch": 0.5690782405844256, + "grad_norm": 0.8267004409730132, + "learning_rate": 8.257209010593401e-06, + "loss": 0.7829, + "step": 9270 + }, + { + "epoch": 0.569139629822892, + "grad_norm": 0.8303940176036694, + "learning_rate": 8.255251124392648e-06, + "loss": 0.8155, + "step": 9271 + }, + { + "epoch": 0.5692010190613586, + "grad_norm": 0.8647075323574718, + "learning_rate": 8.253293307171149e-06, + "loss": 0.7561, + "step": 9272 + }, + { + "epoch": 0.569262408299825, + "grad_norm": 0.764107706392159, + "learning_rate": 8.251335559006304e-06, + "loss": 0.8454, + "step": 9273 + }, + { + "epoch": 0.5693237975382915, + "grad_norm": 0.8733612320677611, + "learning_rate": 8.249377879975527e-06, + "loss": 0.8311, + "step": 9274 + }, + { + "epoch": 0.569385186776758, + "grad_norm": 0.7280528404444765, + "learning_rate": 8.247420270156196e-06, + "loss": 0.7777, + "step": 9275 + }, + { + "epoch": 0.5694465760152245, + "grad_norm": 0.7864853704417094, + "learning_rate": 8.24546272962572e-06, + "loss": 0.8225, + "step": 9276 + }, + { + "epoch": 0.5695079652536911, + "grad_norm": 0.8049457911692138, + "learning_rate": 8.24350525846148e-06, + "loss": 0.8746, + "step": 9277 + }, + { + "epoch": 0.5695693544921575, + "grad_norm": 0.8864669237194163, + "learning_rate": 8.241547856740879e-06, + "loss": 0.772, + "step": 9278 + }, + { + "epoch": 0.5696307437306241, + "grad_norm": 0.8952924293982112, + "learning_rate": 8.239590524541293e-06, + "loss": 0.8631, + "step": 9279 + }, + { + "epoch": 0.5696921329690905, + "grad_norm": 0.8293714315762777, + "learning_rate": 8.237633261940107e-06, + "loss": 0.8601, + "step": 9280 + }, + { + "epoch": 0.569753522207557, + "grad_norm": 0.7240559732755182, + "learning_rate": 8.235676069014707e-06, + "loss": 0.7801, + "step": 9281 + }, + { + "epoch": 0.5698149114460235, + "grad_norm": 0.885850955276004, + "learning_rate": 8.233718945842464e-06, + "loss": 0.8479, + "step": 9282 + }, + { + "epoch": 0.56987630068449, + "grad_norm": 0.8829901285323414, + "learning_rate": 8.231761892500764e-06, + "loss": 0.8322, + "step": 9283 + }, + { + "epoch": 0.5699376899229565, + "grad_norm": 0.8053013684342225, + "learning_rate": 8.22980490906697e-06, + "loss": 0.8233, + "step": 9284 + }, + { + "epoch": 0.569999079161423, + "grad_norm": 0.8274973209181156, + "learning_rate": 8.227847995618453e-06, + "loss": 0.8327, + "step": 9285 + }, + { + "epoch": 0.5700604683998896, + "grad_norm": 0.8228273011143776, + "learning_rate": 8.225891152232587e-06, + "loss": 0.8403, + "step": 9286 + }, + { + "epoch": 0.570121857638356, + "grad_norm": 0.947230714073049, + "learning_rate": 8.223934378986733e-06, + "loss": 0.8179, + "step": 9287 + }, + { + "epoch": 0.5701832468768225, + "grad_norm": 0.7107638511740911, + "learning_rate": 8.221977675958252e-06, + "loss": 0.7764, + "step": 9288 + }, + { + "epoch": 0.570244636115289, + "grad_norm": 0.8482555576203655, + "learning_rate": 8.2200210432245e-06, + "loss": 0.81, + "step": 9289 + }, + { + "epoch": 0.5703060253537555, + "grad_norm": 0.7972712046616197, + "learning_rate": 8.218064480862837e-06, + "loss": 0.829, + "step": 9290 + }, + { + "epoch": 0.570367414592222, + "grad_norm": 0.8296086914691441, + "learning_rate": 8.216107988950614e-06, + "loss": 0.8215, + "step": 9291 + }, + { + "epoch": 0.5704288038306885, + "grad_norm": 0.9048840635182775, + "learning_rate": 8.214151567565185e-06, + "loss": 0.8158, + "step": 9292 + }, + { + "epoch": 0.5704901930691549, + "grad_norm": 0.8014731015005417, + "learning_rate": 8.212195216783899e-06, + "loss": 0.8119, + "step": 9293 + }, + { + "epoch": 0.5705515823076215, + "grad_norm": 0.8289252366779953, + "learning_rate": 8.210238936684094e-06, + "loss": 0.829, + "step": 9294 + }, + { + "epoch": 0.5706129715460879, + "grad_norm": 0.8331872687367782, + "learning_rate": 8.208282727343116e-06, + "loss": 0.8042, + "step": 9295 + }, + { + "epoch": 0.5706743607845545, + "grad_norm": 0.8972926461743658, + "learning_rate": 8.206326588838305e-06, + "loss": 0.8277, + "step": 9296 + }, + { + "epoch": 0.570735750023021, + "grad_norm": 0.8691630932890311, + "learning_rate": 8.204370521246998e-06, + "loss": 0.7898, + "step": 9297 + }, + { + "epoch": 0.5707971392614875, + "grad_norm": 0.7556625901877068, + "learning_rate": 8.20241452464653e-06, + "loss": 0.8123, + "step": 9298 + }, + { + "epoch": 0.570858528499954, + "grad_norm": 0.8874321806235896, + "learning_rate": 8.200458599114227e-06, + "loss": 0.7661, + "step": 9299 + }, + { + "epoch": 0.5709199177384204, + "grad_norm": 0.836720735774986, + "learning_rate": 8.19850274472742e-06, + "loss": 0.8234, + "step": 9300 + }, + { + "epoch": 0.570981306976887, + "grad_norm": 0.8846780154499787, + "learning_rate": 8.196546961563436e-06, + "loss": 0.8395, + "step": 9301 + }, + { + "epoch": 0.5710426962153534, + "grad_norm": 0.8578851804965075, + "learning_rate": 8.194591249699595e-06, + "loss": 0.799, + "step": 9302 + }, + { + "epoch": 0.57110408545382, + "grad_norm": 0.8121978147012975, + "learning_rate": 8.19263560921322e-06, + "loss": 0.8718, + "step": 9303 + }, + { + "epoch": 0.5711654746922864, + "grad_norm": 0.8698622672914333, + "learning_rate": 8.190680040181625e-06, + "loss": 0.8219, + "step": 9304 + }, + { + "epoch": 0.571226863930753, + "grad_norm": 0.9579578249591327, + "learning_rate": 8.188724542682123e-06, + "loss": 0.8331, + "step": 9305 + }, + { + "epoch": 0.5712882531692194, + "grad_norm": 0.8647802598198615, + "learning_rate": 8.18676911679203e-06, + "loss": 0.8257, + "step": 9306 + }, + { + "epoch": 0.5713496424076859, + "grad_norm": 0.7642131455890439, + "learning_rate": 8.184813762588649e-06, + "loss": 0.8192, + "step": 9307 + }, + { + "epoch": 0.5714110316461525, + "grad_norm": 0.9008057167508379, + "learning_rate": 8.18285848014929e-06, + "loss": 0.8315, + "step": 9308 + }, + { + "epoch": 0.5714724208846189, + "grad_norm": 0.8449559805448233, + "learning_rate": 8.180903269551254e-06, + "loss": 0.7964, + "step": 9309 + }, + { + "epoch": 0.5715338101230855, + "grad_norm": 0.7676930842101205, + "learning_rate": 8.17894813087184e-06, + "loss": 0.8366, + "step": 9310 + }, + { + "epoch": 0.5715951993615519, + "grad_norm": 0.748515846344151, + "learning_rate": 8.176993064188347e-06, + "loss": 0.7921, + "step": 9311 + }, + { + "epoch": 0.5716565886000184, + "grad_norm": 0.9103350619130652, + "learning_rate": 8.175038069578066e-06, + "loss": 0.8361, + "step": 9312 + }, + { + "epoch": 0.5717179778384849, + "grad_norm": 0.7995386320998639, + "learning_rate": 8.173083147118296e-06, + "loss": 0.8116, + "step": 9313 + }, + { + "epoch": 0.5717793670769514, + "grad_norm": 0.7845656186727086, + "learning_rate": 8.171128296886316e-06, + "loss": 0.818, + "step": 9314 + }, + { + "epoch": 0.5718407563154179, + "grad_norm": 0.5938164262381499, + "learning_rate": 8.169173518959417e-06, + "loss": 0.6841, + "step": 9315 + }, + { + "epoch": 0.5719021455538844, + "grad_norm": 0.8730993084658744, + "learning_rate": 8.167218813414878e-06, + "loss": 0.8551, + "step": 9316 + }, + { + "epoch": 0.5719635347923508, + "grad_norm": 0.8208783769174667, + "learning_rate": 8.165264180329985e-06, + "loss": 0.817, + "step": 9317 + }, + { + "epoch": 0.5720249240308174, + "grad_norm": 0.801186247492311, + "learning_rate": 8.163309619782014e-06, + "loss": 0.8242, + "step": 9318 + }, + { + "epoch": 0.5720863132692839, + "grad_norm": 0.8878232196618114, + "learning_rate": 8.161355131848232e-06, + "loss": 0.8422, + "step": 9319 + }, + { + "epoch": 0.5721477025077504, + "grad_norm": 0.8292561397563677, + "learning_rate": 8.159400716605918e-06, + "loss": 0.8018, + "step": 9320 + }, + { + "epoch": 0.5722090917462169, + "grad_norm": 0.8435625848228704, + "learning_rate": 8.157446374132335e-06, + "loss": 0.8218, + "step": 9321 + }, + { + "epoch": 0.5722704809846834, + "grad_norm": 0.7063572386395148, + "learning_rate": 8.155492104504755e-06, + "loss": 0.804, + "step": 9322 + }, + { + "epoch": 0.5723318702231499, + "grad_norm": 0.8699205377354541, + "learning_rate": 8.153537907800438e-06, + "loss": 0.882, + "step": 9323 + }, + { + "epoch": 0.5723932594616163, + "grad_norm": 0.7054509816951756, + "learning_rate": 8.15158378409664e-06, + "loss": 0.7897, + "step": 9324 + }, + { + "epoch": 0.5724546487000829, + "grad_norm": 0.8237834699944221, + "learning_rate": 8.149629733470622e-06, + "loss": 0.8409, + "step": 9325 + }, + { + "epoch": 0.5725160379385493, + "grad_norm": 0.8320859153969158, + "learning_rate": 8.147675755999638e-06, + "loss": 0.8058, + "step": 9326 + }, + { + "epoch": 0.5725774271770159, + "grad_norm": 0.7563059280022374, + "learning_rate": 8.145721851760934e-06, + "loss": 0.8196, + "step": 9327 + }, + { + "epoch": 0.5726388164154824, + "grad_norm": 0.7867536649895758, + "learning_rate": 8.14376802083177e-06, + "loss": 0.8377, + "step": 9328 + }, + { + "epoch": 0.5727002056539489, + "grad_norm": 0.6024025446443698, + "learning_rate": 8.14181426328938e-06, + "loss": 0.6866, + "step": 9329 + }, + { + "epoch": 0.5727615948924154, + "grad_norm": 0.8941749348306234, + "learning_rate": 8.13986057921101e-06, + "loss": 0.8225, + "step": 9330 + }, + { + "epoch": 0.5728229841308818, + "grad_norm": 0.870175890280539, + "learning_rate": 8.1379069686739e-06, + "loss": 0.7913, + "step": 9331 + }, + { + "epoch": 0.5728843733693484, + "grad_norm": 0.7871645774698103, + "learning_rate": 8.135953431755286e-06, + "loss": 0.8277, + "step": 9332 + }, + { + "epoch": 0.5729457626078148, + "grad_norm": 0.7983877534310317, + "learning_rate": 8.133999968532406e-06, + "loss": 0.8214, + "step": 9333 + }, + { + "epoch": 0.5730071518462814, + "grad_norm": 0.8360004885222904, + "learning_rate": 8.132046579082486e-06, + "loss": 0.8334, + "step": 9334 + }, + { + "epoch": 0.5730685410847478, + "grad_norm": 0.7459009652830296, + "learning_rate": 8.130093263482752e-06, + "loss": 0.7901, + "step": 9335 + }, + { + "epoch": 0.5731299303232144, + "grad_norm": 0.9862333223244426, + "learning_rate": 8.128140021810436e-06, + "loss": 0.8141, + "step": 9336 + }, + { + "epoch": 0.5731913195616808, + "grad_norm": 0.8648262046640097, + "learning_rate": 8.126186854142752e-06, + "loss": 0.824, + "step": 9337 + }, + { + "epoch": 0.5732527088001473, + "grad_norm": 0.9187058155602984, + "learning_rate": 8.124233760556932e-06, + "loss": 0.8307, + "step": 9338 + }, + { + "epoch": 0.5733140980386139, + "grad_norm": 0.8227390660643096, + "learning_rate": 8.122280741130177e-06, + "loss": 0.8099, + "step": 9339 + }, + { + "epoch": 0.5733754872770803, + "grad_norm": 0.6151131436810918, + "learning_rate": 8.120327795939708e-06, + "loss": 0.7033, + "step": 9340 + }, + { + "epoch": 0.5734368765155469, + "grad_norm": 0.8730826063866325, + "learning_rate": 8.118374925062733e-06, + "loss": 0.8269, + "step": 9341 + }, + { + "epoch": 0.5734982657540133, + "grad_norm": 0.8522553314994818, + "learning_rate": 8.116422128576462e-06, + "loss": 0.876, + "step": 9342 + }, + { + "epoch": 0.5735596549924799, + "grad_norm": 0.8501302362431006, + "learning_rate": 8.114469406558102e-06, + "loss": 0.7884, + "step": 9343 + }, + { + "epoch": 0.5736210442309463, + "grad_norm": 0.8073247480242655, + "learning_rate": 8.112516759084845e-06, + "loss": 0.7579, + "step": 9344 + }, + { + "epoch": 0.5736824334694128, + "grad_norm": 0.5746412829859859, + "learning_rate": 8.1105641862339e-06, + "loss": 0.7319, + "step": 9345 + }, + { + "epoch": 0.5737438227078793, + "grad_norm": 0.8644115984814223, + "learning_rate": 8.108611688082453e-06, + "loss": 0.8263, + "step": 9346 + }, + { + "epoch": 0.5738052119463458, + "grad_norm": 0.7715883101496431, + "learning_rate": 8.106659264707707e-06, + "loss": 0.8031, + "step": 9347 + }, + { + "epoch": 0.5738666011848123, + "grad_norm": 0.8094279066162334, + "learning_rate": 8.104706916186847e-06, + "loss": 0.7838, + "step": 9348 + }, + { + "epoch": 0.5739279904232788, + "grad_norm": 0.9399730478891518, + "learning_rate": 8.102754642597055e-06, + "loss": 0.8736, + "step": 9349 + }, + { + "epoch": 0.5739893796617453, + "grad_norm": 0.8323542130303553, + "learning_rate": 8.100802444015522e-06, + "loss": 0.8306, + "step": 9350 + }, + { + "epoch": 0.5740507689002118, + "grad_norm": 0.951708045558342, + "learning_rate": 8.098850320519423e-06, + "loss": 0.8287, + "step": 9351 + }, + { + "epoch": 0.5741121581386783, + "grad_norm": 0.8239886831180446, + "learning_rate": 8.096898272185945e-06, + "loss": 0.7708, + "step": 9352 + }, + { + "epoch": 0.5741735473771448, + "grad_norm": 0.8404224132818735, + "learning_rate": 8.094946299092252e-06, + "loss": 0.8038, + "step": 9353 + }, + { + "epoch": 0.5742349366156113, + "grad_norm": 0.8766273293855544, + "learning_rate": 8.092994401315522e-06, + "loss": 0.8282, + "step": 9354 + }, + { + "epoch": 0.5742963258540777, + "grad_norm": 0.7464696348980032, + "learning_rate": 8.09104257893292e-06, + "loss": 0.8164, + "step": 9355 + }, + { + "epoch": 0.5743577150925443, + "grad_norm": 0.7997864225468685, + "learning_rate": 8.089090832021617e-06, + "loss": 0.7808, + "step": 9356 + }, + { + "epoch": 0.5744191043310107, + "grad_norm": 0.8040167477328838, + "learning_rate": 8.087139160658778e-06, + "loss": 0.7404, + "step": 9357 + }, + { + "epoch": 0.5744804935694773, + "grad_norm": 0.8448950757290058, + "learning_rate": 8.085187564921553e-06, + "loss": 0.775, + "step": 9358 + }, + { + "epoch": 0.5745418828079437, + "grad_norm": 0.7827096518672858, + "learning_rate": 8.083236044887106e-06, + "loss": 0.8184, + "step": 9359 + }, + { + "epoch": 0.5746032720464103, + "grad_norm": 0.7684526763476035, + "learning_rate": 8.081284600632589e-06, + "loss": 0.7742, + "step": 9360 + }, + { + "epoch": 0.5746646612848768, + "grad_norm": 0.7761037879291212, + "learning_rate": 8.079333232235154e-06, + "loss": 0.7995, + "step": 9361 + }, + { + "epoch": 0.5747260505233432, + "grad_norm": 0.8509173751801836, + "learning_rate": 8.077381939771952e-06, + "loss": 0.8662, + "step": 9362 + }, + { + "epoch": 0.5747874397618098, + "grad_norm": 0.8391856731074452, + "learning_rate": 8.07543072332012e-06, + "loss": 0.7693, + "step": 9363 + }, + { + "epoch": 0.5748488290002762, + "grad_norm": 0.859132412144188, + "learning_rate": 8.073479582956806e-06, + "loss": 0.8166, + "step": 9364 + }, + { + "epoch": 0.5749102182387428, + "grad_norm": 0.7896138298138268, + "learning_rate": 8.07152851875915e-06, + "loss": 0.766, + "step": 9365 + }, + { + "epoch": 0.5749716074772092, + "grad_norm": 0.8306521149147978, + "learning_rate": 8.069577530804283e-06, + "loss": 0.8314, + "step": 9366 + }, + { + "epoch": 0.5750329967156758, + "grad_norm": 0.8311697699419976, + "learning_rate": 8.067626619169344e-06, + "loss": 0.8498, + "step": 9367 + }, + { + "epoch": 0.5750943859541422, + "grad_norm": 0.8088070262249554, + "learning_rate": 8.06567578393146e-06, + "loss": 0.7993, + "step": 9368 + }, + { + "epoch": 0.5751557751926087, + "grad_norm": 0.866548845368458, + "learning_rate": 8.063725025167755e-06, + "loss": 0.8581, + "step": 9369 + }, + { + "epoch": 0.5752171644310752, + "grad_norm": 0.8207864450522566, + "learning_rate": 8.061774342955357e-06, + "loss": 0.8366, + "step": 9370 + }, + { + "epoch": 0.5752785536695417, + "grad_norm": 0.8593057893608242, + "learning_rate": 8.059823737371384e-06, + "loss": 0.8096, + "step": 9371 + }, + { + "epoch": 0.5753399429080083, + "grad_norm": 0.8862566070985254, + "learning_rate": 8.05787320849296e-06, + "loss": 0.8379, + "step": 9372 + }, + { + "epoch": 0.5754013321464747, + "grad_norm": 0.8076381643084203, + "learning_rate": 8.055922756397192e-06, + "loss": 0.7978, + "step": 9373 + }, + { + "epoch": 0.5754627213849413, + "grad_norm": 0.8670347860701826, + "learning_rate": 8.053972381161192e-06, + "loss": 0.7966, + "step": 9374 + }, + { + "epoch": 0.5755241106234077, + "grad_norm": 0.7967646949414146, + "learning_rate": 8.052022082862076e-06, + "loss": 0.8078, + "step": 9375 + }, + { + "epoch": 0.5755854998618742, + "grad_norm": 0.8961504452696133, + "learning_rate": 8.050071861576942e-06, + "loss": 0.8012, + "step": 9376 + }, + { + "epoch": 0.5756468891003407, + "grad_norm": 0.8079843660554825, + "learning_rate": 8.048121717382904e-06, + "loss": 0.8481, + "step": 9377 + }, + { + "epoch": 0.5757082783388072, + "grad_norm": 0.934021999968231, + "learning_rate": 8.046171650357047e-06, + "loss": 0.8523, + "step": 9378 + }, + { + "epoch": 0.5757696675772737, + "grad_norm": 0.8300074454017079, + "learning_rate": 8.044221660576476e-06, + "loss": 0.7979, + "step": 9379 + }, + { + "epoch": 0.5758310568157402, + "grad_norm": 0.8505664676165169, + "learning_rate": 8.042271748118283e-06, + "loss": 0.8126, + "step": 9380 + }, + { + "epoch": 0.5758924460542068, + "grad_norm": 0.8222257864224993, + "learning_rate": 8.04032191305956e-06, + "loss": 0.7907, + "step": 9381 + }, + { + "epoch": 0.5759538352926732, + "grad_norm": 0.8263878159497261, + "learning_rate": 8.038372155477393e-06, + "loss": 0.7971, + "step": 9382 + }, + { + "epoch": 0.5760152245311397, + "grad_norm": 0.9569297128853972, + "learning_rate": 8.036422475448863e-06, + "loss": 0.8537, + "step": 9383 + }, + { + "epoch": 0.5760766137696062, + "grad_norm": 0.822036151279859, + "learning_rate": 8.034472873051056e-06, + "loss": 0.7892, + "step": 9384 + }, + { + "epoch": 0.5761380030080727, + "grad_norm": 0.8234805081020461, + "learning_rate": 8.032523348361047e-06, + "loss": 0.7663, + "step": 9385 + }, + { + "epoch": 0.5761993922465392, + "grad_norm": 0.8038382419201834, + "learning_rate": 8.030573901455915e-06, + "loss": 0.7829, + "step": 9386 + }, + { + "epoch": 0.5762607814850057, + "grad_norm": 0.7938129917759273, + "learning_rate": 8.028624532412734e-06, + "loss": 0.8046, + "step": 9387 + }, + { + "epoch": 0.5763221707234721, + "grad_norm": 0.9234805347181274, + "learning_rate": 8.02667524130856e-06, + "loss": 0.8098, + "step": 9388 + }, + { + "epoch": 0.5763835599619387, + "grad_norm": 0.9481167020299617, + "learning_rate": 8.024726028220474e-06, + "loss": 0.8327, + "step": 9389 + }, + { + "epoch": 0.5764449492004051, + "grad_norm": 0.8252109114338289, + "learning_rate": 8.022776893225533e-06, + "loss": 0.8339, + "step": 9390 + }, + { + "epoch": 0.5765063384388717, + "grad_norm": 0.8220731730488421, + "learning_rate": 8.020827836400792e-06, + "loss": 0.8406, + "step": 9391 + }, + { + "epoch": 0.5765677276773382, + "grad_norm": 0.9146521603867155, + "learning_rate": 8.018878857823317e-06, + "loss": 0.8324, + "step": 9392 + }, + { + "epoch": 0.5766291169158047, + "grad_norm": 0.8782273869809855, + "learning_rate": 8.016929957570154e-06, + "loss": 0.8145, + "step": 9393 + }, + { + "epoch": 0.5766905061542712, + "grad_norm": 0.9586027627501458, + "learning_rate": 8.014981135718354e-06, + "loss": 0.8237, + "step": 9394 + }, + { + "epoch": 0.5767518953927376, + "grad_norm": 0.5729917325505324, + "learning_rate": 8.013032392344969e-06, + "loss": 0.682, + "step": 9395 + }, + { + "epoch": 0.5768132846312042, + "grad_norm": 0.9486064795795017, + "learning_rate": 8.011083727527038e-06, + "loss": 0.8789, + "step": 9396 + }, + { + "epoch": 0.5768746738696706, + "grad_norm": 0.8744602486830244, + "learning_rate": 8.009135141341608e-06, + "loss": 0.8045, + "step": 9397 + }, + { + "epoch": 0.5769360631081372, + "grad_norm": 0.8774308764340951, + "learning_rate": 8.007186633865714e-06, + "loss": 0.7999, + "step": 9398 + }, + { + "epoch": 0.5769974523466036, + "grad_norm": 0.7901429656994983, + "learning_rate": 8.005238205176387e-06, + "loss": 0.7622, + "step": 9399 + }, + { + "epoch": 0.5770588415850701, + "grad_norm": 0.8280490621496723, + "learning_rate": 8.003289855350665e-06, + "loss": 0.7958, + "step": 9400 + }, + { + "epoch": 0.5771202308235366, + "grad_norm": 0.8608483176344566, + "learning_rate": 8.00134158446557e-06, + "loss": 0.8777, + "step": 9401 + }, + { + "epoch": 0.5771816200620031, + "grad_norm": 0.8528481223111254, + "learning_rate": 7.99939339259814e-06, + "loss": 0.7905, + "step": 9402 + }, + { + "epoch": 0.5772430093004697, + "grad_norm": 0.5758526534691071, + "learning_rate": 7.997445279825385e-06, + "loss": 0.6677, + "step": 9403 + }, + { + "epoch": 0.5773043985389361, + "grad_norm": 0.9455630587392095, + "learning_rate": 7.995497246224328e-06, + "loss": 0.8828, + "step": 9404 + }, + { + "epoch": 0.5773657877774027, + "grad_norm": 0.8324463715948459, + "learning_rate": 7.993549291871983e-06, + "loss": 0.7961, + "step": 9405 + }, + { + "epoch": 0.5774271770158691, + "grad_norm": 0.7951297613944365, + "learning_rate": 7.991601416845368e-06, + "loss": 0.8026, + "step": 9406 + }, + { + "epoch": 0.5774885662543356, + "grad_norm": 0.8390132573745961, + "learning_rate": 7.989653621221494e-06, + "loss": 0.8443, + "step": 9407 + }, + { + "epoch": 0.5775499554928021, + "grad_norm": 0.8262738201019472, + "learning_rate": 7.98770590507736e-06, + "loss": 0.8513, + "step": 9408 + }, + { + "epoch": 0.5776113447312686, + "grad_norm": 0.8966070155527878, + "learning_rate": 7.985758268489975e-06, + "loss": 0.8441, + "step": 9409 + }, + { + "epoch": 0.5776727339697351, + "grad_norm": 0.8465873033972878, + "learning_rate": 7.98381071153634e-06, + "loss": 0.851, + "step": 9410 + }, + { + "epoch": 0.5777341232082016, + "grad_norm": 0.8371590028924706, + "learning_rate": 7.981863234293453e-06, + "loss": 0.8797, + "step": 9411 + }, + { + "epoch": 0.577795512446668, + "grad_norm": 0.7298576240257941, + "learning_rate": 7.979915836838302e-06, + "loss": 0.803, + "step": 9412 + }, + { + "epoch": 0.5778569016851346, + "grad_norm": 0.8913654410574934, + "learning_rate": 7.977968519247881e-06, + "loss": 0.8374, + "step": 9413 + }, + { + "epoch": 0.5779182909236011, + "grad_norm": 0.8039215639851508, + "learning_rate": 7.976021281599182e-06, + "loss": 0.845, + "step": 9414 + }, + { + "epoch": 0.5779796801620676, + "grad_norm": 0.9029929213437997, + "learning_rate": 7.974074123969185e-06, + "loss": 0.7967, + "step": 9415 + }, + { + "epoch": 0.5780410694005341, + "grad_norm": 0.8847576928304893, + "learning_rate": 7.972127046434878e-06, + "loss": 0.8768, + "step": 9416 + }, + { + "epoch": 0.5781024586390006, + "grad_norm": 0.8795218249787057, + "learning_rate": 7.97018004907323e-06, + "loss": 0.8795, + "step": 9417 + }, + { + "epoch": 0.5781638478774671, + "grad_norm": 0.8269078118127124, + "learning_rate": 7.968233131961223e-06, + "loss": 0.7861, + "step": 9418 + }, + { + "epoch": 0.5782252371159335, + "grad_norm": 0.81435707922313, + "learning_rate": 7.966286295175824e-06, + "loss": 0.8043, + "step": 9419 + }, + { + "epoch": 0.5782866263544001, + "grad_norm": 0.8854329028165495, + "learning_rate": 7.964339538794006e-06, + "loss": 0.8081, + "step": 9420 + }, + { + "epoch": 0.5783480155928665, + "grad_norm": 0.8348298200737053, + "learning_rate": 7.962392862892738e-06, + "loss": 0.7765, + "step": 9421 + }, + { + "epoch": 0.5784094048313331, + "grad_norm": 0.8205285963475656, + "learning_rate": 7.960446267548972e-06, + "loss": 0.7772, + "step": 9422 + }, + { + "epoch": 0.5784707940697995, + "grad_norm": 0.8488350923086533, + "learning_rate": 7.958499752839677e-06, + "loss": 0.7971, + "step": 9423 + }, + { + "epoch": 0.5785321833082661, + "grad_norm": 0.831717140956946, + "learning_rate": 7.956553318841801e-06, + "loss": 0.9006, + "step": 9424 + }, + { + "epoch": 0.5785935725467326, + "grad_norm": 0.9171975013689994, + "learning_rate": 7.954606965632305e-06, + "loss": 0.8165, + "step": 9425 + }, + { + "epoch": 0.578654961785199, + "grad_norm": 0.8279543824385117, + "learning_rate": 7.952660693288137e-06, + "loss": 0.7925, + "step": 9426 + }, + { + "epoch": 0.5787163510236656, + "grad_norm": 0.8999757526144919, + "learning_rate": 7.950714501886239e-06, + "loss": 0.7994, + "step": 9427 + }, + { + "epoch": 0.578777740262132, + "grad_norm": 0.8499410300295027, + "learning_rate": 7.948768391503558e-06, + "loss": 0.8045, + "step": 9428 + }, + { + "epoch": 0.5788391295005986, + "grad_norm": 0.8343982618862741, + "learning_rate": 7.946822362217033e-06, + "loss": 0.787, + "step": 9429 + }, + { + "epoch": 0.578900518739065, + "grad_norm": 0.9156278434734152, + "learning_rate": 7.9448764141036e-06, + "loss": 0.8011, + "step": 9430 + }, + { + "epoch": 0.5789619079775316, + "grad_norm": 0.8840128394703206, + "learning_rate": 7.942930547240196e-06, + "loss": 0.8689, + "step": 9431 + }, + { + "epoch": 0.579023297215998, + "grad_norm": 0.8776422864694423, + "learning_rate": 7.94098476170375e-06, + "loss": 0.785, + "step": 9432 + }, + { + "epoch": 0.5790846864544645, + "grad_norm": 0.9534017440460664, + "learning_rate": 7.939039057571186e-06, + "loss": 0.8444, + "step": 9433 + }, + { + "epoch": 0.5791460756929311, + "grad_norm": 0.8805861021616063, + "learning_rate": 7.937093434919431e-06, + "loss": 0.8138, + "step": 9434 + }, + { + "epoch": 0.5792074649313975, + "grad_norm": 0.6125798714299762, + "learning_rate": 7.935147893825405e-06, + "loss": 0.7064, + "step": 9435 + }, + { + "epoch": 0.5792688541698641, + "grad_norm": 0.8761034400783723, + "learning_rate": 7.933202434366032e-06, + "loss": 0.8102, + "step": 9436 + }, + { + "epoch": 0.5793302434083305, + "grad_norm": 0.8873905313393843, + "learning_rate": 7.931257056618215e-06, + "loss": 0.8257, + "step": 9437 + }, + { + "epoch": 0.579391632646797, + "grad_norm": 0.8869971449962687, + "learning_rate": 7.92931176065887e-06, + "loss": 0.8261, + "step": 9438 + }, + { + "epoch": 0.5794530218852635, + "grad_norm": 0.8685260489530968, + "learning_rate": 7.927366546564911e-06, + "loss": 0.7918, + "step": 9439 + }, + { + "epoch": 0.57951441112373, + "grad_norm": 0.8763739152283605, + "learning_rate": 7.925421414413234e-06, + "loss": 0.8541, + "step": 9440 + }, + { + "epoch": 0.5795758003621965, + "grad_norm": 0.9421569684410421, + "learning_rate": 7.923476364280748e-06, + "loss": 0.7702, + "step": 9441 + }, + { + "epoch": 0.579637189600663, + "grad_norm": 0.8111048900490799, + "learning_rate": 7.921531396244344e-06, + "loss": 0.8384, + "step": 9442 + }, + { + "epoch": 0.5796985788391295, + "grad_norm": 0.8832259529509817, + "learning_rate": 7.919586510380922e-06, + "loss": 0.8055, + "step": 9443 + }, + { + "epoch": 0.579759968077596, + "grad_norm": 0.8251567027053348, + "learning_rate": 7.91764170676737e-06, + "loss": 0.7764, + "step": 9444 + }, + { + "epoch": 0.5798213573160625, + "grad_norm": 0.7825283544564684, + "learning_rate": 7.91569698548058e-06, + "loss": 0.7746, + "step": 9445 + }, + { + "epoch": 0.579882746554529, + "grad_norm": 0.8427107067664995, + "learning_rate": 7.913752346597438e-06, + "loss": 0.7904, + "step": 9446 + }, + { + "epoch": 0.5799441357929955, + "grad_norm": 0.8661388706542149, + "learning_rate": 7.91180779019482e-06, + "loss": 0.7747, + "step": 9447 + }, + { + "epoch": 0.580005525031462, + "grad_norm": 0.7491257734608068, + "learning_rate": 7.90986331634961e-06, + "loss": 0.8329, + "step": 9448 + }, + { + "epoch": 0.5800669142699285, + "grad_norm": 0.8574730480432242, + "learning_rate": 7.90791892513868e-06, + "loss": 0.8075, + "step": 9449 + }, + { + "epoch": 0.580128303508395, + "grad_norm": 0.8786527461142016, + "learning_rate": 7.905974616638906e-06, + "loss": 0.782, + "step": 9450 + }, + { + "epoch": 0.5801896927468615, + "grad_norm": 0.8113565677514698, + "learning_rate": 7.904030390927158e-06, + "loss": 0.7845, + "step": 9451 + }, + { + "epoch": 0.5802510819853279, + "grad_norm": 0.808919124406243, + "learning_rate": 7.902086248080294e-06, + "loss": 0.8026, + "step": 9452 + }, + { + "epoch": 0.5803124712237945, + "grad_norm": 0.9106980235624944, + "learning_rate": 7.900142188175183e-06, + "loss": 0.8045, + "step": 9453 + }, + { + "epoch": 0.5803738604622609, + "grad_norm": 0.8291418546226661, + "learning_rate": 7.898198211288679e-06, + "loss": 0.7967, + "step": 9454 + }, + { + "epoch": 0.5804352497007275, + "grad_norm": 0.8811821795987922, + "learning_rate": 7.896254317497644e-06, + "loss": 0.8533, + "step": 9455 + }, + { + "epoch": 0.580496638939194, + "grad_norm": 0.8217092352486678, + "learning_rate": 7.894310506878931e-06, + "loss": 0.8136, + "step": 9456 + }, + { + "epoch": 0.5805580281776604, + "grad_norm": 0.8264097934258023, + "learning_rate": 7.892366779509381e-06, + "loss": 0.8203, + "step": 9457 + }, + { + "epoch": 0.580619417416127, + "grad_norm": 0.7835179448980163, + "learning_rate": 7.890423135465845e-06, + "loss": 0.8195, + "step": 9458 + }, + { + "epoch": 0.5806808066545934, + "grad_norm": 0.8897970651660141, + "learning_rate": 7.888479574825166e-06, + "loss": 0.8679, + "step": 9459 + }, + { + "epoch": 0.58074219589306, + "grad_norm": 0.8487329579920467, + "learning_rate": 7.88653609766418e-06, + "loss": 0.8023, + "step": 9460 + }, + { + "epoch": 0.5808035851315264, + "grad_norm": 0.8105602953125826, + "learning_rate": 7.88459270405973e-06, + "loss": 0.8151, + "step": 9461 + }, + { + "epoch": 0.580864974369993, + "grad_norm": 0.8224573576122433, + "learning_rate": 7.882649394088644e-06, + "loss": 0.8376, + "step": 9462 + }, + { + "epoch": 0.5809263636084594, + "grad_norm": 0.7889833180781137, + "learning_rate": 7.880706167827748e-06, + "loss": 0.8057, + "step": 9463 + }, + { + "epoch": 0.5809877528469259, + "grad_norm": 0.8262891205728029, + "learning_rate": 7.878763025353875e-06, + "loss": 0.7763, + "step": 9464 + }, + { + "epoch": 0.5810491420853924, + "grad_norm": 0.8067709016461589, + "learning_rate": 7.876819966743842e-06, + "loss": 0.8308, + "step": 9465 + }, + { + "epoch": 0.5811105313238589, + "grad_norm": 0.8336026445354523, + "learning_rate": 7.874876992074476e-06, + "loss": 0.8055, + "step": 9466 + }, + { + "epoch": 0.5811719205623255, + "grad_norm": 0.8986778281367006, + "learning_rate": 7.872934101422585e-06, + "loss": 0.8208, + "step": 9467 + }, + { + "epoch": 0.5812333098007919, + "grad_norm": 0.7776170991709145, + "learning_rate": 7.870991294864986e-06, + "loss": 0.7918, + "step": 9468 + }, + { + "epoch": 0.5812946990392585, + "grad_norm": 0.7501709222637978, + "learning_rate": 7.869048572478488e-06, + "loss": 0.8017, + "step": 9469 + }, + { + "epoch": 0.5813560882777249, + "grad_norm": 0.9586140002919451, + "learning_rate": 7.867105934339898e-06, + "loss": 0.816, + "step": 9470 + }, + { + "epoch": 0.5814174775161914, + "grad_norm": 0.9419669482801163, + "learning_rate": 7.865163380526019e-06, + "loss": 0.8636, + "step": 9471 + }, + { + "epoch": 0.5814788667546579, + "grad_norm": 0.8558579158158891, + "learning_rate": 7.863220911113645e-06, + "loss": 0.8256, + "step": 9472 + }, + { + "epoch": 0.5815402559931244, + "grad_norm": 0.8917227686794973, + "learning_rate": 7.86127852617958e-06, + "loss": 0.8417, + "step": 9473 + }, + { + "epoch": 0.5816016452315909, + "grad_norm": 0.8014357635368681, + "learning_rate": 7.85933622580061e-06, + "loss": 0.8157, + "step": 9474 + }, + { + "epoch": 0.5816630344700574, + "grad_norm": 0.8565851884616488, + "learning_rate": 7.857394010053531e-06, + "loss": 0.7777, + "step": 9475 + }, + { + "epoch": 0.5817244237085238, + "grad_norm": 0.7606207577471273, + "learning_rate": 7.85545187901513e-06, + "loss": 0.7914, + "step": 9476 + }, + { + "epoch": 0.5817858129469904, + "grad_norm": 0.9105877190371329, + "learning_rate": 7.85350983276218e-06, + "loss": 0.8515, + "step": 9477 + }, + { + "epoch": 0.5818472021854569, + "grad_norm": 0.8310621473442791, + "learning_rate": 7.851567871371468e-06, + "loss": 0.7697, + "step": 9478 + }, + { + "epoch": 0.5819085914239234, + "grad_norm": 0.8105326436622801, + "learning_rate": 7.849625994919767e-06, + "loss": 0.7981, + "step": 9479 + }, + { + "epoch": 0.5819699806623899, + "grad_norm": 0.775647307185117, + "learning_rate": 7.847684203483859e-06, + "loss": 0.7968, + "step": 9480 + }, + { + "epoch": 0.5820313699008564, + "grad_norm": 0.8748978002045806, + "learning_rate": 7.845742497140498e-06, + "loss": 0.8298, + "step": 9481 + }, + { + "epoch": 0.5820927591393229, + "grad_norm": 0.9266560239732505, + "learning_rate": 7.843800875966462e-06, + "loss": 0.8671, + "step": 9482 + }, + { + "epoch": 0.5821541483777893, + "grad_norm": 0.7608583445263086, + "learning_rate": 7.841859340038505e-06, + "loss": 0.7776, + "step": 9483 + }, + { + "epoch": 0.5822155376162559, + "grad_norm": 1.018488031829931, + "learning_rate": 7.839917889433395e-06, + "loss": 0.8393, + "step": 9484 + }, + { + "epoch": 0.5822769268547223, + "grad_norm": 0.974758595853701, + "learning_rate": 7.837976524227884e-06, + "loss": 0.8191, + "step": 9485 + }, + { + "epoch": 0.5823383160931889, + "grad_norm": 0.8459043189423618, + "learning_rate": 7.836035244498722e-06, + "loss": 0.8165, + "step": 9486 + }, + { + "epoch": 0.5823997053316554, + "grad_norm": 0.8092217744085457, + "learning_rate": 7.834094050322661e-06, + "loss": 0.8065, + "step": 9487 + }, + { + "epoch": 0.5824610945701219, + "grad_norm": 0.8218790576057071, + "learning_rate": 7.832152941776445e-06, + "loss": 0.7943, + "step": 9488 + }, + { + "epoch": 0.5825224838085884, + "grad_norm": 0.715665708754366, + "learning_rate": 7.83021191893682e-06, + "loss": 0.7714, + "step": 9489 + }, + { + "epoch": 0.5825838730470548, + "grad_norm": 0.8463700871449673, + "learning_rate": 7.828270981880525e-06, + "loss": 0.7891, + "step": 9490 + }, + { + "epoch": 0.5826452622855214, + "grad_norm": 0.8603742973017553, + "learning_rate": 7.826330130684287e-06, + "loss": 0.7739, + "step": 9491 + }, + { + "epoch": 0.5827066515239878, + "grad_norm": 0.8887585597783096, + "learning_rate": 7.824389365424849e-06, + "loss": 0.78, + "step": 9492 + }, + { + "epoch": 0.5827680407624544, + "grad_norm": 0.84422746676354, + "learning_rate": 7.822448686178934e-06, + "loss": 0.7873, + "step": 9493 + }, + { + "epoch": 0.5828294300009208, + "grad_norm": 0.8301877847158655, + "learning_rate": 7.820508093023268e-06, + "loss": 0.8034, + "step": 9494 + }, + { + "epoch": 0.5828908192393873, + "grad_norm": 0.8952436505455381, + "learning_rate": 7.818567586034578e-06, + "loss": 0.763, + "step": 9495 + }, + { + "epoch": 0.5829522084778538, + "grad_norm": 0.8922573652966896, + "learning_rate": 7.816627165289573e-06, + "loss": 0.8517, + "step": 9496 + }, + { + "epoch": 0.5830135977163203, + "grad_norm": 0.7385795982877945, + "learning_rate": 7.814686830864975e-06, + "loss": 0.7664, + "step": 9497 + }, + { + "epoch": 0.5830749869547869, + "grad_norm": 0.9724837888134615, + "learning_rate": 7.812746582837496e-06, + "loss": 0.8282, + "step": 9498 + }, + { + "epoch": 0.5831363761932533, + "grad_norm": 0.7573661203264326, + "learning_rate": 7.81080642128384e-06, + "loss": 0.8325, + "step": 9499 + }, + { + "epoch": 0.5831977654317199, + "grad_norm": 0.9139522815888396, + "learning_rate": 7.80886634628072e-06, + "loss": 0.87, + "step": 9500 + }, + { + "epoch": 0.5832591546701863, + "grad_norm": 0.919326192581944, + "learning_rate": 7.80692635790483e-06, + "loss": 0.8928, + "step": 9501 + }, + { + "epoch": 0.5833205439086528, + "grad_norm": 0.9523607481064319, + "learning_rate": 7.804986456232868e-06, + "loss": 0.8692, + "step": 9502 + }, + { + "epoch": 0.5833819331471193, + "grad_norm": 0.855439170541846, + "learning_rate": 7.803046641341534e-06, + "loss": 0.7834, + "step": 9503 + }, + { + "epoch": 0.5834433223855858, + "grad_norm": 0.8774724115249957, + "learning_rate": 7.801106913307512e-06, + "loss": 0.8075, + "step": 9504 + }, + { + "epoch": 0.5835047116240523, + "grad_norm": 0.8491350075283564, + "learning_rate": 7.7991672722075e-06, + "loss": 0.7809, + "step": 9505 + }, + { + "epoch": 0.5835661008625188, + "grad_norm": 0.9542407428480237, + "learning_rate": 7.797227718118176e-06, + "loss": 0.7725, + "step": 9506 + }, + { + "epoch": 0.5836274901009852, + "grad_norm": 0.8224309328896842, + "learning_rate": 7.79528825111622e-06, + "loss": 0.8221, + "step": 9507 + }, + { + "epoch": 0.5836888793394518, + "grad_norm": 0.9392164755110212, + "learning_rate": 7.793348871278308e-06, + "loss": 0.8589, + "step": 9508 + }, + { + "epoch": 0.5837502685779183, + "grad_norm": 0.8048049444999428, + "learning_rate": 7.79140957868112e-06, + "loss": 0.8001, + "step": 9509 + }, + { + "epoch": 0.5838116578163848, + "grad_norm": 0.820279403848641, + "learning_rate": 7.789470373401327e-06, + "loss": 0.7844, + "step": 9510 + }, + { + "epoch": 0.5838730470548513, + "grad_norm": 0.9814945821295032, + "learning_rate": 7.787531255515587e-06, + "loss": 0.8389, + "step": 9511 + }, + { + "epoch": 0.5839344362933178, + "grad_norm": 0.9111355530170675, + "learning_rate": 7.785592225100573e-06, + "loss": 0.8431, + "step": 9512 + }, + { + "epoch": 0.5839958255317843, + "grad_norm": 0.8955161975468386, + "learning_rate": 7.78365328223294e-06, + "loss": 0.8265, + "step": 9513 + }, + { + "epoch": 0.5840572147702507, + "grad_norm": 0.7952402170813446, + "learning_rate": 7.781714426989346e-06, + "loss": 0.8017, + "step": 9514 + }, + { + "epoch": 0.5841186040087173, + "grad_norm": 0.8333155612898089, + "learning_rate": 7.779775659446449e-06, + "loss": 0.8264, + "step": 9515 + }, + { + "epoch": 0.5841799932471837, + "grad_norm": 0.882634016105373, + "learning_rate": 7.77783697968089e-06, + "loss": 0.8406, + "step": 9516 + }, + { + "epoch": 0.5842413824856503, + "grad_norm": 0.8168852507014867, + "learning_rate": 7.775898387769324e-06, + "loss": 0.8235, + "step": 9517 + }, + { + "epoch": 0.5843027717241167, + "grad_norm": 0.7955202525034782, + "learning_rate": 7.773959883788387e-06, + "loss": 0.7763, + "step": 9518 + }, + { + "epoch": 0.5843641609625833, + "grad_norm": 0.7937901779843294, + "learning_rate": 7.772021467814723e-06, + "loss": 0.777, + "step": 9519 + }, + { + "epoch": 0.5844255502010498, + "grad_norm": 0.7981341401991353, + "learning_rate": 7.77008313992497e-06, + "loss": 0.7793, + "step": 9520 + }, + { + "epoch": 0.5844869394395162, + "grad_norm": 0.8285127380939431, + "learning_rate": 7.768144900195752e-06, + "loss": 0.7496, + "step": 9521 + }, + { + "epoch": 0.5845483286779828, + "grad_norm": 0.884941403581906, + "learning_rate": 7.766206748703703e-06, + "loss": 0.8453, + "step": 9522 + }, + { + "epoch": 0.5846097179164492, + "grad_norm": 0.9432485252446692, + "learning_rate": 7.764268685525449e-06, + "loss": 0.8752, + "step": 9523 + }, + { + "epoch": 0.5846711071549158, + "grad_norm": 0.805707207883744, + "learning_rate": 7.762330710737612e-06, + "loss": 0.8193, + "step": 9524 + }, + { + "epoch": 0.5847324963933822, + "grad_norm": 0.8825582410277822, + "learning_rate": 7.760392824416811e-06, + "loss": 0.8793, + "step": 9525 + }, + { + "epoch": 0.5847938856318488, + "grad_norm": 0.8110477373113147, + "learning_rate": 7.75845502663966e-06, + "loss": 0.7903, + "step": 9526 + }, + { + "epoch": 0.5848552748703152, + "grad_norm": 0.8788229021288357, + "learning_rate": 7.756517317482767e-06, + "loss": 0.8415, + "step": 9527 + }, + { + "epoch": 0.5849166641087817, + "grad_norm": 0.9603748375589026, + "learning_rate": 7.754579697022746e-06, + "loss": 0.8141, + "step": 9528 + }, + { + "epoch": 0.5849780533472482, + "grad_norm": 0.7537690478006936, + "learning_rate": 7.752642165336195e-06, + "loss": 0.7787, + "step": 9529 + }, + { + "epoch": 0.5850394425857147, + "grad_norm": 0.8630487722692352, + "learning_rate": 7.750704722499727e-06, + "loss": 0.8221, + "step": 9530 + }, + { + "epoch": 0.5851008318241813, + "grad_norm": 0.8967269258264394, + "learning_rate": 7.748767368589927e-06, + "loss": 0.841, + "step": 9531 + }, + { + "epoch": 0.5851622210626477, + "grad_norm": 0.8365109116247246, + "learning_rate": 7.746830103683391e-06, + "loss": 0.786, + "step": 9532 + }, + { + "epoch": 0.5852236103011142, + "grad_norm": 0.8496161118463085, + "learning_rate": 7.744892927856715e-06, + "loss": 0.8171, + "step": 9533 + }, + { + "epoch": 0.5852849995395807, + "grad_norm": 0.7798353301494045, + "learning_rate": 7.74295584118648e-06, + "loss": 0.8044, + "step": 9534 + }, + { + "epoch": 0.5853463887780472, + "grad_norm": 0.8130361447411925, + "learning_rate": 7.741018843749279e-06, + "loss": 0.8319, + "step": 9535 + }, + { + "epoch": 0.5854077780165137, + "grad_norm": 0.9048725617404155, + "learning_rate": 7.739081935621677e-06, + "loss": 0.8191, + "step": 9536 + }, + { + "epoch": 0.5854691672549802, + "grad_norm": 0.8391290436230487, + "learning_rate": 7.737145116880261e-06, + "loss": 0.808, + "step": 9537 + }, + { + "epoch": 0.5855305564934467, + "grad_norm": 0.811043078771539, + "learning_rate": 7.735208387601601e-06, + "loss": 0.8228, + "step": 9538 + }, + { + "epoch": 0.5855919457319132, + "grad_norm": 0.9155092282611755, + "learning_rate": 7.733271747862265e-06, + "loss": 0.8482, + "step": 9539 + }, + { + "epoch": 0.5856533349703797, + "grad_norm": 0.9810305457030146, + "learning_rate": 7.731335197738826e-06, + "loss": 0.8386, + "step": 9540 + }, + { + "epoch": 0.5857147242088462, + "grad_norm": 0.9629017190085727, + "learning_rate": 7.729398737307834e-06, + "loss": 0.787, + "step": 9541 + }, + { + "epoch": 0.5857761134473127, + "grad_norm": 0.8774730861429674, + "learning_rate": 7.727462366645856e-06, + "loss": 0.8384, + "step": 9542 + }, + { + "epoch": 0.5858375026857792, + "grad_norm": 0.9112563066693887, + "learning_rate": 7.725526085829444e-06, + "loss": 0.8105, + "step": 9543 + }, + { + "epoch": 0.5858988919242457, + "grad_norm": 0.8386335816864032, + "learning_rate": 7.723589894935154e-06, + "loss": 0.8593, + "step": 9544 + }, + { + "epoch": 0.5859602811627121, + "grad_norm": 0.8589103111187106, + "learning_rate": 7.72165379403953e-06, + "loss": 0.8027, + "step": 9545 + }, + { + "epoch": 0.5860216704011787, + "grad_norm": 0.750189636221057, + "learning_rate": 7.719717783219115e-06, + "loss": 0.746, + "step": 9546 + }, + { + "epoch": 0.5860830596396451, + "grad_norm": 0.8817088115858119, + "learning_rate": 7.717781862550449e-06, + "loss": 0.7991, + "step": 9547 + }, + { + "epoch": 0.5861444488781117, + "grad_norm": 0.8019888697758846, + "learning_rate": 7.715846032110076e-06, + "loss": 0.8242, + "step": 9548 + }, + { + "epoch": 0.5862058381165781, + "grad_norm": 0.8913000958282413, + "learning_rate": 7.713910291974527e-06, + "loss": 0.7446, + "step": 9549 + }, + { + "epoch": 0.5862672273550447, + "grad_norm": 0.8486596870964834, + "learning_rate": 7.711974642220329e-06, + "loss": 0.823, + "step": 9550 + }, + { + "epoch": 0.5863286165935112, + "grad_norm": 0.875840280297812, + "learning_rate": 7.71003908292401e-06, + "loss": 0.7791, + "step": 9551 + }, + { + "epoch": 0.5863900058319776, + "grad_norm": 0.9590327141389052, + "learning_rate": 7.708103614162092e-06, + "loss": 0.8507, + "step": 9552 + }, + { + "epoch": 0.5864513950704442, + "grad_norm": 0.7950977834639842, + "learning_rate": 7.706168236011099e-06, + "loss": 0.8139, + "step": 9553 + }, + { + "epoch": 0.5865127843089106, + "grad_norm": 0.8787426370222975, + "learning_rate": 7.704232948547544e-06, + "loss": 0.8791, + "step": 9554 + }, + { + "epoch": 0.5865741735473772, + "grad_norm": 0.8402442921071395, + "learning_rate": 7.702297751847938e-06, + "loss": 0.8237, + "step": 9555 + }, + { + "epoch": 0.5866355627858436, + "grad_norm": 0.8205999304675688, + "learning_rate": 7.700362645988792e-06, + "loss": 0.8397, + "step": 9556 + }, + { + "epoch": 0.5866969520243102, + "grad_norm": 0.8639981108465097, + "learning_rate": 7.698427631046608e-06, + "loss": 0.7036, + "step": 9557 + }, + { + "epoch": 0.5867583412627766, + "grad_norm": 0.8603763600727967, + "learning_rate": 7.69649270709789e-06, + "loss": 0.7965, + "step": 9558 + }, + { + "epoch": 0.5868197305012431, + "grad_norm": 0.940885532992849, + "learning_rate": 7.694557874219139e-06, + "loss": 0.8204, + "step": 9559 + }, + { + "epoch": 0.5868811197397096, + "grad_norm": 0.8595729670572244, + "learning_rate": 7.692623132486844e-06, + "loss": 0.8729, + "step": 9560 + }, + { + "epoch": 0.5869425089781761, + "grad_norm": 0.7905387854415753, + "learning_rate": 7.690688481977493e-06, + "loss": 0.8126, + "step": 9561 + }, + { + "epoch": 0.5870038982166427, + "grad_norm": 0.8412830624558845, + "learning_rate": 7.68875392276758e-06, + "loss": 0.7525, + "step": 9562 + }, + { + "epoch": 0.5870652874551091, + "grad_norm": 0.8396447806200319, + "learning_rate": 7.686819454933584e-06, + "loss": 0.8158, + "step": 9563 + }, + { + "epoch": 0.5871266766935757, + "grad_norm": 0.8642933851823794, + "learning_rate": 7.684885078551991e-06, + "loss": 0.8565, + "step": 9564 + }, + { + "epoch": 0.5871880659320421, + "grad_norm": 0.8569383664447913, + "learning_rate": 7.682950793699271e-06, + "loss": 0.846, + "step": 9565 + }, + { + "epoch": 0.5872494551705086, + "grad_norm": 0.8942183279809532, + "learning_rate": 7.681016600451897e-06, + "loss": 0.8231, + "step": 9566 + }, + { + "epoch": 0.5873108444089751, + "grad_norm": 0.8352352621631426, + "learning_rate": 7.679082498886341e-06, + "loss": 0.8436, + "step": 9567 + }, + { + "epoch": 0.5873722336474416, + "grad_norm": 0.8874720559736639, + "learning_rate": 7.677148489079064e-06, + "loss": 0.7859, + "step": 9568 + }, + { + "epoch": 0.5874336228859081, + "grad_norm": 0.7901160581868412, + "learning_rate": 7.675214571106538e-06, + "loss": 0.8191, + "step": 9569 + }, + { + "epoch": 0.5874950121243746, + "grad_norm": 0.8630812330231307, + "learning_rate": 7.673280745045208e-06, + "loss": 0.8088, + "step": 9570 + }, + { + "epoch": 0.587556401362841, + "grad_norm": 0.8872377875929063, + "learning_rate": 7.671347010971536e-06, + "loss": 0.8592, + "step": 9571 + }, + { + "epoch": 0.5876177906013076, + "grad_norm": 0.7631585609475532, + "learning_rate": 7.66941336896197e-06, + "loss": 0.7784, + "step": 9572 + }, + { + "epoch": 0.5876791798397741, + "grad_norm": 0.8242050705729106, + "learning_rate": 7.66747981909296e-06, + "loss": 0.8491, + "step": 9573 + }, + { + "epoch": 0.5877405690782406, + "grad_norm": 0.7782862648392525, + "learning_rate": 7.66554636144095e-06, + "loss": 0.7903, + "step": 9574 + }, + { + "epoch": 0.5878019583167071, + "grad_norm": 0.8246092611548957, + "learning_rate": 7.663612996082372e-06, + "loss": 0.809, + "step": 9575 + }, + { + "epoch": 0.5878633475551736, + "grad_norm": 0.8993796289025567, + "learning_rate": 7.661679723093673e-06, + "loss": 0.8283, + "step": 9576 + }, + { + "epoch": 0.5879247367936401, + "grad_norm": 0.891854664497923, + "learning_rate": 7.659746542551275e-06, + "loss": 0.7881, + "step": 9577 + }, + { + "epoch": 0.5879861260321065, + "grad_norm": 0.817255806391117, + "learning_rate": 7.657813454531619e-06, + "loss": 0.7728, + "step": 9578 + }, + { + "epoch": 0.5880475152705731, + "grad_norm": 0.859979014223842, + "learning_rate": 7.655880459111123e-06, + "loss": 0.8514, + "step": 9579 + }, + { + "epoch": 0.5881089045090395, + "grad_norm": 0.890180314024258, + "learning_rate": 7.653947556366207e-06, + "loss": 0.7726, + "step": 9580 + }, + { + "epoch": 0.5881702937475061, + "grad_norm": 0.8741974409202268, + "learning_rate": 7.652014746373292e-06, + "loss": 0.7991, + "step": 9581 + }, + { + "epoch": 0.5882316829859725, + "grad_norm": 0.7506222741344322, + "learning_rate": 7.650082029208793e-06, + "loss": 0.7812, + "step": 9582 + }, + { + "epoch": 0.588293072224439, + "grad_norm": 0.8784143795755979, + "learning_rate": 7.64814940494912e-06, + "loss": 0.8253, + "step": 9583 + }, + { + "epoch": 0.5883544614629056, + "grad_norm": 0.8885536491928413, + "learning_rate": 7.646216873670682e-06, + "loss": 0.7815, + "step": 9584 + }, + { + "epoch": 0.588415850701372, + "grad_norm": 0.9270058853395367, + "learning_rate": 7.644284435449877e-06, + "loss": 0.8261, + "step": 9585 + }, + { + "epoch": 0.5884772399398386, + "grad_norm": 0.8199109174146302, + "learning_rate": 7.642352090363105e-06, + "loss": 0.7626, + "step": 9586 + }, + { + "epoch": 0.588538629178305, + "grad_norm": 0.7773225428575976, + "learning_rate": 7.640419838486769e-06, + "loss": 0.7627, + "step": 9587 + }, + { + "epoch": 0.5886000184167716, + "grad_norm": 0.8549080698192743, + "learning_rate": 7.638487679897252e-06, + "loss": 0.8292, + "step": 9588 + }, + { + "epoch": 0.588661407655238, + "grad_norm": 0.8517734475241046, + "learning_rate": 7.636555614670953e-06, + "loss": 0.8032, + "step": 9589 + }, + { + "epoch": 0.5887227968937045, + "grad_norm": 0.8793291789204526, + "learning_rate": 7.634623642884249e-06, + "loss": 0.8534, + "step": 9590 + }, + { + "epoch": 0.588784186132171, + "grad_norm": 0.848160746986689, + "learning_rate": 7.63269176461352e-06, + "loss": 0.7824, + "step": 9591 + }, + { + "epoch": 0.5888455753706375, + "grad_norm": 0.8602086230603532, + "learning_rate": 7.63075997993515e-06, + "loss": 0.799, + "step": 9592 + }, + { + "epoch": 0.5889069646091041, + "grad_norm": 0.829079805915306, + "learning_rate": 7.628828288925507e-06, + "loss": 0.8051, + "step": 9593 + }, + { + "epoch": 0.5889683538475705, + "grad_norm": 0.7582679083895191, + "learning_rate": 7.626896691660969e-06, + "loss": 0.7884, + "step": 9594 + }, + { + "epoch": 0.5890297430860371, + "grad_norm": 0.7695875362290633, + "learning_rate": 7.6249651882178935e-06, + "loss": 0.8074, + "step": 9595 + }, + { + "epoch": 0.5890911323245035, + "grad_norm": 0.8355867765316994, + "learning_rate": 7.623033778672645e-06, + "loss": 0.7966, + "step": 9596 + }, + { + "epoch": 0.58915252156297, + "grad_norm": 0.8033784867404808, + "learning_rate": 7.621102463101586e-06, + "loss": 0.7466, + "step": 9597 + }, + { + "epoch": 0.5892139108014365, + "grad_norm": 0.8477513674029336, + "learning_rate": 7.619171241581068e-06, + "loss": 0.7907, + "step": 9598 + }, + { + "epoch": 0.589275300039903, + "grad_norm": 0.8991953756427412, + "learning_rate": 7.617240114187452e-06, + "loss": 0.8088, + "step": 9599 + }, + { + "epoch": 0.5893366892783695, + "grad_norm": 0.940347773622032, + "learning_rate": 7.61530908099707e-06, + "loss": 0.8228, + "step": 9600 + }, + { + "epoch": 0.589398078516836, + "grad_norm": 0.9259048477244596, + "learning_rate": 7.6133781420862774e-06, + "loss": 0.8624, + "step": 9601 + }, + { + "epoch": 0.5894594677553024, + "grad_norm": 0.8699976523558054, + "learning_rate": 7.6114472975314094e-06, + "loss": 0.7736, + "step": 9602 + }, + { + "epoch": 0.589520856993769, + "grad_norm": 0.8344122908403067, + "learning_rate": 7.609516547408805e-06, + "loss": 0.7992, + "step": 9603 + }, + { + "epoch": 0.5895822462322355, + "grad_norm": 0.7411341040814413, + "learning_rate": 7.607585891794799e-06, + "loss": 0.8194, + "step": 9604 + }, + { + "epoch": 0.589643635470702, + "grad_norm": 0.9613586586238604, + "learning_rate": 7.605655330765716e-06, + "loss": 0.8347, + "step": 9605 + }, + { + "epoch": 0.5897050247091685, + "grad_norm": 0.8220635472769875, + "learning_rate": 7.603724864397885e-06, + "loss": 0.7808, + "step": 9606 + }, + { + "epoch": 0.589766413947635, + "grad_norm": 0.9127666572490265, + "learning_rate": 7.601794492767625e-06, + "loss": 0.8096, + "step": 9607 + }, + { + "epoch": 0.5898278031861015, + "grad_norm": 0.7426651793799035, + "learning_rate": 7.599864215951257e-06, + "loss": 0.7759, + "step": 9608 + }, + { + "epoch": 0.5898891924245679, + "grad_norm": 0.8522792569888089, + "learning_rate": 7.597934034025093e-06, + "loss": 0.8194, + "step": 9609 + }, + { + "epoch": 0.5899505816630345, + "grad_norm": 0.9805700098671517, + "learning_rate": 7.5960039470654416e-06, + "loss": 0.821, + "step": 9610 + }, + { + "epoch": 0.5900119709015009, + "grad_norm": 0.8873018624860318, + "learning_rate": 7.594073955148613e-06, + "loss": 0.7567, + "step": 9611 + }, + { + "epoch": 0.5900733601399675, + "grad_norm": 0.8821021490531918, + "learning_rate": 7.59214405835091e-06, + "loss": 0.8292, + "step": 9612 + }, + { + "epoch": 0.5901347493784339, + "grad_norm": 0.7544538949897412, + "learning_rate": 7.590214256748631e-06, + "loss": 0.7762, + "step": 9613 + }, + { + "epoch": 0.5901961386169005, + "grad_norm": 0.9319757931080804, + "learning_rate": 7.588284550418068e-06, + "loss": 0.7951, + "step": 9614 + }, + { + "epoch": 0.590257527855367, + "grad_norm": 0.920980363571181, + "learning_rate": 7.586354939435516e-06, + "loss": 0.85, + "step": 9615 + }, + { + "epoch": 0.5903189170938334, + "grad_norm": 0.8737445760220698, + "learning_rate": 7.584425423877262e-06, + "loss": 0.8107, + "step": 9616 + }, + { + "epoch": 0.5903803063323, + "grad_norm": 0.9966402831140468, + "learning_rate": 7.5824960038195915e-06, + "loss": 0.8345, + "step": 9617 + }, + { + "epoch": 0.5904416955707664, + "grad_norm": 0.8468771586734976, + "learning_rate": 7.580566679338787e-06, + "loss": 0.7888, + "step": 9618 + }, + { + "epoch": 0.590503084809233, + "grad_norm": 0.7852359309518369, + "learning_rate": 7.578637450511116e-06, + "loss": 0.7834, + "step": 9619 + }, + { + "epoch": 0.5905644740476994, + "grad_norm": 0.8980602005286584, + "learning_rate": 7.576708317412859e-06, + "loss": 0.7753, + "step": 9620 + }, + { + "epoch": 0.590625863286166, + "grad_norm": 0.9168583342644202, + "learning_rate": 7.574779280120281e-06, + "loss": 0.8408, + "step": 9621 + }, + { + "epoch": 0.5906872525246324, + "grad_norm": 0.7389971081456712, + "learning_rate": 7.572850338709652e-06, + "loss": 0.8105, + "step": 9622 + }, + { + "epoch": 0.5907486417630989, + "grad_norm": 0.762778743508985, + "learning_rate": 7.570921493257233e-06, + "loss": 0.8104, + "step": 9623 + }, + { + "epoch": 0.5908100310015654, + "grad_norm": 0.8588304575875587, + "learning_rate": 7.568992743839275e-06, + "loss": 0.7928, + "step": 9624 + }, + { + "epoch": 0.5908714202400319, + "grad_norm": 0.7409799405288161, + "learning_rate": 7.567064090532035e-06, + "loss": 0.8081, + "step": 9625 + }, + { + "epoch": 0.5909328094784985, + "grad_norm": 0.8272673333533833, + "learning_rate": 7.565135533411766e-06, + "loss": 0.7847, + "step": 9626 + }, + { + "epoch": 0.5909941987169649, + "grad_norm": 0.8547418575644132, + "learning_rate": 7.563207072554709e-06, + "loss": 0.7658, + "step": 9627 + }, + { + "epoch": 0.5910555879554314, + "grad_norm": 0.9471916310678146, + "learning_rate": 7.561278708037114e-06, + "loss": 0.7951, + "step": 9628 + }, + { + "epoch": 0.5911169771938979, + "grad_norm": 0.8036905128734245, + "learning_rate": 7.559350439935213e-06, + "loss": 0.81, + "step": 9629 + }, + { + "epoch": 0.5911783664323644, + "grad_norm": 0.8556730327446413, + "learning_rate": 7.557422268325239e-06, + "loss": 0.8251, + "step": 9630 + }, + { + "epoch": 0.5912397556708309, + "grad_norm": 0.7739781412630639, + "learning_rate": 7.55549419328343e-06, + "loss": 0.7405, + "step": 9631 + }, + { + "epoch": 0.5913011449092974, + "grad_norm": 0.9223925655365005, + "learning_rate": 7.553566214886008e-06, + "loss": 0.865, + "step": 9632 + }, + { + "epoch": 0.5913625341477639, + "grad_norm": 0.865163258097281, + "learning_rate": 7.551638333209202e-06, + "loss": 0.8262, + "step": 9633 + }, + { + "epoch": 0.5914239233862304, + "grad_norm": 0.8971662974326321, + "learning_rate": 7.549710548329224e-06, + "loss": 0.8288, + "step": 9634 + }, + { + "epoch": 0.591485312624697, + "grad_norm": 0.8143657909076472, + "learning_rate": 7.547782860322293e-06, + "loss": 0.8194, + "step": 9635 + }, + { + "epoch": 0.5915467018631634, + "grad_norm": 0.8692542565760681, + "learning_rate": 7.545855269264621e-06, + "loss": 0.808, + "step": 9636 + }, + { + "epoch": 0.5916080911016299, + "grad_norm": 0.9321628675158581, + "learning_rate": 7.543927775232414e-06, + "loss": 0.8937, + "step": 9637 + }, + { + "epoch": 0.5916694803400964, + "grad_norm": 0.9617065029636448, + "learning_rate": 7.542000378301886e-06, + "loss": 0.772, + "step": 9638 + }, + { + "epoch": 0.5917308695785629, + "grad_norm": 0.9335746248703516, + "learning_rate": 7.540073078549221e-06, + "loss": 0.8163, + "step": 9639 + }, + { + "epoch": 0.5917922588170293, + "grad_norm": 0.8394811609910723, + "learning_rate": 7.538145876050628e-06, + "loss": 0.8204, + "step": 9640 + }, + { + "epoch": 0.5918536480554959, + "grad_norm": 0.874850057716661, + "learning_rate": 7.5362187708822924e-06, + "loss": 0.8158, + "step": 9641 + }, + { + "epoch": 0.5919150372939623, + "grad_norm": 0.7775946112512477, + "learning_rate": 7.534291763120407e-06, + "loss": 0.7898, + "step": 9642 + }, + { + "epoch": 0.5919764265324289, + "grad_norm": 0.8911715725008298, + "learning_rate": 7.53236485284116e-06, + "loss": 0.8278, + "step": 9643 + }, + { + "epoch": 0.5920378157708953, + "grad_norm": 0.8047924794785144, + "learning_rate": 7.530438040120722e-06, + "loss": 0.8296, + "step": 9644 + }, + { + "epoch": 0.5920992050093619, + "grad_norm": 0.8007940310367319, + "learning_rate": 7.528511325035279e-06, + "loss": 0.8077, + "step": 9645 + }, + { + "epoch": 0.5921605942478284, + "grad_norm": 0.8961627464954186, + "learning_rate": 7.526584707661001e-06, + "loss": 0.8233, + "step": 9646 + }, + { + "epoch": 0.5922219834862948, + "grad_norm": 0.9001355755664593, + "learning_rate": 7.524658188074059e-06, + "loss": 0.7942, + "step": 9647 + }, + { + "epoch": 0.5922833727247614, + "grad_norm": 0.9258626009097788, + "learning_rate": 7.52273176635062e-06, + "loss": 0.7522, + "step": 9648 + }, + { + "epoch": 0.5923447619632278, + "grad_norm": 0.8352854880056567, + "learning_rate": 7.5208054425668405e-06, + "loss": 0.7835, + "step": 9649 + }, + { + "epoch": 0.5924061512016944, + "grad_norm": 0.8907952910354207, + "learning_rate": 7.5188792167988835e-06, + "loss": 0.7934, + "step": 9650 + }, + { + "epoch": 0.5924675404401608, + "grad_norm": 0.8983732618723507, + "learning_rate": 7.5169530891229e-06, + "loss": 0.8292, + "step": 9651 + }, + { + "epoch": 0.5925289296786274, + "grad_norm": 0.8105574727901598, + "learning_rate": 7.51502705961504e-06, + "loss": 0.8238, + "step": 9652 + }, + { + "epoch": 0.5925903189170938, + "grad_norm": 0.8583212417880413, + "learning_rate": 7.513101128351454e-06, + "loss": 0.8305, + "step": 9653 + }, + { + "epoch": 0.5926517081555603, + "grad_norm": 0.9034048435133746, + "learning_rate": 7.511175295408279e-06, + "loss": 0.8336, + "step": 9654 + }, + { + "epoch": 0.5927130973940268, + "grad_norm": 0.9512505282235884, + "learning_rate": 7.5092495608616555e-06, + "loss": 0.7859, + "step": 9655 + }, + { + "epoch": 0.5927744866324933, + "grad_norm": 0.9205694763297806, + "learning_rate": 7.5073239247877195e-06, + "loss": 0.8346, + "step": 9656 + }, + { + "epoch": 0.5928358758709599, + "grad_norm": 0.8512229505151471, + "learning_rate": 7.505398387262598e-06, + "loss": 0.8176, + "step": 9657 + }, + { + "epoch": 0.5928972651094263, + "grad_norm": 0.8513564006186741, + "learning_rate": 7.503472948362425e-06, + "loss": 0.8462, + "step": 9658 + }, + { + "epoch": 0.5929586543478929, + "grad_norm": 0.8567307794586188, + "learning_rate": 7.501547608163316e-06, + "loss": 0.8437, + "step": 9659 + }, + { + "epoch": 0.5930200435863593, + "grad_norm": 0.8191761258352918, + "learning_rate": 7.499622366741391e-06, + "loss": 0.8386, + "step": 9660 + }, + { + "epoch": 0.5930814328248258, + "grad_norm": 0.8574665575413707, + "learning_rate": 7.49769722417277e-06, + "loss": 0.7953, + "step": 9661 + }, + { + "epoch": 0.5931428220632923, + "grad_norm": 0.9183601692198579, + "learning_rate": 7.4957721805335585e-06, + "loss": 0.8224, + "step": 9662 + }, + { + "epoch": 0.5932042113017588, + "grad_norm": 0.8444013663012359, + "learning_rate": 7.493847235899871e-06, + "loss": 0.7657, + "step": 9663 + }, + { + "epoch": 0.5932656005402253, + "grad_norm": 0.8149908415372307, + "learning_rate": 7.491922390347801e-06, + "loss": 0.8172, + "step": 9664 + }, + { + "epoch": 0.5933269897786918, + "grad_norm": 0.8583998209692448, + "learning_rate": 7.489997643953455e-06, + "loss": 0.8385, + "step": 9665 + }, + { + "epoch": 0.5933883790171582, + "grad_norm": 0.8052771763914613, + "learning_rate": 7.488072996792923e-06, + "loss": 0.7974, + "step": 9666 + }, + { + "epoch": 0.5934497682556248, + "grad_norm": 0.8899589922591079, + "learning_rate": 7.486148448942305e-06, + "loss": 0.8195, + "step": 9667 + }, + { + "epoch": 0.5935111574940913, + "grad_norm": 0.813666328623889, + "learning_rate": 7.484224000477684e-06, + "loss": 0.8045, + "step": 9668 + }, + { + "epoch": 0.5935725467325578, + "grad_norm": 0.8384535264623646, + "learning_rate": 7.48229965147514e-06, + "loss": 0.7982, + "step": 9669 + }, + { + "epoch": 0.5936339359710243, + "grad_norm": 0.9780073829555681, + "learning_rate": 7.480375402010758e-06, + "loss": 0.7826, + "step": 9670 + }, + { + "epoch": 0.5936953252094908, + "grad_norm": 0.9045857159804439, + "learning_rate": 7.478451252160611e-06, + "loss": 0.8234, + "step": 9671 + }, + { + "epoch": 0.5937567144479573, + "grad_norm": 0.8165285226865169, + "learning_rate": 7.476527202000774e-06, + "loss": 0.7532, + "step": 9672 + }, + { + "epoch": 0.5938181036864237, + "grad_norm": 0.794447420874295, + "learning_rate": 7.4746032516073154e-06, + "loss": 0.7917, + "step": 9673 + }, + { + "epoch": 0.5938794929248903, + "grad_norm": 0.8705486506472915, + "learning_rate": 7.472679401056293e-06, + "loss": 0.8, + "step": 9674 + }, + { + "epoch": 0.5939408821633567, + "grad_norm": 0.9168468027189364, + "learning_rate": 7.470755650423772e-06, + "loss": 0.8276, + "step": 9675 + }, + { + "epoch": 0.5940022714018233, + "grad_norm": 0.8214048745656051, + "learning_rate": 7.468831999785809e-06, + "loss": 0.7786, + "step": 9676 + }, + { + "epoch": 0.5940636606402897, + "grad_norm": 0.8757063989242265, + "learning_rate": 7.466908449218455e-06, + "loss": 0.8256, + "step": 9677 + }, + { + "epoch": 0.5941250498787563, + "grad_norm": 0.7875995340755062, + "learning_rate": 7.464984998797755e-06, + "loss": 0.8227, + "step": 9678 + }, + { + "epoch": 0.5941864391172228, + "grad_norm": 0.8638900796805477, + "learning_rate": 7.463061648599757e-06, + "loss": 0.8104, + "step": 9679 + }, + { + "epoch": 0.5942478283556892, + "grad_norm": 0.9064452746823988, + "learning_rate": 7.461138398700501e-06, + "loss": 0.8152, + "step": 9680 + }, + { + "epoch": 0.5943092175941558, + "grad_norm": 0.8249030261047684, + "learning_rate": 7.459215249176021e-06, + "loss": 0.8329, + "step": 9681 + }, + { + "epoch": 0.5943706068326222, + "grad_norm": 0.9063648908736028, + "learning_rate": 7.457292200102357e-06, + "loss": 0.8282, + "step": 9682 + }, + { + "epoch": 0.5944319960710888, + "grad_norm": 0.8691268503682409, + "learning_rate": 7.455369251555527e-06, + "loss": 0.816, + "step": 9683 + }, + { + "epoch": 0.5944933853095552, + "grad_norm": 0.8114605549102415, + "learning_rate": 7.453446403611561e-06, + "loss": 0.8338, + "step": 9684 + }, + { + "epoch": 0.5945547745480217, + "grad_norm": 0.8941846118489777, + "learning_rate": 7.451523656346476e-06, + "loss": 0.8341, + "step": 9685 + }, + { + "epoch": 0.5946161637864882, + "grad_norm": 0.8244204113035195, + "learning_rate": 7.449601009836295e-06, + "loss": 0.8005, + "step": 9686 + }, + { + "epoch": 0.5946775530249547, + "grad_norm": 0.778373151909993, + "learning_rate": 7.447678464157028e-06, + "loss": 0.7859, + "step": 9687 + }, + { + "epoch": 0.5947389422634213, + "grad_norm": 0.830876047597177, + "learning_rate": 7.44575601938468e-06, + "loss": 0.8024, + "step": 9688 + }, + { + "epoch": 0.5948003315018877, + "grad_norm": 0.8219484673671318, + "learning_rate": 7.443833675595254e-06, + "loss": 0.8205, + "step": 9689 + }, + { + "epoch": 0.5948617207403543, + "grad_norm": 0.8411960708182151, + "learning_rate": 7.441911432864758e-06, + "loss": 0.8051, + "step": 9690 + }, + { + "epoch": 0.5949231099788207, + "grad_norm": 0.8457727470314648, + "learning_rate": 7.439989291269183e-06, + "loss": 0.7992, + "step": 9691 + }, + { + "epoch": 0.5949844992172872, + "grad_norm": 0.8078442301459585, + "learning_rate": 7.438067250884526e-06, + "loss": 0.8077, + "step": 9692 + }, + { + "epoch": 0.5950458884557537, + "grad_norm": 0.8356066964603648, + "learning_rate": 7.436145311786771e-06, + "loss": 0.8095, + "step": 9693 + }, + { + "epoch": 0.5951072776942202, + "grad_norm": 0.9012744992942584, + "learning_rate": 7.434223474051903e-06, + "loss": 0.8181, + "step": 9694 + }, + { + "epoch": 0.5951686669326867, + "grad_norm": 0.8279157800757766, + "learning_rate": 7.432301737755905e-06, + "loss": 0.7794, + "step": 9695 + }, + { + "epoch": 0.5952300561711532, + "grad_norm": 0.8725625377763977, + "learning_rate": 7.43038010297475e-06, + "loss": 0.871, + "step": 9696 + }, + { + "epoch": 0.5952914454096196, + "grad_norm": 0.906830477149632, + "learning_rate": 7.428458569784418e-06, + "loss": 0.8274, + "step": 9697 + }, + { + "epoch": 0.5953528346480862, + "grad_norm": 0.8308499492627197, + "learning_rate": 7.42653713826087e-06, + "loss": 0.8294, + "step": 9698 + }, + { + "epoch": 0.5954142238865527, + "grad_norm": 0.9075191182689977, + "learning_rate": 7.424615808480069e-06, + "loss": 0.8203, + "step": 9699 + }, + { + "epoch": 0.5954756131250192, + "grad_norm": 0.8790580424090926, + "learning_rate": 7.422694580517984e-06, + "loss": 0.8065, + "step": 9700 + }, + { + "epoch": 0.5955370023634857, + "grad_norm": 0.9128476007022174, + "learning_rate": 7.420773454450563e-06, + "loss": 0.838, + "step": 9701 + }, + { + "epoch": 0.5955983916019522, + "grad_norm": 0.8040128949598926, + "learning_rate": 7.418852430353769e-06, + "loss": 0.7913, + "step": 9702 + }, + { + "epoch": 0.5956597808404187, + "grad_norm": 0.9430307361446414, + "learning_rate": 7.4169315083035356e-06, + "loss": 0.8192, + "step": 9703 + }, + { + "epoch": 0.5957211700788851, + "grad_norm": 0.9054463683093852, + "learning_rate": 7.415010688375819e-06, + "loss": 0.8089, + "step": 9704 + }, + { + "epoch": 0.5957825593173517, + "grad_norm": 0.8902240657090625, + "learning_rate": 7.413089970646552e-06, + "loss": 0.7694, + "step": 9705 + }, + { + "epoch": 0.5958439485558181, + "grad_norm": 0.8268964972274263, + "learning_rate": 7.411169355191676e-06, + "loss": 0.8079, + "step": 9706 + }, + { + "epoch": 0.5959053377942847, + "grad_norm": 0.8682793847695872, + "learning_rate": 7.409248842087124e-06, + "loss": 0.7961, + "step": 9707 + }, + { + "epoch": 0.5959667270327511, + "grad_norm": 0.8481833792527919, + "learning_rate": 7.407328431408818e-06, + "loss": 0.801, + "step": 9708 + }, + { + "epoch": 0.5960281162712177, + "grad_norm": 0.7915912250135202, + "learning_rate": 7.405408123232687e-06, + "loss": 0.7308, + "step": 9709 + }, + { + "epoch": 0.5960895055096842, + "grad_norm": 0.9108981074438403, + "learning_rate": 7.403487917634648e-06, + "loss": 0.825, + "step": 9710 + }, + { + "epoch": 0.5961508947481506, + "grad_norm": 0.9043997519161814, + "learning_rate": 7.4015678146906215e-06, + "loss": 0.7906, + "step": 9711 + }, + { + "epoch": 0.5962122839866172, + "grad_norm": 0.8943368462752842, + "learning_rate": 7.399647814476518e-06, + "loss": 0.7961, + "step": 9712 + }, + { + "epoch": 0.5962736732250836, + "grad_norm": 0.854048128719259, + "learning_rate": 7.39772791706824e-06, + "loss": 0.7964, + "step": 9713 + }, + { + "epoch": 0.5963350624635502, + "grad_norm": 0.8811281475610957, + "learning_rate": 7.395808122541697e-06, + "loss": 0.7732, + "step": 9714 + }, + { + "epoch": 0.5963964517020166, + "grad_norm": 0.8107425621698259, + "learning_rate": 7.393888430972788e-06, + "loss": 0.8355, + "step": 9715 + }, + { + "epoch": 0.5964578409404832, + "grad_norm": 0.9378113929575586, + "learning_rate": 7.391968842437404e-06, + "loss": 0.8223, + "step": 9716 + }, + { + "epoch": 0.5965192301789496, + "grad_norm": 0.8872181961961867, + "learning_rate": 7.3900493570114466e-06, + "loss": 0.7845, + "step": 9717 + }, + { + "epoch": 0.5965806194174161, + "grad_norm": 0.8578656998614055, + "learning_rate": 7.388129974770795e-06, + "loss": 0.7869, + "step": 9718 + }, + { + "epoch": 0.5966420086558826, + "grad_norm": 0.9300475303575484, + "learning_rate": 7.386210695791331e-06, + "loss": 0.847, + "step": 9719 + }, + { + "epoch": 0.5967033978943491, + "grad_norm": 0.7888144662656191, + "learning_rate": 7.384291520148941e-06, + "loss": 0.8036, + "step": 9720 + }, + { + "epoch": 0.5967647871328157, + "grad_norm": 0.5707149860813905, + "learning_rate": 7.3823724479194944e-06, + "loss": 0.6459, + "step": 9721 + }, + { + "epoch": 0.5968261763712821, + "grad_norm": 0.7776819861962284, + "learning_rate": 7.38045347917887e-06, + "loss": 0.7675, + "step": 9722 + }, + { + "epoch": 0.5968875656097486, + "grad_norm": 0.8372427414376782, + "learning_rate": 7.378534614002926e-06, + "loss": 0.7841, + "step": 9723 + }, + { + "epoch": 0.5969489548482151, + "grad_norm": 0.8753029631690595, + "learning_rate": 7.376615852467529e-06, + "loss": 0.783, + "step": 9724 + }, + { + "epoch": 0.5970103440866816, + "grad_norm": 0.8297975766186789, + "learning_rate": 7.374697194648539e-06, + "loss": 0.8389, + "step": 9725 + }, + { + "epoch": 0.5970717333251481, + "grad_norm": 0.9697782961495304, + "learning_rate": 7.372778640621809e-06, + "loss": 0.8133, + "step": 9726 + }, + { + "epoch": 0.5971331225636146, + "grad_norm": 0.9188473501970673, + "learning_rate": 7.370860190463196e-06, + "loss": 0.785, + "step": 9727 + }, + { + "epoch": 0.597194511802081, + "grad_norm": 0.8687729279999524, + "learning_rate": 7.368941844248536e-06, + "loss": 0.8308, + "step": 9728 + }, + { + "epoch": 0.5972559010405476, + "grad_norm": 1.0444503694640073, + "learning_rate": 7.367023602053679e-06, + "loss": 0.8526, + "step": 9729 + }, + { + "epoch": 0.597317290279014, + "grad_norm": 0.8773473037712377, + "learning_rate": 7.365105463954459e-06, + "loss": 0.7905, + "step": 9730 + }, + { + "epoch": 0.5973786795174806, + "grad_norm": 0.8771556733073486, + "learning_rate": 7.3631874300267125e-06, + "loss": 0.7789, + "step": 9731 + }, + { + "epoch": 0.5974400687559471, + "grad_norm": 0.9215797892522523, + "learning_rate": 7.361269500346274e-06, + "loss": 0.7977, + "step": 9732 + }, + { + "epoch": 0.5975014579944136, + "grad_norm": 0.8958722521404464, + "learning_rate": 7.359351674988959e-06, + "loss": 0.7673, + "step": 9733 + }, + { + "epoch": 0.5975628472328801, + "grad_norm": 0.9201241199729102, + "learning_rate": 7.357433954030599e-06, + "loss": 0.7837, + "step": 9734 + }, + { + "epoch": 0.5976242364713465, + "grad_norm": 0.9779800808104687, + "learning_rate": 7.355516337547006e-06, + "loss": 0.7924, + "step": 9735 + }, + { + "epoch": 0.5976856257098131, + "grad_norm": 0.8138868478212059, + "learning_rate": 7.353598825613999e-06, + "loss": 0.8136, + "step": 9736 + }, + { + "epoch": 0.5977470149482795, + "grad_norm": 0.8922305033714615, + "learning_rate": 7.351681418307384e-06, + "loss": 0.8025, + "step": 9737 + }, + { + "epoch": 0.5978084041867461, + "grad_norm": 0.8777678174432424, + "learning_rate": 7.349764115702964e-06, + "loss": 0.8214, + "step": 9738 + }, + { + "epoch": 0.5978697934252125, + "grad_norm": 0.8498325402613421, + "learning_rate": 7.3478469178765444e-06, + "loss": 0.8463, + "step": 9739 + }, + { + "epoch": 0.5979311826636791, + "grad_norm": 0.8935638441384363, + "learning_rate": 7.345929824903919e-06, + "loss": 0.8085, + "step": 9740 + }, + { + "epoch": 0.5979925719021456, + "grad_norm": 0.7811970989041743, + "learning_rate": 7.3440128368608894e-06, + "loss": 0.8136, + "step": 9741 + }, + { + "epoch": 0.598053961140612, + "grad_norm": 0.8060546433638235, + "learning_rate": 7.342095953823232e-06, + "loss": 0.7964, + "step": 9742 + }, + { + "epoch": 0.5981153503790786, + "grad_norm": 0.8479537398462809, + "learning_rate": 7.3401791758667375e-06, + "loss": 0.7492, + "step": 9743 + }, + { + "epoch": 0.598176739617545, + "grad_norm": 0.9219304224598207, + "learning_rate": 7.338262503067184e-06, + "loss": 0.7903, + "step": 9744 + }, + { + "epoch": 0.5982381288560116, + "grad_norm": 0.9135909828240613, + "learning_rate": 7.336345935500353e-06, + "loss": 0.7593, + "step": 9745 + }, + { + "epoch": 0.598299518094478, + "grad_norm": 0.8882883931051402, + "learning_rate": 7.334429473242014e-06, + "loss": 0.8095, + "step": 9746 + }, + { + "epoch": 0.5983609073329446, + "grad_norm": 0.8447324216205191, + "learning_rate": 7.332513116367931e-06, + "loss": 0.8249, + "step": 9747 + }, + { + "epoch": 0.598422296571411, + "grad_norm": 0.7976676078976979, + "learning_rate": 7.330596864953874e-06, + "loss": 0.8057, + "step": 9748 + }, + { + "epoch": 0.5984836858098775, + "grad_norm": 0.8756245570403499, + "learning_rate": 7.328680719075596e-06, + "loss": 0.8364, + "step": 9749 + }, + { + "epoch": 0.598545075048344, + "grad_norm": 0.7792049532640755, + "learning_rate": 7.32676467880886e-06, + "loss": 0.7929, + "step": 9750 + }, + { + "epoch": 0.5986064642868105, + "grad_norm": 0.9117710586137536, + "learning_rate": 7.324848744229415e-06, + "loss": 0.8211, + "step": 9751 + }, + { + "epoch": 0.5986678535252771, + "grad_norm": 0.9159048731825353, + "learning_rate": 7.322932915413004e-06, + "loss": 0.8494, + "step": 9752 + }, + { + "epoch": 0.5987292427637435, + "grad_norm": 0.8523831721425041, + "learning_rate": 7.321017192435374e-06, + "loss": 0.8379, + "step": 9753 + }, + { + "epoch": 0.59879063200221, + "grad_norm": 0.7940312229278651, + "learning_rate": 7.31910157537226e-06, + "loss": 0.7893, + "step": 9754 + }, + { + "epoch": 0.5988520212406765, + "grad_norm": 0.9886207439025855, + "learning_rate": 7.317186064299401e-06, + "loss": 0.7853, + "step": 9755 + }, + { + "epoch": 0.598913410479143, + "grad_norm": 1.001808943492777, + "learning_rate": 7.315270659292528e-06, + "loss": 0.8507, + "step": 9756 + }, + { + "epoch": 0.5989747997176095, + "grad_norm": 0.8568037945371272, + "learning_rate": 7.313355360427363e-06, + "loss": 0.7886, + "step": 9757 + }, + { + "epoch": 0.599036188956076, + "grad_norm": 0.9030263653649525, + "learning_rate": 7.3114401677796275e-06, + "loss": 0.8102, + "step": 9758 + }, + { + "epoch": 0.5990975781945425, + "grad_norm": 0.9565990694277838, + "learning_rate": 7.309525081425044e-06, + "loss": 0.8066, + "step": 9759 + }, + { + "epoch": 0.599158967433009, + "grad_norm": 0.816841703050126, + "learning_rate": 7.3076101014393215e-06, + "loss": 0.7742, + "step": 9760 + }, + { + "epoch": 0.5992203566714754, + "grad_norm": 0.8825501532157839, + "learning_rate": 7.305695227898175e-06, + "loss": 0.8497, + "step": 9761 + }, + { + "epoch": 0.599281745909942, + "grad_norm": 0.8674910280881014, + "learning_rate": 7.303780460877305e-06, + "loss": 0.7742, + "step": 9762 + }, + { + "epoch": 0.5993431351484085, + "grad_norm": 0.8171228761482208, + "learning_rate": 7.301865800452412e-06, + "loss": 0.8235, + "step": 9763 + }, + { + "epoch": 0.599404524386875, + "grad_norm": 0.9679318056655675, + "learning_rate": 7.299951246699198e-06, + "loss": 0.8519, + "step": 9764 + }, + { + "epoch": 0.5994659136253415, + "grad_norm": 0.8910736775050032, + "learning_rate": 7.298036799693347e-06, + "loss": 0.8226, + "step": 9765 + }, + { + "epoch": 0.599527302863808, + "grad_norm": 0.9005850575054744, + "learning_rate": 7.29612245951056e-06, + "loss": 0.7881, + "step": 9766 + }, + { + "epoch": 0.5995886921022745, + "grad_norm": 0.8703194039123324, + "learning_rate": 7.294208226226507e-06, + "loss": 0.7837, + "step": 9767 + }, + { + "epoch": 0.5996500813407409, + "grad_norm": 0.94259809847688, + "learning_rate": 7.292294099916877e-06, + "loss": 0.8053, + "step": 9768 + }, + { + "epoch": 0.5997114705792075, + "grad_norm": 0.8568576288855, + "learning_rate": 7.29038008065734e-06, + "loss": 0.7738, + "step": 9769 + }, + { + "epoch": 0.5997728598176739, + "grad_norm": 0.8675632583253513, + "learning_rate": 7.288466168523574e-06, + "loss": 0.7622, + "step": 9770 + }, + { + "epoch": 0.5998342490561405, + "grad_norm": 0.9256704292563418, + "learning_rate": 7.286552363591244e-06, + "loss": 0.7936, + "step": 9771 + }, + { + "epoch": 0.5998956382946069, + "grad_norm": 0.877607778435087, + "learning_rate": 7.284638665936008e-06, + "loss": 0.7583, + "step": 9772 + }, + { + "epoch": 0.5999570275330735, + "grad_norm": 0.8348685729661781, + "learning_rate": 7.28272507563353e-06, + "loss": 0.8393, + "step": 9773 + }, + { + "epoch": 0.60001841677154, + "grad_norm": 0.8537352293693563, + "learning_rate": 7.28081159275946e-06, + "loss": 0.7845, + "step": 9774 + }, + { + "epoch": 0.6000798060100064, + "grad_norm": 0.8731773394523776, + "learning_rate": 7.278898217389454e-06, + "loss": 0.7916, + "step": 9775 + }, + { + "epoch": 0.600141195248473, + "grad_norm": 0.7747724863400502, + "learning_rate": 7.276984949599156e-06, + "loss": 0.7993, + "step": 9776 + }, + { + "epoch": 0.6002025844869394, + "grad_norm": 0.7895373647050782, + "learning_rate": 7.275071789464203e-06, + "loss": 0.7635, + "step": 9777 + }, + { + "epoch": 0.600263973725406, + "grad_norm": 0.7959477252412351, + "learning_rate": 7.273158737060238e-06, + "loss": 0.8342, + "step": 9778 + }, + { + "epoch": 0.6003253629638724, + "grad_norm": 0.83151449066072, + "learning_rate": 7.271245792462891e-06, + "loss": 0.8317, + "step": 9779 + }, + { + "epoch": 0.600386752202339, + "grad_norm": 0.8423195283067063, + "learning_rate": 7.269332955747794e-06, + "loss": 0.8067, + "step": 9780 + }, + { + "epoch": 0.6004481414408054, + "grad_norm": 0.9051679790146746, + "learning_rate": 7.2674202269905715e-06, + "loss": 0.7859, + "step": 9781 + }, + { + "epoch": 0.6005095306792719, + "grad_norm": 0.9181055467044942, + "learning_rate": 7.265507606266841e-06, + "loss": 0.8462, + "step": 9782 + }, + { + "epoch": 0.6005709199177384, + "grad_norm": 0.9115007933114517, + "learning_rate": 7.263595093652217e-06, + "loss": 0.8428, + "step": 9783 + }, + { + "epoch": 0.6006323091562049, + "grad_norm": 0.921410747184172, + "learning_rate": 7.261682689222317e-06, + "loss": 0.8309, + "step": 9784 + }, + { + "epoch": 0.6006936983946715, + "grad_norm": 0.9018943413946975, + "learning_rate": 7.259770393052743e-06, + "loss": 0.8206, + "step": 9785 + }, + { + "epoch": 0.6007550876331379, + "grad_norm": 0.8192583383624608, + "learning_rate": 7.257858205219106e-06, + "loss": 0.8365, + "step": 9786 + }, + { + "epoch": 0.6008164768716044, + "grad_norm": 0.8664096261788021, + "learning_rate": 7.255946125796998e-06, + "loss": 0.851, + "step": 9787 + }, + { + "epoch": 0.6008778661100709, + "grad_norm": 0.8195018669365804, + "learning_rate": 7.254034154862013e-06, + "loss": 0.752, + "step": 9788 + }, + { + "epoch": 0.6009392553485374, + "grad_norm": 0.802921752806974, + "learning_rate": 7.252122292489747e-06, + "loss": 0.7691, + "step": 9789 + }, + { + "epoch": 0.6010006445870039, + "grad_norm": 0.8973589270396137, + "learning_rate": 7.250210538755782e-06, + "loss": 0.8311, + "step": 9790 + }, + { + "epoch": 0.6010620338254704, + "grad_norm": 0.8272857027447634, + "learning_rate": 7.248298893735705e-06, + "loss": 0.8243, + "step": 9791 + }, + { + "epoch": 0.6011234230639368, + "grad_norm": 0.8066744363307677, + "learning_rate": 7.246387357505087e-06, + "loss": 0.7756, + "step": 9792 + }, + { + "epoch": 0.6011848123024034, + "grad_norm": 0.8207142807041884, + "learning_rate": 7.244475930139505e-06, + "loss": 0.7818, + "step": 9793 + }, + { + "epoch": 0.6012462015408699, + "grad_norm": 0.8861880876773848, + "learning_rate": 7.242564611714524e-06, + "loss": 0.7733, + "step": 9794 + }, + { + "epoch": 0.6013075907793364, + "grad_norm": 0.8255145663065191, + "learning_rate": 7.2406534023057155e-06, + "loss": 0.7935, + "step": 9795 + }, + { + "epoch": 0.6013689800178029, + "grad_norm": 0.9064841222682228, + "learning_rate": 7.238742301988637e-06, + "loss": 0.8018, + "step": 9796 + }, + { + "epoch": 0.6014303692562694, + "grad_norm": 0.753536738725881, + "learning_rate": 7.23683131083884e-06, + "loss": 0.7846, + "step": 9797 + }, + { + "epoch": 0.6014917584947359, + "grad_norm": 0.82466956479386, + "learning_rate": 7.234920428931882e-06, + "loss": 0.7841, + "step": 9798 + }, + { + "epoch": 0.6015531477332023, + "grad_norm": 0.8480239302947279, + "learning_rate": 7.233009656343304e-06, + "loss": 0.7871, + "step": 9799 + }, + { + "epoch": 0.6016145369716689, + "grad_norm": 0.8696615827409303, + "learning_rate": 7.231098993148658e-06, + "loss": 0.7716, + "step": 9800 + }, + { + "epoch": 0.6016759262101353, + "grad_norm": 0.7610109954867909, + "learning_rate": 7.229188439423478e-06, + "loss": 0.7868, + "step": 9801 + }, + { + "epoch": 0.6017373154486019, + "grad_norm": 0.8123045853304365, + "learning_rate": 7.227277995243295e-06, + "loss": 0.7998, + "step": 9802 + }, + { + "epoch": 0.6017987046870683, + "grad_norm": 0.8323292173156501, + "learning_rate": 7.225367660683644e-06, + "loss": 0.8117, + "step": 9803 + }, + { + "epoch": 0.6018600939255349, + "grad_norm": 0.8280072773850051, + "learning_rate": 7.223457435820047e-06, + "loss": 0.7953, + "step": 9804 + }, + { + "epoch": 0.6019214831640014, + "grad_norm": 0.8616023395557997, + "learning_rate": 7.221547320728035e-06, + "loss": 0.8408, + "step": 9805 + }, + { + "epoch": 0.6019828724024678, + "grad_norm": 0.8859306751184627, + "learning_rate": 7.21963731548311e-06, + "loss": 0.8098, + "step": 9806 + }, + { + "epoch": 0.6020442616409344, + "grad_norm": 0.7026764720514739, + "learning_rate": 7.217727420160796e-06, + "loss": 0.7723, + "step": 9807 + }, + { + "epoch": 0.6021056508794008, + "grad_norm": 0.7847458366647064, + "learning_rate": 7.215817634836595e-06, + "loss": 0.8178, + "step": 9808 + }, + { + "epoch": 0.6021670401178674, + "grad_norm": 0.8516715011453337, + "learning_rate": 7.213907959586015e-06, + "loss": 0.8357, + "step": 9809 + }, + { + "epoch": 0.6022284293563338, + "grad_norm": 0.7613661414534025, + "learning_rate": 7.211998394484556e-06, + "loss": 0.8124, + "step": 9810 + }, + { + "epoch": 0.6022898185948004, + "grad_norm": 0.8413985478128518, + "learning_rate": 7.210088939607709e-06, + "loss": 0.8132, + "step": 9811 + }, + { + "epoch": 0.6023512078332668, + "grad_norm": 0.9254656270037975, + "learning_rate": 7.20817959503097e-06, + "loss": 0.8126, + "step": 9812 + }, + { + "epoch": 0.6024125970717333, + "grad_norm": 0.8474122412475975, + "learning_rate": 7.20627036082982e-06, + "loss": 0.7816, + "step": 9813 + }, + { + "epoch": 0.6024739863101998, + "grad_norm": 0.8359652287391427, + "learning_rate": 7.204361237079746e-06, + "loss": 0.7755, + "step": 9814 + }, + { + "epoch": 0.6025353755486663, + "grad_norm": 0.8942893063797075, + "learning_rate": 7.202452223856229e-06, + "loss": 0.7643, + "step": 9815 + }, + { + "epoch": 0.6025967647871329, + "grad_norm": 0.9040470242456521, + "learning_rate": 7.200543321234732e-06, + "loss": 0.8135, + "step": 9816 + }, + { + "epoch": 0.6026581540255993, + "grad_norm": 0.9095386040419169, + "learning_rate": 7.198634529290733e-06, + "loss": 0.8081, + "step": 9817 + }, + { + "epoch": 0.6027195432640658, + "grad_norm": 0.8545719811080892, + "learning_rate": 7.196725848099691e-06, + "loss": 0.7959, + "step": 9818 + }, + { + "epoch": 0.6027809325025323, + "grad_norm": 0.9011303321636898, + "learning_rate": 7.194817277737072e-06, + "loss": 0.8301, + "step": 9819 + }, + { + "epoch": 0.6028423217409988, + "grad_norm": 0.8957936590069848, + "learning_rate": 7.1929088182783314e-06, + "loss": 0.8004, + "step": 9820 + }, + { + "epoch": 0.6029037109794653, + "grad_norm": 0.8855678263432946, + "learning_rate": 7.1910004697989166e-06, + "loss": 0.8148, + "step": 9821 + }, + { + "epoch": 0.6029651002179318, + "grad_norm": 0.9242152474923108, + "learning_rate": 7.189092232374273e-06, + "loss": 0.8663, + "step": 9822 + }, + { + "epoch": 0.6030264894563983, + "grad_norm": 0.8023306465938438, + "learning_rate": 7.187184106079851e-06, + "loss": 0.7736, + "step": 9823 + }, + { + "epoch": 0.6030878786948648, + "grad_norm": 0.8380132843043446, + "learning_rate": 7.185276090991083e-06, + "loss": 0.7678, + "step": 9824 + }, + { + "epoch": 0.6031492679333312, + "grad_norm": 0.8253871511449586, + "learning_rate": 7.1833681871834085e-06, + "loss": 0.8089, + "step": 9825 + }, + { + "epoch": 0.6032106571717978, + "grad_norm": 0.8707845039092292, + "learning_rate": 7.181460394732254e-06, + "loss": 0.7879, + "step": 9826 + }, + { + "epoch": 0.6032720464102643, + "grad_norm": 0.7806735139315594, + "learning_rate": 7.1795527137130405e-06, + "loss": 0.7531, + "step": 9827 + }, + { + "epoch": 0.6033334356487308, + "grad_norm": 0.7872515114512624, + "learning_rate": 7.177645144201195e-06, + "loss": 0.8186, + "step": 9828 + }, + { + "epoch": 0.6033948248871973, + "grad_norm": 0.93794671958747, + "learning_rate": 7.175737686272131e-06, + "loss": 0.7914, + "step": 9829 + }, + { + "epoch": 0.6034562141256637, + "grad_norm": 0.9168572055357592, + "learning_rate": 7.173830340001266e-06, + "loss": 0.7972, + "step": 9830 + }, + { + "epoch": 0.6035176033641303, + "grad_norm": 0.7780598039547193, + "learning_rate": 7.171923105464001e-06, + "loss": 0.7884, + "step": 9831 + }, + { + "epoch": 0.6035789926025967, + "grad_norm": 0.8233452892461194, + "learning_rate": 7.1700159827357384e-06, + "loss": 0.7696, + "step": 9832 + }, + { + "epoch": 0.6036403818410633, + "grad_norm": 0.8699170628047693, + "learning_rate": 7.1681089718918804e-06, + "loss": 0.7584, + "step": 9833 + }, + { + "epoch": 0.6037017710795297, + "grad_norm": 0.969727290181655, + "learning_rate": 7.166202073007823e-06, + "loss": 0.8617, + "step": 9834 + }, + { + "epoch": 0.6037631603179963, + "grad_norm": 0.8554822930853241, + "learning_rate": 7.164295286158955e-06, + "loss": 0.7955, + "step": 9835 + }, + { + "epoch": 0.6038245495564627, + "grad_norm": 0.8911261809085325, + "learning_rate": 7.162388611420657e-06, + "loss": 0.7658, + "step": 9836 + }, + { + "epoch": 0.6038859387949292, + "grad_norm": 0.900519471316296, + "learning_rate": 7.160482048868316e-06, + "loss": 0.8213, + "step": 9837 + }, + { + "epoch": 0.6039473280333958, + "grad_norm": 0.9041083176685212, + "learning_rate": 7.158575598577304e-06, + "loss": 0.8046, + "step": 9838 + }, + { + "epoch": 0.6040087172718622, + "grad_norm": 0.8365015919486022, + "learning_rate": 7.156669260622997e-06, + "loss": 0.846, + "step": 9839 + }, + { + "epoch": 0.6040701065103288, + "grad_norm": 0.8881783355708552, + "learning_rate": 7.154763035080765e-06, + "loss": 0.7875, + "step": 9840 + }, + { + "epoch": 0.6041314957487952, + "grad_norm": 0.8825340269902091, + "learning_rate": 7.152856922025962e-06, + "loss": 0.8141, + "step": 9841 + }, + { + "epoch": 0.6041928849872618, + "grad_norm": 0.9528926181573844, + "learning_rate": 7.150950921533956e-06, + "loss": 0.7913, + "step": 9842 + }, + { + "epoch": 0.6042542742257282, + "grad_norm": 0.9243126111190233, + "learning_rate": 7.149045033680095e-06, + "loss": 0.7945, + "step": 9843 + }, + { + "epoch": 0.6043156634641947, + "grad_norm": 0.8368441533868667, + "learning_rate": 7.147139258539734e-06, + "loss": 0.7461, + "step": 9844 + }, + { + "epoch": 0.6043770527026612, + "grad_norm": 0.8574610573885322, + "learning_rate": 7.145233596188218e-06, + "loss": 0.7676, + "step": 9845 + }, + { + "epoch": 0.6044384419411277, + "grad_norm": 0.9177447720648412, + "learning_rate": 7.143328046700884e-06, + "loss": 0.8341, + "step": 9846 + }, + { + "epoch": 0.6044998311795943, + "grad_norm": 0.9285780399313773, + "learning_rate": 7.14142261015307e-06, + "loss": 0.8369, + "step": 9847 + }, + { + "epoch": 0.6045612204180607, + "grad_norm": 0.6737352310571014, + "learning_rate": 7.1395172866201105e-06, + "loss": 0.7115, + "step": 9848 + }, + { + "epoch": 0.6046226096565273, + "grad_norm": 0.8168002475666032, + "learning_rate": 7.137612076177329e-06, + "loss": 0.7521, + "step": 9849 + }, + { + "epoch": 0.6046839988949937, + "grad_norm": 0.8247859863574868, + "learning_rate": 7.135706978900055e-06, + "loss": 0.8103, + "step": 9850 + }, + { + "epoch": 0.6047453881334602, + "grad_norm": 0.8897555395541522, + "learning_rate": 7.133801994863603e-06, + "loss": 0.7924, + "step": 9851 + }, + { + "epoch": 0.6048067773719267, + "grad_norm": 0.9222925295059033, + "learning_rate": 7.1318971241432845e-06, + "loss": 0.7992, + "step": 9852 + }, + { + "epoch": 0.6048681666103932, + "grad_norm": 0.8994980767796932, + "learning_rate": 7.1299923668144145e-06, + "loss": 0.7908, + "step": 9853 + }, + { + "epoch": 0.6049295558488597, + "grad_norm": 0.7520378625141576, + "learning_rate": 7.1280877229522934e-06, + "loss": 0.7937, + "step": 9854 + }, + { + "epoch": 0.6049909450873262, + "grad_norm": 0.9285920140234418, + "learning_rate": 7.12618319263223e-06, + "loss": 0.8765, + "step": 9855 + }, + { + "epoch": 0.6050523343257926, + "grad_norm": 0.8180247958702431, + "learning_rate": 7.124278775929513e-06, + "loss": 0.8293, + "step": 9856 + }, + { + "epoch": 0.6051137235642592, + "grad_norm": 0.8969505287674178, + "learning_rate": 7.122374472919434e-06, + "loss": 0.8195, + "step": 9857 + }, + { + "epoch": 0.6051751128027257, + "grad_norm": 0.8670749142742535, + "learning_rate": 7.1204702836772856e-06, + "loss": 0.829, + "step": 9858 + }, + { + "epoch": 0.6052365020411922, + "grad_norm": 0.9276917500925657, + "learning_rate": 7.118566208278346e-06, + "loss": 0.8175, + "step": 9859 + }, + { + "epoch": 0.6052978912796587, + "grad_norm": 0.9284860600160494, + "learning_rate": 7.116662246797899e-06, + "loss": 0.8422, + "step": 9860 + }, + { + "epoch": 0.6053592805181252, + "grad_norm": 0.836145601841809, + "learning_rate": 7.1147583993112105e-06, + "loss": 0.8113, + "step": 9861 + }, + { + "epoch": 0.6054206697565917, + "grad_norm": 0.8569601007909219, + "learning_rate": 7.112854665893554e-06, + "loss": 0.8183, + "step": 9862 + }, + { + "epoch": 0.6054820589950581, + "grad_norm": 0.9161667387810887, + "learning_rate": 7.110951046620194e-06, + "loss": 0.7988, + "step": 9863 + }, + { + "epoch": 0.6055434482335247, + "grad_norm": 0.8673345357559189, + "learning_rate": 7.109047541566392e-06, + "loss": 0.806, + "step": 9864 + }, + { + "epoch": 0.6056048374719911, + "grad_norm": 0.9541297622901785, + "learning_rate": 7.107144150807403e-06, + "loss": 0.8258, + "step": 9865 + }, + { + "epoch": 0.6056662267104577, + "grad_norm": 0.7966803191585459, + "learning_rate": 7.105240874418475e-06, + "loss": 0.7689, + "step": 9866 + }, + { + "epoch": 0.6057276159489241, + "grad_norm": 0.8461420857169227, + "learning_rate": 7.10333771247486e-06, + "loss": 0.7565, + "step": 9867 + }, + { + "epoch": 0.6057890051873907, + "grad_norm": 0.8798944797025737, + "learning_rate": 7.101434665051796e-06, + "loss": 0.7899, + "step": 9868 + }, + { + "epoch": 0.6058503944258572, + "grad_norm": 0.8612307756650548, + "learning_rate": 7.099531732224524e-06, + "loss": 0.7528, + "step": 9869 + }, + { + "epoch": 0.6059117836643236, + "grad_norm": 0.914714434505021, + "learning_rate": 7.097628914068278e-06, + "loss": 0.8147, + "step": 9870 + }, + { + "epoch": 0.6059731729027902, + "grad_norm": 1.0478166796440576, + "learning_rate": 7.095726210658281e-06, + "loss": 0.8222, + "step": 9871 + }, + { + "epoch": 0.6060345621412566, + "grad_norm": 0.8290443477726432, + "learning_rate": 7.0938236220697575e-06, + "loss": 0.779, + "step": 9872 + }, + { + "epoch": 0.6060959513797232, + "grad_norm": 0.8913137177176877, + "learning_rate": 7.091921148377932e-06, + "loss": 0.8044, + "step": 9873 + }, + { + "epoch": 0.6061573406181896, + "grad_norm": 0.8777635497492825, + "learning_rate": 7.090018789658019e-06, + "loss": 0.8223, + "step": 9874 + }, + { + "epoch": 0.6062187298566561, + "grad_norm": 0.9031247825394584, + "learning_rate": 7.088116545985224e-06, + "loss": 0.755, + "step": 9875 + }, + { + "epoch": 0.6062801190951226, + "grad_norm": 0.6393386321306297, + "learning_rate": 7.086214417434758e-06, + "loss": 0.6597, + "step": 9876 + }, + { + "epoch": 0.6063415083335891, + "grad_norm": 0.7616707352135779, + "learning_rate": 7.084312404081816e-06, + "loss": 0.7394, + "step": 9877 + }, + { + "epoch": 0.6064028975720556, + "grad_norm": 0.7755206802031707, + "learning_rate": 7.0824105060016025e-06, + "loss": 0.7796, + "step": 9878 + }, + { + "epoch": 0.6064642868105221, + "grad_norm": 0.8939477988585013, + "learning_rate": 7.080508723269308e-06, + "loss": 0.84, + "step": 9879 + }, + { + "epoch": 0.6065256760489887, + "grad_norm": 0.8770519153744831, + "learning_rate": 7.078607055960114e-06, + "loss": 0.7906, + "step": 9880 + }, + { + "epoch": 0.6065870652874551, + "grad_norm": 0.9750471515024494, + "learning_rate": 7.076705504149208e-06, + "loss": 0.7931, + "step": 9881 + }, + { + "epoch": 0.6066484545259216, + "grad_norm": 0.9263812456944548, + "learning_rate": 7.074804067911769e-06, + "loss": 0.8571, + "step": 9882 + }, + { + "epoch": 0.6067098437643881, + "grad_norm": 0.8056644420980095, + "learning_rate": 7.0729027473229715e-06, + "loss": 0.7711, + "step": 9883 + }, + { + "epoch": 0.6067712330028546, + "grad_norm": 0.8869756588930949, + "learning_rate": 7.071001542457984e-06, + "loss": 0.7878, + "step": 9884 + }, + { + "epoch": 0.6068326222413211, + "grad_norm": 0.8815993365537557, + "learning_rate": 7.069100453391971e-06, + "loss": 0.8234, + "step": 9885 + }, + { + "epoch": 0.6068940114797876, + "grad_norm": 0.8263230128809359, + "learning_rate": 7.06719948020009e-06, + "loss": 0.7862, + "step": 9886 + }, + { + "epoch": 0.606955400718254, + "grad_norm": 0.9277330629125558, + "learning_rate": 7.065298622957501e-06, + "loss": 0.8437, + "step": 9887 + }, + { + "epoch": 0.6070167899567206, + "grad_norm": 0.8430022958149002, + "learning_rate": 7.063397881739351e-06, + "loss": 0.7995, + "step": 9888 + }, + { + "epoch": 0.607078179195187, + "grad_norm": 0.883374239552471, + "learning_rate": 7.061497256620793e-06, + "loss": 0.8286, + "step": 9889 + }, + { + "epoch": 0.6071395684336536, + "grad_norm": 0.8252162548812445, + "learning_rate": 7.059596747676963e-06, + "loss": 0.8188, + "step": 9890 + }, + { + "epoch": 0.6072009576721201, + "grad_norm": 0.8714333540437339, + "learning_rate": 7.0576963549829965e-06, + "loss": 0.8567, + "step": 9891 + }, + { + "epoch": 0.6072623469105866, + "grad_norm": 0.8156770954007457, + "learning_rate": 7.055796078614034e-06, + "loss": 0.831, + "step": 9892 + }, + { + "epoch": 0.6073237361490531, + "grad_norm": 0.8436434961493827, + "learning_rate": 7.053895918645196e-06, + "loss": 0.7698, + "step": 9893 + }, + { + "epoch": 0.6073851253875195, + "grad_norm": 0.8460445813647192, + "learning_rate": 7.051995875151614e-06, + "loss": 0.828, + "step": 9894 + }, + { + "epoch": 0.6074465146259861, + "grad_norm": 0.8326595152467267, + "learning_rate": 7.050095948208399e-06, + "loss": 0.7818, + "step": 9895 + }, + { + "epoch": 0.6075079038644525, + "grad_norm": 0.8476295219628175, + "learning_rate": 7.048196137890666e-06, + "loss": 0.7564, + "step": 9896 + }, + { + "epoch": 0.6075692931029191, + "grad_norm": 0.8407067330600193, + "learning_rate": 7.046296444273531e-06, + "loss": 0.7899, + "step": 9897 + }, + { + "epoch": 0.6076306823413855, + "grad_norm": 0.870973153114571, + "learning_rate": 7.044396867432093e-06, + "loss": 0.8017, + "step": 9898 + }, + { + "epoch": 0.6076920715798521, + "grad_norm": 0.9378871696076098, + "learning_rate": 7.042497407441458e-06, + "loss": 0.8635, + "step": 9899 + }, + { + "epoch": 0.6077534608183186, + "grad_norm": 0.8919003799618449, + "learning_rate": 7.040598064376713e-06, + "loss": 0.836, + "step": 9900 + }, + { + "epoch": 0.607814850056785, + "grad_norm": 0.8941754948385876, + "learning_rate": 7.038698838312957e-06, + "loss": 0.8265, + "step": 9901 + }, + { + "epoch": 0.6078762392952516, + "grad_norm": 0.9824452201708872, + "learning_rate": 7.036799729325272e-06, + "loss": 0.8173, + "step": 9902 + }, + { + "epoch": 0.607937628533718, + "grad_norm": 0.8730583277548506, + "learning_rate": 7.0349007374887454e-06, + "loss": 0.7935, + "step": 9903 + }, + { + "epoch": 0.6079990177721846, + "grad_norm": 0.9388172413888598, + "learning_rate": 7.033001862878452e-06, + "loss": 0.7916, + "step": 9904 + }, + { + "epoch": 0.608060407010651, + "grad_norm": 0.8153089667240649, + "learning_rate": 7.031103105569459e-06, + "loss": 0.7836, + "step": 9905 + }, + { + "epoch": 0.6081217962491176, + "grad_norm": 0.921948745785663, + "learning_rate": 7.029204465636842e-06, + "loss": 0.8375, + "step": 9906 + }, + { + "epoch": 0.608183185487584, + "grad_norm": 0.90636041783181, + "learning_rate": 7.027305943155659e-06, + "loss": 0.7727, + "step": 9907 + }, + { + "epoch": 0.6082445747260505, + "grad_norm": 0.8927118018589474, + "learning_rate": 7.025407538200973e-06, + "loss": 0.8054, + "step": 9908 + }, + { + "epoch": 0.608305963964517, + "grad_norm": 0.8681893311739898, + "learning_rate": 7.0235092508478385e-06, + "loss": 0.8275, + "step": 9909 + }, + { + "epoch": 0.6083673532029835, + "grad_norm": 0.6054609548655463, + "learning_rate": 7.0216110811713e-06, + "loss": 0.6469, + "step": 9910 + }, + { + "epoch": 0.6084287424414501, + "grad_norm": 0.8909547841468706, + "learning_rate": 7.019713029246404e-06, + "loss": 0.8312, + "step": 9911 + }, + { + "epoch": 0.6084901316799165, + "grad_norm": 0.8282681693497953, + "learning_rate": 7.017815095148193e-06, + "loss": 0.8493, + "step": 9912 + }, + { + "epoch": 0.608551520918383, + "grad_norm": 0.8969379266156241, + "learning_rate": 7.015917278951699e-06, + "loss": 0.7802, + "step": 9913 + }, + { + "epoch": 0.6086129101568495, + "grad_norm": 0.7712771424590987, + "learning_rate": 7.01401958073196e-06, + "loss": 0.7943, + "step": 9914 + }, + { + "epoch": 0.608674299395316, + "grad_norm": 0.8568986051472077, + "learning_rate": 7.012122000563995e-06, + "loss": 0.843, + "step": 9915 + }, + { + "epoch": 0.6087356886337825, + "grad_norm": 0.9854067427833961, + "learning_rate": 7.010224538522825e-06, + "loss": 0.8088, + "step": 9916 + }, + { + "epoch": 0.608797077872249, + "grad_norm": 0.8524974001060183, + "learning_rate": 7.0083271946834705e-06, + "loss": 0.8329, + "step": 9917 + }, + { + "epoch": 0.6088584671107155, + "grad_norm": 0.8277048543070188, + "learning_rate": 7.006429969120943e-06, + "loss": 0.8279, + "step": 9918 + }, + { + "epoch": 0.608919856349182, + "grad_norm": 0.973209029845214, + "learning_rate": 7.004532861910251e-06, + "loss": 0.7912, + "step": 9919 + }, + { + "epoch": 0.6089812455876484, + "grad_norm": 0.8803196744051359, + "learning_rate": 7.002635873126396e-06, + "loss": 0.7954, + "step": 9920 + }, + { + "epoch": 0.609042634826115, + "grad_norm": 0.7723748406297718, + "learning_rate": 7.000739002844372e-06, + "loss": 0.8365, + "step": 9921 + }, + { + "epoch": 0.6091040240645815, + "grad_norm": 0.8369262682761937, + "learning_rate": 6.998842251139179e-06, + "loss": 0.7917, + "step": 9922 + }, + { + "epoch": 0.609165413303048, + "grad_norm": 0.8936641829798213, + "learning_rate": 6.996945618085802e-06, + "loss": 0.7978, + "step": 9923 + }, + { + "epoch": 0.6092268025415145, + "grad_norm": 0.8039923510884486, + "learning_rate": 6.995049103759233e-06, + "loss": 0.7342, + "step": 9924 + }, + { + "epoch": 0.609288191779981, + "grad_norm": 0.8588238238256753, + "learning_rate": 6.993152708234436e-06, + "loss": 0.7808, + "step": 9925 + }, + { + "epoch": 0.6093495810184475, + "grad_norm": 0.8540420864596816, + "learning_rate": 6.991256431586397e-06, + "loss": 0.8079, + "step": 9926 + }, + { + "epoch": 0.6094109702569139, + "grad_norm": 0.9476959964582531, + "learning_rate": 6.989360273890082e-06, + "loss": 0.7581, + "step": 9927 + }, + { + "epoch": 0.6094723594953805, + "grad_norm": 0.9869591003313647, + "learning_rate": 6.987464235220459e-06, + "loss": 0.7947, + "step": 9928 + }, + { + "epoch": 0.6095337487338469, + "grad_norm": 0.8309169273330302, + "learning_rate": 6.985568315652489e-06, + "loss": 0.8016, + "step": 9929 + }, + { + "epoch": 0.6095951379723135, + "grad_norm": 0.9585591057642182, + "learning_rate": 6.983672515261122e-06, + "loss": 0.8912, + "step": 9930 + }, + { + "epoch": 0.6096565272107799, + "grad_norm": 0.906196048666951, + "learning_rate": 6.981776834121314e-06, + "loss": 0.806, + "step": 9931 + }, + { + "epoch": 0.6097179164492464, + "grad_norm": 0.7745534467709936, + "learning_rate": 6.979881272308009e-06, + "loss": 0.7703, + "step": 9932 + }, + { + "epoch": 0.609779305687713, + "grad_norm": 0.8209922570014306, + "learning_rate": 6.9779858298961525e-06, + "loss": 0.8465, + "step": 9933 + }, + { + "epoch": 0.6098406949261794, + "grad_norm": 0.873177443579213, + "learning_rate": 6.97609050696068e-06, + "loss": 0.7825, + "step": 9934 + }, + { + "epoch": 0.609902084164646, + "grad_norm": 0.7922304454540982, + "learning_rate": 6.97419530357652e-06, + "loss": 0.8007, + "step": 9935 + }, + { + "epoch": 0.6099634734031124, + "grad_norm": 0.9355613295377342, + "learning_rate": 6.972300219818604e-06, + "loss": 0.8317, + "step": 9936 + }, + { + "epoch": 0.610024862641579, + "grad_norm": 0.7753625743227827, + "learning_rate": 6.970405255761854e-06, + "loss": 0.7792, + "step": 9937 + }, + { + "epoch": 0.6100862518800454, + "grad_norm": 0.8800083501795029, + "learning_rate": 6.9685104114811884e-06, + "loss": 0.7905, + "step": 9938 + }, + { + "epoch": 0.6101476411185119, + "grad_norm": 0.6229250176117512, + "learning_rate": 6.966615687051517e-06, + "loss": 0.6831, + "step": 9939 + }, + { + "epoch": 0.6102090303569784, + "grad_norm": 0.9282292561597609, + "learning_rate": 6.964721082547753e-06, + "loss": 0.751, + "step": 9940 + }, + { + "epoch": 0.6102704195954449, + "grad_norm": 0.8471316927307535, + "learning_rate": 6.962826598044796e-06, + "loss": 0.7651, + "step": 9941 + }, + { + "epoch": 0.6103318088339114, + "grad_norm": 0.970773257041073, + "learning_rate": 6.96093223361755e-06, + "loss": 0.8314, + "step": 9942 + }, + { + "epoch": 0.6103931980723779, + "grad_norm": 0.6514926929365098, + "learning_rate": 6.959037989340909e-06, + "loss": 0.6999, + "step": 9943 + }, + { + "epoch": 0.6104545873108445, + "grad_norm": 0.995177948940755, + "learning_rate": 6.9571438652897565e-06, + "loss": 0.7989, + "step": 9944 + }, + { + "epoch": 0.6105159765493109, + "grad_norm": 0.9328769210813287, + "learning_rate": 6.9552498615389826e-06, + "loss": 0.8105, + "step": 9945 + }, + { + "epoch": 0.6105773657877774, + "grad_norm": 0.8377520181632017, + "learning_rate": 6.953355978163465e-06, + "loss": 0.775, + "step": 9946 + }, + { + "epoch": 0.6106387550262439, + "grad_norm": 0.8764536812503767, + "learning_rate": 6.951462215238081e-06, + "loss": 0.7965, + "step": 9947 + }, + { + "epoch": 0.6107001442647104, + "grad_norm": 0.8870289799891248, + "learning_rate": 6.949568572837704e-06, + "loss": 0.7996, + "step": 9948 + }, + { + "epoch": 0.6107615335031769, + "grad_norm": 0.9144063216301213, + "learning_rate": 6.947675051037193e-06, + "loss": 0.7483, + "step": 9949 + }, + { + "epoch": 0.6108229227416434, + "grad_norm": 0.9447692135899101, + "learning_rate": 6.94578164991141e-06, + "loss": 0.8029, + "step": 9950 + }, + { + "epoch": 0.6108843119801098, + "grad_norm": 0.8975310885311829, + "learning_rate": 6.943888369535217e-06, + "loss": 0.846, + "step": 9951 + }, + { + "epoch": 0.6109457012185764, + "grad_norm": 0.8760636731946667, + "learning_rate": 6.941995209983458e-06, + "loss": 0.795, + "step": 9952 + }, + { + "epoch": 0.6110070904570429, + "grad_norm": 0.8494092022712607, + "learning_rate": 6.940102171330989e-06, + "loss": 0.8069, + "step": 9953 + }, + { + "epoch": 0.6110684796955094, + "grad_norm": 0.9275055592385425, + "learning_rate": 6.938209253652644e-06, + "loss": 0.8271, + "step": 9954 + }, + { + "epoch": 0.6111298689339759, + "grad_norm": 0.9651280954987574, + "learning_rate": 6.936316457023262e-06, + "loss": 0.8503, + "step": 9955 + }, + { + "epoch": 0.6111912581724424, + "grad_norm": 0.8359511036115421, + "learning_rate": 6.934423781517676e-06, + "loss": 0.787, + "step": 9956 + }, + { + "epoch": 0.6112526474109089, + "grad_norm": 0.8256314900781584, + "learning_rate": 6.932531227210714e-06, + "loss": 0.7908, + "step": 9957 + }, + { + "epoch": 0.6113140366493753, + "grad_norm": 0.8465355835057831, + "learning_rate": 6.930638794177203e-06, + "loss": 0.8003, + "step": 9958 + }, + { + "epoch": 0.6113754258878419, + "grad_norm": 0.9648582752682429, + "learning_rate": 6.928746482491953e-06, + "loss": 0.8016, + "step": 9959 + }, + { + "epoch": 0.6114368151263083, + "grad_norm": 0.9223102295663026, + "learning_rate": 6.9268542922297775e-06, + "loss": 0.8122, + "step": 9960 + }, + { + "epoch": 0.6114982043647749, + "grad_norm": 1.012834940997894, + "learning_rate": 6.9249622234654925e-06, + "loss": 0.835, + "step": 9961 + }, + { + "epoch": 0.6115595936032413, + "grad_norm": 0.8367890207829042, + "learning_rate": 6.923070276273896e-06, + "loss": 0.7915, + "step": 9962 + }, + { + "epoch": 0.6116209828417078, + "grad_norm": 0.874214002923169, + "learning_rate": 6.921178450729791e-06, + "loss": 0.785, + "step": 9963 + }, + { + "epoch": 0.6116823720801744, + "grad_norm": 0.8934882192721452, + "learning_rate": 6.9192867469079625e-06, + "loss": 0.824, + "step": 9964 + }, + { + "epoch": 0.6117437613186408, + "grad_norm": 0.8418165906136823, + "learning_rate": 6.9173951648832104e-06, + "loss": 0.7317, + "step": 9965 + }, + { + "epoch": 0.6118051505571074, + "grad_norm": 0.9147986577937135, + "learning_rate": 6.915503704730311e-06, + "loss": 0.8204, + "step": 9966 + }, + { + "epoch": 0.6118665397955738, + "grad_norm": 0.9129814524298511, + "learning_rate": 6.9136123665240495e-06, + "loss": 0.7755, + "step": 9967 + }, + { + "epoch": 0.6119279290340404, + "grad_norm": 0.915819968710442, + "learning_rate": 6.9117211503392e-06, + "loss": 0.7979, + "step": 9968 + }, + { + "epoch": 0.6119893182725068, + "grad_norm": 0.8870377599687084, + "learning_rate": 6.909830056250527e-06, + "loss": 0.8636, + "step": 9969 + }, + { + "epoch": 0.6120507075109733, + "grad_norm": 0.8655554622789844, + "learning_rate": 6.907939084332802e-06, + "loss": 0.773, + "step": 9970 + }, + { + "epoch": 0.6121120967494398, + "grad_norm": 0.8540289020705573, + "learning_rate": 6.906048234660778e-06, + "loss": 0.7755, + "step": 9971 + }, + { + "epoch": 0.6121734859879063, + "grad_norm": 0.8760549882949457, + "learning_rate": 6.9041575073092196e-06, + "loss": 0.7814, + "step": 9972 + }, + { + "epoch": 0.6122348752263728, + "grad_norm": 0.815998133520709, + "learning_rate": 6.902266902352874e-06, + "loss": 0.7832, + "step": 9973 + }, + { + "epoch": 0.6122962644648393, + "grad_norm": 0.8128491051827399, + "learning_rate": 6.9003764198664835e-06, + "loss": 0.7645, + "step": 9974 + }, + { + "epoch": 0.6123576537033059, + "grad_norm": 0.8027511419303661, + "learning_rate": 6.8984860599247885e-06, + "loss": 0.791, + "step": 9975 + }, + { + "epoch": 0.6124190429417723, + "grad_norm": 0.9217054407009836, + "learning_rate": 6.89659582260253e-06, + "loss": 0.7713, + "step": 9976 + }, + { + "epoch": 0.6124804321802388, + "grad_norm": 0.9721812189927562, + "learning_rate": 6.894705707974434e-06, + "loss": 0.7968, + "step": 9977 + }, + { + "epoch": 0.6125418214187053, + "grad_norm": 0.9769092678183752, + "learning_rate": 6.892815716115236e-06, + "loss": 0.8852, + "step": 9978 + }, + { + "epoch": 0.6126032106571718, + "grad_norm": 0.8722376245061887, + "learning_rate": 6.890925847099646e-06, + "loss": 0.8253, + "step": 9979 + }, + { + "epoch": 0.6126645998956383, + "grad_norm": 0.9443585309086105, + "learning_rate": 6.889036101002385e-06, + "loss": 0.783, + "step": 9980 + }, + { + "epoch": 0.6127259891341048, + "grad_norm": 0.8613339901954451, + "learning_rate": 6.887146477898168e-06, + "loss": 0.8096, + "step": 9981 + }, + { + "epoch": 0.6127873783725712, + "grad_norm": 0.8758350682346252, + "learning_rate": 6.885256977861698e-06, + "loss": 0.8439, + "step": 9982 + }, + { + "epoch": 0.6128487676110378, + "grad_norm": 0.7885660119458767, + "learning_rate": 6.883367600967681e-06, + "loss": 0.7526, + "step": 9983 + }, + { + "epoch": 0.6129101568495042, + "grad_norm": 0.8666245099397012, + "learning_rate": 6.8814783472908106e-06, + "loss": 0.7984, + "step": 9984 + }, + { + "epoch": 0.6129715460879708, + "grad_norm": 0.7453529609709736, + "learning_rate": 6.879589216905777e-06, + "loss": 0.7478, + "step": 9985 + }, + { + "epoch": 0.6130329353264373, + "grad_norm": 0.8763036904457833, + "learning_rate": 6.877700209887275e-06, + "loss": 0.8553, + "step": 9986 + }, + { + "epoch": 0.6130943245649038, + "grad_norm": 0.8010558858613378, + "learning_rate": 6.8758113263099794e-06, + "loss": 0.7751, + "step": 9987 + }, + { + "epoch": 0.6131557138033703, + "grad_norm": 0.8205216441456138, + "learning_rate": 6.873922566248577e-06, + "loss": 0.7818, + "step": 9988 + }, + { + "epoch": 0.6132171030418367, + "grad_norm": 0.9736497082098625, + "learning_rate": 6.872033929777731e-06, + "loss": 0.7852, + "step": 9989 + }, + { + "epoch": 0.6132784922803033, + "grad_norm": 0.8824686697912262, + "learning_rate": 6.8701454169721135e-06, + "loss": 0.7777, + "step": 9990 + }, + { + "epoch": 0.6133398815187697, + "grad_norm": 0.8661891750047778, + "learning_rate": 6.868257027906385e-06, + "loss": 0.7551, + "step": 9991 + }, + { + "epoch": 0.6134012707572363, + "grad_norm": 0.9180274840014621, + "learning_rate": 6.866368762655209e-06, + "loss": 0.7756, + "step": 9992 + }, + { + "epoch": 0.6134626599957027, + "grad_norm": 0.8942417239080908, + "learning_rate": 6.864480621293237e-06, + "loss": 0.8266, + "step": 9993 + }, + { + "epoch": 0.6135240492341693, + "grad_norm": 0.9088429821714541, + "learning_rate": 6.862592603895113e-06, + "loss": 0.8279, + "step": 9994 + }, + { + "epoch": 0.6135854384726358, + "grad_norm": 0.9111121242392285, + "learning_rate": 6.860704710535484e-06, + "loss": 0.7935, + "step": 9995 + }, + { + "epoch": 0.6136468277111022, + "grad_norm": 0.9427900953819098, + "learning_rate": 6.858816941288987e-06, + "loss": 0.7836, + "step": 9996 + }, + { + "epoch": 0.6137082169495688, + "grad_norm": 0.841636508347563, + "learning_rate": 6.856929296230258e-06, + "loss": 0.8091, + "step": 9997 + }, + { + "epoch": 0.6137696061880352, + "grad_norm": 0.8881399080891482, + "learning_rate": 6.855041775433926e-06, + "loss": 0.8957, + "step": 9998 + }, + { + "epoch": 0.6138309954265018, + "grad_norm": 1.0345783325015887, + "learning_rate": 6.85315437897461e-06, + "loss": 0.8688, + "step": 9999 + }, + { + "epoch": 0.6138923846649682, + "grad_norm": 0.7357972025851824, + "learning_rate": 6.851267106926933e-06, + "loss": 0.7535, + "step": 10000 + }, + { + "epoch": 0.6139537739034348, + "grad_norm": 0.830779149101513, + "learning_rate": 6.849379959365509e-06, + "loss": 0.8452, + "step": 10001 + }, + { + "epoch": 0.6140151631419012, + "grad_norm": 0.8556555617999587, + "learning_rate": 6.8474929363649466e-06, + "loss": 0.77, + "step": 10002 + }, + { + "epoch": 0.6140765523803677, + "grad_norm": 0.9203073984372235, + "learning_rate": 6.845606037999846e-06, + "loss": 0.8569, + "step": 10003 + }, + { + "epoch": 0.6141379416188342, + "grad_norm": 1.0311632131247734, + "learning_rate": 6.843719264344812e-06, + "loss": 0.8395, + "step": 10004 + }, + { + "epoch": 0.6141993308573007, + "grad_norm": 0.8441360071722896, + "learning_rate": 6.841832615474433e-06, + "loss": 0.8039, + "step": 10005 + }, + { + "epoch": 0.6142607200957673, + "grad_norm": 0.8302424691750087, + "learning_rate": 6.839946091463305e-06, + "loss": 0.7901, + "step": 10006 + }, + { + "epoch": 0.6143221093342337, + "grad_norm": 0.8388172546689739, + "learning_rate": 6.8380596923860096e-06, + "loss": 0.8689, + "step": 10007 + }, + { + "epoch": 0.6143834985727002, + "grad_norm": 0.8776829720533623, + "learning_rate": 6.836173418317124e-06, + "loss": 0.8091, + "step": 10008 + }, + { + "epoch": 0.6144448878111667, + "grad_norm": 0.859295705654135, + "learning_rate": 6.834287269331226e-06, + "loss": 0.7822, + "step": 10009 + }, + { + "epoch": 0.6145062770496332, + "grad_norm": 0.9837647593802613, + "learning_rate": 6.83240124550288e-06, + "loss": 0.7984, + "step": 10010 + }, + { + "epoch": 0.6145676662880997, + "grad_norm": 0.9032919225164558, + "learning_rate": 6.830515346906658e-06, + "loss": 0.7953, + "step": 10011 + }, + { + "epoch": 0.6146290555265662, + "grad_norm": 0.818243799357814, + "learning_rate": 6.8286295736171175e-06, + "loss": 0.8215, + "step": 10012 + }, + { + "epoch": 0.6146904447650327, + "grad_norm": 0.8795965119417706, + "learning_rate": 6.82674392570881e-06, + "loss": 0.7831, + "step": 10013 + }, + { + "epoch": 0.6147518340034992, + "grad_norm": 0.796528780311238, + "learning_rate": 6.824858403256284e-06, + "loss": 0.8057, + "step": 10014 + }, + { + "epoch": 0.6148132232419656, + "grad_norm": 0.9202513025567974, + "learning_rate": 6.8229730063340895e-06, + "loss": 0.7934, + "step": 10015 + }, + { + "epoch": 0.6148746124804322, + "grad_norm": 0.7951070543467471, + "learning_rate": 6.821087735016762e-06, + "loss": 0.8019, + "step": 10016 + }, + { + "epoch": 0.6149360017188987, + "grad_norm": 0.8260426781224973, + "learning_rate": 6.819202589378841e-06, + "loss": 0.8021, + "step": 10017 + }, + { + "epoch": 0.6149973909573652, + "grad_norm": 0.9099792217496921, + "learning_rate": 6.817317569494855e-06, + "loss": 0.8294, + "step": 10018 + }, + { + "epoch": 0.6150587801958317, + "grad_norm": 0.5884338390878269, + "learning_rate": 6.815432675439323e-06, + "loss": 0.7272, + "step": 10019 + }, + { + "epoch": 0.6151201694342981, + "grad_norm": 0.828263000927018, + "learning_rate": 6.813547907286773e-06, + "loss": 0.8223, + "step": 10020 + }, + { + "epoch": 0.6151815586727647, + "grad_norm": 0.8209811721640461, + "learning_rate": 6.811663265111713e-06, + "loss": 0.8123, + "step": 10021 + }, + { + "epoch": 0.6152429479112311, + "grad_norm": 0.8368873610556661, + "learning_rate": 6.809778748988663e-06, + "loss": 0.8314, + "step": 10022 + }, + { + "epoch": 0.6153043371496977, + "grad_norm": 0.8506083017853198, + "learning_rate": 6.8078943589921176e-06, + "loss": 0.8111, + "step": 10023 + }, + { + "epoch": 0.6153657263881641, + "grad_norm": 0.8291314462262763, + "learning_rate": 6.806010095196578e-06, + "loss": 0.8141, + "step": 10024 + }, + { + "epoch": 0.6154271156266307, + "grad_norm": 0.8234774688840976, + "learning_rate": 6.804125957676546e-06, + "loss": 0.806, + "step": 10025 + }, + { + "epoch": 0.6154885048650971, + "grad_norm": 0.93156503428581, + "learning_rate": 6.802241946506505e-06, + "loss": 0.806, + "step": 10026 + }, + { + "epoch": 0.6155498941035636, + "grad_norm": 0.9276811025018201, + "learning_rate": 6.800358061760948e-06, + "loss": 0.8526, + "step": 10027 + }, + { + "epoch": 0.6156112833420302, + "grad_norm": 0.8347194536443135, + "learning_rate": 6.7984743035143445e-06, + "loss": 0.7977, + "step": 10028 + }, + { + "epoch": 0.6156726725804966, + "grad_norm": 0.8295326930960143, + "learning_rate": 6.7965906718411766e-06, + "loss": 0.7919, + "step": 10029 + }, + { + "epoch": 0.6157340618189632, + "grad_norm": 0.8345595948183008, + "learning_rate": 6.794707166815911e-06, + "loss": 0.7783, + "step": 10030 + }, + { + "epoch": 0.6157954510574296, + "grad_norm": 0.8126925276106078, + "learning_rate": 6.792823788513015e-06, + "loss": 0.7818, + "step": 10031 + }, + { + "epoch": 0.6158568402958962, + "grad_norm": 0.9193388620860375, + "learning_rate": 6.7909405370069495e-06, + "loss": 0.7902, + "step": 10032 + }, + { + "epoch": 0.6159182295343626, + "grad_norm": 0.8720464726574985, + "learning_rate": 6.789057412372165e-06, + "loss": 0.7772, + "step": 10033 + }, + { + "epoch": 0.6159796187728291, + "grad_norm": 0.9633985930054427, + "learning_rate": 6.7871744146831166e-06, + "loss": 0.7818, + "step": 10034 + }, + { + "epoch": 0.6160410080112956, + "grad_norm": 0.8792584416884656, + "learning_rate": 6.7852915440142444e-06, + "loss": 0.7592, + "step": 10035 + }, + { + "epoch": 0.6161023972497621, + "grad_norm": 0.9165398257688453, + "learning_rate": 6.783408800439992e-06, + "loss": 0.7965, + "step": 10036 + }, + { + "epoch": 0.6161637864882286, + "grad_norm": 0.9886186220921003, + "learning_rate": 6.7815261840347964e-06, + "loss": 0.7643, + "step": 10037 + }, + { + "epoch": 0.6162251757266951, + "grad_norm": 0.9149227601308697, + "learning_rate": 6.779643694873081e-06, + "loss": 0.808, + "step": 10038 + }, + { + "epoch": 0.6162865649651617, + "grad_norm": 0.8803265389469912, + "learning_rate": 6.777761333029274e-06, + "loss": 0.7789, + "step": 10039 + }, + { + "epoch": 0.6163479542036281, + "grad_norm": 0.5791572661204296, + "learning_rate": 6.775879098577798e-06, + "loss": 0.6305, + "step": 10040 + }, + { + "epoch": 0.6164093434420946, + "grad_norm": 0.7418730342635665, + "learning_rate": 6.773996991593061e-06, + "loss": 0.7804, + "step": 10041 + }, + { + "epoch": 0.6164707326805611, + "grad_norm": 0.9275042057768114, + "learning_rate": 6.772115012149481e-06, + "loss": 0.8077, + "step": 10042 + }, + { + "epoch": 0.6165321219190276, + "grad_norm": 0.8905171866447845, + "learning_rate": 6.770233160321457e-06, + "loss": 0.8098, + "step": 10043 + }, + { + "epoch": 0.6165935111574941, + "grad_norm": 0.9397612835900384, + "learning_rate": 6.768351436183387e-06, + "loss": 0.8161, + "step": 10044 + }, + { + "epoch": 0.6166549003959606, + "grad_norm": 0.8336092613415875, + "learning_rate": 6.766469839809673e-06, + "loss": 0.7478, + "step": 10045 + }, + { + "epoch": 0.616716289634427, + "grad_norm": 0.9113445644115702, + "learning_rate": 6.764588371274696e-06, + "loss": 0.8055, + "step": 10046 + }, + { + "epoch": 0.6167776788728936, + "grad_norm": 0.6506404492321409, + "learning_rate": 6.762707030652851e-06, + "loss": 0.7144, + "step": 10047 + }, + { + "epoch": 0.6168390681113601, + "grad_norm": 0.9572647567517765, + "learning_rate": 6.7608258180185085e-06, + "loss": 0.8328, + "step": 10048 + }, + { + "epoch": 0.6169004573498266, + "grad_norm": 0.8235559289065487, + "learning_rate": 6.758944733446043e-06, + "loss": 0.7671, + "step": 10049 + }, + { + "epoch": 0.6169618465882931, + "grad_norm": 0.9069000199394949, + "learning_rate": 6.757063777009829e-06, + "loss": 0.7831, + "step": 10050 + }, + { + "epoch": 0.6170232358267596, + "grad_norm": 0.9189715906967613, + "learning_rate": 6.755182948784227e-06, + "loss": 0.8107, + "step": 10051 + }, + { + "epoch": 0.6170846250652261, + "grad_norm": 0.7754051611485063, + "learning_rate": 6.753302248843603e-06, + "loss": 0.7588, + "step": 10052 + }, + { + "epoch": 0.6171460143036925, + "grad_norm": 0.9671513194243183, + "learning_rate": 6.7514216772623e-06, + "loss": 0.9174, + "step": 10053 + }, + { + "epoch": 0.6172074035421591, + "grad_norm": 0.8932043360925701, + "learning_rate": 6.749541234114674e-06, + "loss": 0.7576, + "step": 10054 + }, + { + "epoch": 0.6172687927806255, + "grad_norm": 0.9548516545699888, + "learning_rate": 6.747660919475065e-06, + "loss": 0.7833, + "step": 10055 + }, + { + "epoch": 0.6173301820190921, + "grad_norm": 0.8566788735825943, + "learning_rate": 6.745780733417819e-06, + "loss": 0.7978, + "step": 10056 + }, + { + "epoch": 0.6173915712575585, + "grad_norm": 0.9464735311540998, + "learning_rate": 6.743900676017265e-06, + "loss": 0.8263, + "step": 10057 + }, + { + "epoch": 0.617452960496025, + "grad_norm": 0.8548401335723494, + "learning_rate": 6.742020747347731e-06, + "loss": 0.776, + "step": 10058 + }, + { + "epoch": 0.6175143497344916, + "grad_norm": 0.8709821677999715, + "learning_rate": 6.740140947483541e-06, + "loss": 0.8186, + "step": 10059 + }, + { + "epoch": 0.617575738972958, + "grad_norm": 0.8125018436818625, + "learning_rate": 6.738261276499013e-06, + "loss": 0.7675, + "step": 10060 + }, + { + "epoch": 0.6176371282114246, + "grad_norm": 0.8881149249445625, + "learning_rate": 6.736381734468465e-06, + "loss": 0.8057, + "step": 10061 + }, + { + "epoch": 0.617698517449891, + "grad_norm": 0.7863867345522271, + "learning_rate": 6.734502321466202e-06, + "loss": 0.8393, + "step": 10062 + }, + { + "epoch": 0.6177599066883576, + "grad_norm": 0.8709096501748332, + "learning_rate": 6.732623037566525e-06, + "loss": 0.8304, + "step": 10063 + }, + { + "epoch": 0.617821295926824, + "grad_norm": 0.8518633726977874, + "learning_rate": 6.730743882843736e-06, + "loss": 0.7794, + "step": 10064 + }, + { + "epoch": 0.6178826851652905, + "grad_norm": 0.8591472845375714, + "learning_rate": 6.7288648573721236e-06, + "loss": 0.8196, + "step": 10065 + }, + { + "epoch": 0.617944074403757, + "grad_norm": 0.8896166211483693, + "learning_rate": 6.726985961225983e-06, + "loss": 0.7412, + "step": 10066 + }, + { + "epoch": 0.6180054636422235, + "grad_norm": 0.9255781278384723, + "learning_rate": 6.7251071944795924e-06, + "loss": 0.8248, + "step": 10067 + }, + { + "epoch": 0.61806685288069, + "grad_norm": 0.7962154927431465, + "learning_rate": 6.723228557207229e-06, + "loss": 0.767, + "step": 10068 + }, + { + "epoch": 0.6181282421191565, + "grad_norm": 0.852304699240773, + "learning_rate": 6.721350049483163e-06, + "loss": 0.8362, + "step": 10069 + }, + { + "epoch": 0.6181896313576231, + "grad_norm": 0.8865699288781237, + "learning_rate": 6.719471671381668e-06, + "loss": 0.8044, + "step": 10070 + }, + { + "epoch": 0.6182510205960895, + "grad_norm": 0.8726615026246737, + "learning_rate": 6.717593422977004e-06, + "loss": 0.8187, + "step": 10071 + }, + { + "epoch": 0.618312409834556, + "grad_norm": 0.7982102471554908, + "learning_rate": 6.715715304343424e-06, + "loss": 0.7684, + "step": 10072 + }, + { + "epoch": 0.6183737990730225, + "grad_norm": 0.823228007863961, + "learning_rate": 6.713837315555187e-06, + "loss": 0.8131, + "step": 10073 + }, + { + "epoch": 0.618435188311489, + "grad_norm": 0.7499558901185989, + "learning_rate": 6.711959456686534e-06, + "loss": 0.7421, + "step": 10074 + }, + { + "epoch": 0.6184965775499555, + "grad_norm": 1.012087763606216, + "learning_rate": 6.710081727811711e-06, + "loss": 0.8186, + "step": 10075 + }, + { + "epoch": 0.618557966788422, + "grad_norm": 0.9288403136224115, + "learning_rate": 6.708204129004955e-06, + "loss": 0.8515, + "step": 10076 + }, + { + "epoch": 0.6186193560268884, + "grad_norm": 0.8937809473512335, + "learning_rate": 6.706326660340492e-06, + "loss": 0.7588, + "step": 10077 + }, + { + "epoch": 0.618680745265355, + "grad_norm": 0.8560609843434216, + "learning_rate": 6.704449321892552e-06, + "loss": 0.8162, + "step": 10078 + }, + { + "epoch": 0.6187421345038214, + "grad_norm": 0.9361245211607757, + "learning_rate": 6.702572113735358e-06, + "loss": 0.8321, + "step": 10079 + }, + { + "epoch": 0.618803523742288, + "grad_norm": 0.8868339722287448, + "learning_rate": 6.700695035943122e-06, + "loss": 0.7723, + "step": 10080 + }, + { + "epoch": 0.6188649129807545, + "grad_norm": 0.8479937437164378, + "learning_rate": 6.698818088590062e-06, + "loss": 0.775, + "step": 10081 + }, + { + "epoch": 0.618926302219221, + "grad_norm": 0.8182255007164998, + "learning_rate": 6.696941271750376e-06, + "loss": 0.8162, + "step": 10082 + }, + { + "epoch": 0.6189876914576875, + "grad_norm": 0.9237069460957722, + "learning_rate": 6.695064585498266e-06, + "loss": 0.7898, + "step": 10083 + }, + { + "epoch": 0.6190490806961539, + "grad_norm": 0.8001324663199354, + "learning_rate": 6.693188029907929e-06, + "loss": 0.7816, + "step": 10084 + }, + { + "epoch": 0.6191104699346205, + "grad_norm": 0.9592457720779513, + "learning_rate": 6.691311605053554e-06, + "loss": 0.7756, + "step": 10085 + }, + { + "epoch": 0.6191718591730869, + "grad_norm": 0.8370743806823359, + "learning_rate": 6.689435311009333e-06, + "loss": 0.7954, + "step": 10086 + }, + { + "epoch": 0.6192332484115535, + "grad_norm": 0.9053883188903407, + "learning_rate": 6.687559147849437e-06, + "loss": 0.8168, + "step": 10087 + }, + { + "epoch": 0.6192946376500199, + "grad_norm": 0.8951236071089752, + "learning_rate": 6.685683115648043e-06, + "loss": 0.749, + "step": 10088 + }, + { + "epoch": 0.6193560268884865, + "grad_norm": 0.8646434163751856, + "learning_rate": 6.683807214479323e-06, + "loss": 0.7871, + "step": 10089 + }, + { + "epoch": 0.6194174161269529, + "grad_norm": 0.8904720281684575, + "learning_rate": 6.681931444417438e-06, + "loss": 0.8035, + "step": 10090 + }, + { + "epoch": 0.6194788053654194, + "grad_norm": 0.9787709134577529, + "learning_rate": 6.680055805536556e-06, + "loss": 0.819, + "step": 10091 + }, + { + "epoch": 0.619540194603886, + "grad_norm": 0.94142620989406, + "learning_rate": 6.678180297910817e-06, + "loss": 0.8474, + "step": 10092 + }, + { + "epoch": 0.6196015838423524, + "grad_norm": 0.8816408208183085, + "learning_rate": 6.67630492161438e-06, + "loss": 0.7614, + "step": 10093 + }, + { + "epoch": 0.619662973080819, + "grad_norm": 0.8046241257237662, + "learning_rate": 6.674429676721384e-06, + "loss": 0.803, + "step": 10094 + }, + { + "epoch": 0.6197243623192854, + "grad_norm": 0.9083831179733267, + "learning_rate": 6.672554563305971e-06, + "loss": 0.8204, + "step": 10095 + }, + { + "epoch": 0.619785751557752, + "grad_norm": 0.8093987111711043, + "learning_rate": 6.670679581442274e-06, + "loss": 0.8507, + "step": 10096 + }, + { + "epoch": 0.6198471407962184, + "grad_norm": 0.8152397110533592, + "learning_rate": 6.668804731204417e-06, + "loss": 0.7483, + "step": 10097 + }, + { + "epoch": 0.6199085300346849, + "grad_norm": 0.860870974689436, + "learning_rate": 6.666930012666526e-06, + "loss": 0.7554, + "step": 10098 + }, + { + "epoch": 0.6199699192731514, + "grad_norm": 0.8952929716740261, + "learning_rate": 6.665055425902716e-06, + "loss": 0.8578, + "step": 10099 + }, + { + "epoch": 0.6200313085116179, + "grad_norm": 0.8728130935305668, + "learning_rate": 6.663180970987105e-06, + "loss": 0.808, + "step": 10100 + }, + { + "epoch": 0.6200926977500845, + "grad_norm": 0.872731675427603, + "learning_rate": 6.6613066479937985e-06, + "loss": 0.7647, + "step": 10101 + }, + { + "epoch": 0.6201540869885509, + "grad_norm": 0.818884094441352, + "learning_rate": 6.659432456996893e-06, + "loss": 0.7753, + "step": 10102 + }, + { + "epoch": 0.6202154762270174, + "grad_norm": 0.9226171858140706, + "learning_rate": 6.65755839807049e-06, + "loss": 0.7845, + "step": 10103 + }, + { + "epoch": 0.6202768654654839, + "grad_norm": 0.8814793517501118, + "learning_rate": 6.655684471288678e-06, + "loss": 0.7761, + "step": 10104 + }, + { + "epoch": 0.6203382547039504, + "grad_norm": 0.947262503516861, + "learning_rate": 6.653810676725548e-06, + "loss": 0.8165, + "step": 10105 + }, + { + "epoch": 0.6203996439424169, + "grad_norm": 0.7738352720778868, + "learning_rate": 6.651937014455181e-06, + "loss": 0.7533, + "step": 10106 + }, + { + "epoch": 0.6204610331808834, + "grad_norm": 0.9515313023426063, + "learning_rate": 6.650063484551647e-06, + "loss": 0.8205, + "step": 10107 + }, + { + "epoch": 0.6205224224193499, + "grad_norm": 0.8434373750681776, + "learning_rate": 6.64819008708902e-06, + "loss": 0.7899, + "step": 10108 + }, + { + "epoch": 0.6205838116578164, + "grad_norm": 0.8827760494737822, + "learning_rate": 6.646316822141368e-06, + "loss": 0.7677, + "step": 10109 + }, + { + "epoch": 0.6206452008962828, + "grad_norm": 0.9057724753142501, + "learning_rate": 6.644443689782745e-06, + "loss": 0.7973, + "step": 10110 + }, + { + "epoch": 0.6207065901347494, + "grad_norm": 0.8039373014925073, + "learning_rate": 6.6425706900872155e-06, + "loss": 0.795, + "step": 10111 + }, + { + "epoch": 0.6207679793732159, + "grad_norm": 0.7936193747320268, + "learning_rate": 6.64069782312882e-06, + "loss": 0.7614, + "step": 10112 + }, + { + "epoch": 0.6208293686116824, + "grad_norm": 0.8274630389373472, + "learning_rate": 6.638825088981604e-06, + "loss": 0.8314, + "step": 10113 + }, + { + "epoch": 0.6208907578501489, + "grad_norm": 0.8940937057863567, + "learning_rate": 6.636952487719612e-06, + "loss": 0.8973, + "step": 10114 + }, + { + "epoch": 0.6209521470886153, + "grad_norm": 0.9561293292995919, + "learning_rate": 6.635080019416873e-06, + "loss": 0.7976, + "step": 10115 + }, + { + "epoch": 0.6210135363270819, + "grad_norm": 0.8713545563288213, + "learning_rate": 6.6332076841474225e-06, + "loss": 0.8165, + "step": 10116 + }, + { + "epoch": 0.6210749255655483, + "grad_norm": 0.9722233223947266, + "learning_rate": 6.631335481985275e-06, + "loss": 0.7737, + "step": 10117 + }, + { + "epoch": 0.6211363148040149, + "grad_norm": 0.9590134834573552, + "learning_rate": 6.6294634130044545e-06, + "loss": 0.78, + "step": 10118 + }, + { + "epoch": 0.6211977040424813, + "grad_norm": 0.9280513193033104, + "learning_rate": 6.62759147727897e-06, + "loss": 0.8086, + "step": 10119 + }, + { + "epoch": 0.6212590932809479, + "grad_norm": 0.8682395329139613, + "learning_rate": 6.625719674882832e-06, + "loss": 0.8136, + "step": 10120 + }, + { + "epoch": 0.6213204825194143, + "grad_norm": 0.9506186328451082, + "learning_rate": 6.623848005890046e-06, + "loss": 0.8706, + "step": 10121 + }, + { + "epoch": 0.6213818717578808, + "grad_norm": 0.9738754124052161, + "learning_rate": 6.6219764703746e-06, + "loss": 0.82, + "step": 10122 + }, + { + "epoch": 0.6214432609963474, + "grad_norm": 0.9191002016622588, + "learning_rate": 6.620105068410494e-06, + "loss": 0.7878, + "step": 10123 + }, + { + "epoch": 0.6215046502348138, + "grad_norm": 0.9685945603183223, + "learning_rate": 6.618233800071708e-06, + "loss": 0.7801, + "step": 10124 + }, + { + "epoch": 0.6215660394732804, + "grad_norm": 0.8395205105082578, + "learning_rate": 6.61636266543223e-06, + "loss": 0.775, + "step": 10125 + }, + { + "epoch": 0.6216274287117468, + "grad_norm": 0.8779526002986301, + "learning_rate": 6.614491664566035e-06, + "loss": 0.7816, + "step": 10126 + }, + { + "epoch": 0.6216888179502134, + "grad_norm": 0.770833418663516, + "learning_rate": 6.612620797547087e-06, + "loss": 0.7542, + "step": 10127 + }, + { + "epoch": 0.6217502071886798, + "grad_norm": 0.9493017091000726, + "learning_rate": 6.610750064449358e-06, + "loss": 0.7458, + "step": 10128 + }, + { + "epoch": 0.6218115964271463, + "grad_norm": 0.9123971186343697, + "learning_rate": 6.608879465346804e-06, + "loss": 0.8057, + "step": 10129 + }, + { + "epoch": 0.6218729856656128, + "grad_norm": 0.785972847139596, + "learning_rate": 6.607009000313384e-06, + "loss": 0.7728, + "step": 10130 + }, + { + "epoch": 0.6219343749040793, + "grad_norm": 0.8546168131202108, + "learning_rate": 6.605138669423046e-06, + "loss": 0.7899, + "step": 10131 + }, + { + "epoch": 0.6219957641425458, + "grad_norm": 0.8636544815020047, + "learning_rate": 6.603268472749733e-06, + "loss": 0.7911, + "step": 10132 + }, + { + "epoch": 0.6220571533810123, + "grad_norm": 0.7990279517018122, + "learning_rate": 6.601398410367381e-06, + "loss": 0.8009, + "step": 10133 + }, + { + "epoch": 0.6221185426194789, + "grad_norm": 0.9213849645891752, + "learning_rate": 6.5995284823499295e-06, + "loss": 0.8354, + "step": 10134 + }, + { + "epoch": 0.6221799318579453, + "grad_norm": 0.9075725439809718, + "learning_rate": 6.597658688771307e-06, + "loss": 0.8558, + "step": 10135 + }, + { + "epoch": 0.6222413210964118, + "grad_norm": 0.8797783615933474, + "learning_rate": 6.595789029705427e-06, + "loss": 0.78, + "step": 10136 + }, + { + "epoch": 0.6223027103348783, + "grad_norm": 0.786439053192878, + "learning_rate": 6.593919505226218e-06, + "loss": 0.8082, + "step": 10137 + }, + { + "epoch": 0.6223640995733448, + "grad_norm": 0.8491423896653989, + "learning_rate": 6.592050115407584e-06, + "loss": 0.7852, + "step": 10138 + }, + { + "epoch": 0.6224254888118113, + "grad_norm": 0.9950316457735299, + "learning_rate": 6.59018086032344e-06, + "loss": 0.8408, + "step": 10139 + }, + { + "epoch": 0.6224868780502778, + "grad_norm": 0.8455926303714826, + "learning_rate": 6.588311740047684e-06, + "loss": 0.7982, + "step": 10140 + }, + { + "epoch": 0.6225482672887442, + "grad_norm": 0.8710738136109537, + "learning_rate": 6.5864427546542085e-06, + "loss": 0.7712, + "step": 10141 + }, + { + "epoch": 0.6226096565272108, + "grad_norm": 0.8225432169691651, + "learning_rate": 6.584573904216911e-06, + "loss": 0.7612, + "step": 10142 + }, + { + "epoch": 0.6226710457656772, + "grad_norm": 0.6291758833221949, + "learning_rate": 6.582705188809671e-06, + "loss": 0.6923, + "step": 10143 + }, + { + "epoch": 0.6227324350041438, + "grad_norm": 0.8752702657867644, + "learning_rate": 6.580836608506374e-06, + "loss": 0.784, + "step": 10144 + }, + { + "epoch": 0.6227938242426103, + "grad_norm": 0.8207074908040031, + "learning_rate": 6.5789681633808945e-06, + "loss": 0.7967, + "step": 10145 + }, + { + "epoch": 0.6228552134810768, + "grad_norm": 0.8600714940903137, + "learning_rate": 6.577099853507099e-06, + "loss": 0.7869, + "step": 10146 + }, + { + "epoch": 0.6229166027195433, + "grad_norm": 0.8416622519555785, + "learning_rate": 6.575231678958849e-06, + "loss": 0.7776, + "step": 10147 + }, + { + "epoch": 0.6229779919580097, + "grad_norm": 0.6008614528430986, + "learning_rate": 6.573363639810012e-06, + "loss": 0.7169, + "step": 10148 + }, + { + "epoch": 0.6230393811964763, + "grad_norm": 0.8668208011242634, + "learning_rate": 6.571495736134435e-06, + "loss": 0.7906, + "step": 10149 + }, + { + "epoch": 0.6231007704349427, + "grad_norm": 0.9375143167892399, + "learning_rate": 6.569627968005972e-06, + "loss": 0.8031, + "step": 10150 + }, + { + "epoch": 0.6231621596734093, + "grad_norm": 0.8677568797510058, + "learning_rate": 6.567760335498461e-06, + "loss": 0.8328, + "step": 10151 + }, + { + "epoch": 0.6232235489118757, + "grad_norm": 0.87143138968463, + "learning_rate": 6.565892838685739e-06, + "loss": 0.7315, + "step": 10152 + }, + { + "epoch": 0.6232849381503422, + "grad_norm": 0.8996099487575702, + "learning_rate": 6.56402547764164e-06, + "loss": 0.8355, + "step": 10153 + }, + { + "epoch": 0.6233463273888088, + "grad_norm": 0.9464141849340635, + "learning_rate": 6.5621582524399915e-06, + "loss": 0.7871, + "step": 10154 + }, + { + "epoch": 0.6234077166272752, + "grad_norm": 0.8191052217427682, + "learning_rate": 6.5602911631546165e-06, + "loss": 0.7996, + "step": 10155 + }, + { + "epoch": 0.6234691058657418, + "grad_norm": 0.8426214215993408, + "learning_rate": 6.558424209859327e-06, + "loss": 0.7996, + "step": 10156 + }, + { + "epoch": 0.6235304951042082, + "grad_norm": 0.917386653402422, + "learning_rate": 6.556557392627936e-06, + "loss": 0.7898, + "step": 10157 + }, + { + "epoch": 0.6235918843426748, + "grad_norm": 0.914425685650769, + "learning_rate": 6.554690711534245e-06, + "loss": 0.7914, + "step": 10158 + }, + { + "epoch": 0.6236532735811412, + "grad_norm": 0.8069669823654941, + "learning_rate": 6.552824166652059e-06, + "loss": 0.7931, + "step": 10159 + }, + { + "epoch": 0.6237146628196077, + "grad_norm": 0.8902733131808432, + "learning_rate": 6.550957758055173e-06, + "loss": 0.7717, + "step": 10160 + }, + { + "epoch": 0.6237760520580742, + "grad_norm": 0.8191168069332323, + "learning_rate": 6.549091485817369e-06, + "loss": 0.8068, + "step": 10161 + }, + { + "epoch": 0.6238374412965407, + "grad_norm": 0.8334407954284633, + "learning_rate": 6.547225350012438e-06, + "loss": 0.8474, + "step": 10162 + }, + { + "epoch": 0.6238988305350072, + "grad_norm": 0.9424096079199304, + "learning_rate": 6.545359350714153e-06, + "loss": 0.8653, + "step": 10163 + }, + { + "epoch": 0.6239602197734737, + "grad_norm": 0.8536970535161453, + "learning_rate": 6.543493487996293e-06, + "loss": 0.8311, + "step": 10164 + }, + { + "epoch": 0.6240216090119403, + "grad_norm": 0.9925821999839679, + "learning_rate": 6.541627761932623e-06, + "loss": 0.8274, + "step": 10165 + }, + { + "epoch": 0.6240829982504067, + "grad_norm": 0.846255077048435, + "learning_rate": 6.539762172596901e-06, + "loss": 0.8252, + "step": 10166 + }, + { + "epoch": 0.6241443874888732, + "grad_norm": 0.8487402029414649, + "learning_rate": 6.5378967200628885e-06, + "loss": 0.8035, + "step": 10167 + }, + { + "epoch": 0.6242057767273397, + "grad_norm": 0.8746870188111721, + "learning_rate": 6.536031404404333e-06, + "loss": 0.7982, + "step": 10168 + }, + { + "epoch": 0.6242671659658062, + "grad_norm": 0.763166116632638, + "learning_rate": 6.5341662256949844e-06, + "loss": 0.8208, + "step": 10169 + }, + { + "epoch": 0.6243285552042727, + "grad_norm": 0.7436845140860696, + "learning_rate": 6.532301184008585e-06, + "loss": 0.7396, + "step": 10170 + }, + { + "epoch": 0.6243899444427392, + "grad_norm": 0.7817702405212157, + "learning_rate": 6.530436279418864e-06, + "loss": 0.7996, + "step": 10171 + }, + { + "epoch": 0.6244513336812056, + "grad_norm": 0.9928227537795625, + "learning_rate": 6.52857151199955e-06, + "loss": 0.8135, + "step": 10172 + }, + { + "epoch": 0.6245127229196722, + "grad_norm": 0.8458418926531792, + "learning_rate": 6.526706881824373e-06, + "loss": 0.7404, + "step": 10173 + }, + { + "epoch": 0.6245741121581386, + "grad_norm": 0.9150630507794955, + "learning_rate": 6.524842388967048e-06, + "loss": 0.8291, + "step": 10174 + }, + { + "epoch": 0.6246355013966052, + "grad_norm": 0.9642255359901928, + "learning_rate": 6.522978033501293e-06, + "loss": 0.8214, + "step": 10175 + }, + { + "epoch": 0.6246968906350717, + "grad_norm": 0.852610606354081, + "learning_rate": 6.521113815500812e-06, + "loss": 0.8285, + "step": 10176 + }, + { + "epoch": 0.6247582798735382, + "grad_norm": 0.832630755632229, + "learning_rate": 6.519249735039306e-06, + "loss": 0.7824, + "step": 10177 + }, + { + "epoch": 0.6248196691120047, + "grad_norm": 0.8580811367883231, + "learning_rate": 6.517385792190476e-06, + "loss": 0.8167, + "step": 10178 + }, + { + "epoch": 0.6248810583504711, + "grad_norm": 0.9235387879612424, + "learning_rate": 6.515521987028009e-06, + "loss": 0.8451, + "step": 10179 + }, + { + "epoch": 0.6249424475889377, + "grad_norm": 0.9325652113329815, + "learning_rate": 6.5136583196256e-06, + "loss": 0.7525, + "step": 10180 + }, + { + "epoch": 0.6250038368274041, + "grad_norm": 0.8723182585952217, + "learning_rate": 6.51179479005692e-06, + "loss": 0.7996, + "step": 10181 + }, + { + "epoch": 0.6250652260658707, + "grad_norm": 0.909674307236729, + "learning_rate": 6.509931398395648e-06, + "loss": 0.8244, + "step": 10182 + }, + { + "epoch": 0.6251266153043371, + "grad_norm": 0.9148863949469874, + "learning_rate": 6.508068144715455e-06, + "loss": 0.7831, + "step": 10183 + }, + { + "epoch": 0.6251880045428037, + "grad_norm": 0.89911250655353, + "learning_rate": 6.506205029090005e-06, + "loss": 0.8116, + "step": 10184 + }, + { + "epoch": 0.6252493937812701, + "grad_norm": 0.9179507492423188, + "learning_rate": 6.504342051592958e-06, + "loss": 0.8207, + "step": 10185 + }, + { + "epoch": 0.6253107830197366, + "grad_norm": 0.8330485110374434, + "learning_rate": 6.50247921229796e-06, + "loss": 0.7814, + "step": 10186 + }, + { + "epoch": 0.6253721722582032, + "grad_norm": 0.9191515638180824, + "learning_rate": 6.50061651127867e-06, + "loss": 0.7992, + "step": 10187 + }, + { + "epoch": 0.6254335614966696, + "grad_norm": 0.8016381847585733, + "learning_rate": 6.498753948608722e-06, + "loss": 0.8224, + "step": 10188 + }, + { + "epoch": 0.6254949507351362, + "grad_norm": 0.8921721042568264, + "learning_rate": 6.496891524361757e-06, + "loss": 0.8136, + "step": 10189 + }, + { + "epoch": 0.6255563399736026, + "grad_norm": 0.8017600081818255, + "learning_rate": 6.49502923861141e-06, + "loss": 0.7495, + "step": 10190 + }, + { + "epoch": 0.6256177292120692, + "grad_norm": 0.8986272653532598, + "learning_rate": 6.493167091431298e-06, + "loss": 0.8673, + "step": 10191 + }, + { + "epoch": 0.6256791184505356, + "grad_norm": 0.839333175572983, + "learning_rate": 6.49130508289505e-06, + "loss": 0.8216, + "step": 10192 + }, + { + "epoch": 0.6257405076890021, + "grad_norm": 0.8396155539445415, + "learning_rate": 6.4894432130762745e-06, + "loss": 0.8162, + "step": 10193 + }, + { + "epoch": 0.6258018969274686, + "grad_norm": 0.9427445738978255, + "learning_rate": 6.487581482048586e-06, + "loss": 0.8079, + "step": 10194 + }, + { + "epoch": 0.6258632861659351, + "grad_norm": 0.9173137190721062, + "learning_rate": 6.485719889885591e-06, + "loss": 0.8475, + "step": 10195 + }, + { + "epoch": 0.6259246754044016, + "grad_norm": 0.8843828336479502, + "learning_rate": 6.483858436660882e-06, + "loss": 0.849, + "step": 10196 + }, + { + "epoch": 0.6259860646428681, + "grad_norm": 0.8065060504310801, + "learning_rate": 6.481997122448052e-06, + "loss": 0.8238, + "step": 10197 + }, + { + "epoch": 0.6260474538813346, + "grad_norm": 0.8396276005331791, + "learning_rate": 6.4801359473206935e-06, + "loss": 0.8292, + "step": 10198 + }, + { + "epoch": 0.6261088431198011, + "grad_norm": 0.8709680006133377, + "learning_rate": 6.478274911352385e-06, + "loss": 0.8143, + "step": 10199 + }, + { + "epoch": 0.6261702323582676, + "grad_norm": 0.8270568926571392, + "learning_rate": 6.4764140146167075e-06, + "loss": 0.7402, + "step": 10200 + }, + { + "epoch": 0.6262316215967341, + "grad_norm": 0.8394373724076124, + "learning_rate": 6.474553257187229e-06, + "loss": 0.8031, + "step": 10201 + }, + { + "epoch": 0.6262930108352006, + "grad_norm": 0.7517300505354726, + "learning_rate": 6.472692639137513e-06, + "loss": 0.7943, + "step": 10202 + }, + { + "epoch": 0.626354400073667, + "grad_norm": 0.8253138313764421, + "learning_rate": 6.470832160541125e-06, + "loss": 0.7477, + "step": 10203 + }, + { + "epoch": 0.6264157893121336, + "grad_norm": 0.8445910023504215, + "learning_rate": 6.468971821471619e-06, + "loss": 0.8105, + "step": 10204 + }, + { + "epoch": 0.6264771785506, + "grad_norm": 0.8378350121787463, + "learning_rate": 6.467111622002538e-06, + "loss": 0.7789, + "step": 10205 + }, + { + "epoch": 0.6265385677890666, + "grad_norm": 0.8378781034624838, + "learning_rate": 6.465251562207431e-06, + "loss": 0.772, + "step": 10206 + }, + { + "epoch": 0.6265999570275331, + "grad_norm": 0.8665630575806884, + "learning_rate": 6.463391642159833e-06, + "loss": 0.8001, + "step": 10207 + }, + { + "epoch": 0.6266613462659996, + "grad_norm": 0.8694855934055816, + "learning_rate": 6.461531861933281e-06, + "loss": 0.7419, + "step": 10208 + }, + { + "epoch": 0.6267227355044661, + "grad_norm": 0.852676865559685, + "learning_rate": 6.459672221601301e-06, + "loss": 0.7847, + "step": 10209 + }, + { + "epoch": 0.6267841247429325, + "grad_norm": 0.9134513742095144, + "learning_rate": 6.457812721237411e-06, + "loss": 0.8147, + "step": 10210 + }, + { + "epoch": 0.6268455139813991, + "grad_norm": 0.8920336772974954, + "learning_rate": 6.455953360915128e-06, + "loss": 0.7585, + "step": 10211 + }, + { + "epoch": 0.6269069032198655, + "grad_norm": 0.8708842971320814, + "learning_rate": 6.454094140707965e-06, + "loss": 0.7671, + "step": 10212 + }, + { + "epoch": 0.6269682924583321, + "grad_norm": 0.9587051975588307, + "learning_rate": 6.452235060689423e-06, + "loss": 0.8256, + "step": 10213 + }, + { + "epoch": 0.6270296816967985, + "grad_norm": 0.942089310840063, + "learning_rate": 6.450376120933008e-06, + "loss": 0.7874, + "step": 10214 + }, + { + "epoch": 0.6270910709352651, + "grad_norm": 0.9860516990033023, + "learning_rate": 6.448517321512209e-06, + "loss": 0.8299, + "step": 10215 + }, + { + "epoch": 0.6271524601737315, + "grad_norm": 0.8327387007769183, + "learning_rate": 6.446658662500512e-06, + "loss": 0.7701, + "step": 10216 + }, + { + "epoch": 0.627213849412198, + "grad_norm": 0.91287471993199, + "learning_rate": 6.444800143971404e-06, + "loss": 0.7434, + "step": 10217 + }, + { + "epoch": 0.6272752386506646, + "grad_norm": 0.9927129385600691, + "learning_rate": 6.442941765998361e-06, + "loss": 0.8445, + "step": 10218 + }, + { + "epoch": 0.627336627889131, + "grad_norm": 1.0497695046366091, + "learning_rate": 6.441083528654857e-06, + "loss": 0.7947, + "step": 10219 + }, + { + "epoch": 0.6273980171275976, + "grad_norm": 0.9678238190053886, + "learning_rate": 6.439225432014353e-06, + "loss": 0.8466, + "step": 10220 + }, + { + "epoch": 0.627459406366064, + "grad_norm": 0.8522668207066549, + "learning_rate": 6.437367476150312e-06, + "loss": 0.7834, + "step": 10221 + }, + { + "epoch": 0.6275207956045306, + "grad_norm": 0.9173716711597549, + "learning_rate": 6.4355096611361875e-06, + "loss": 0.8093, + "step": 10222 + }, + { + "epoch": 0.627582184842997, + "grad_norm": 0.8819242869205203, + "learning_rate": 6.433651987045433e-06, + "loss": 0.7761, + "step": 10223 + }, + { + "epoch": 0.6276435740814635, + "grad_norm": 0.8353340295475833, + "learning_rate": 6.431794453951491e-06, + "loss": 0.8036, + "step": 10224 + }, + { + "epoch": 0.62770496331993, + "grad_norm": 0.7887655969631424, + "learning_rate": 6.429937061927795e-06, + "loss": 0.7842, + "step": 10225 + }, + { + "epoch": 0.6277663525583965, + "grad_norm": 0.8646560973089593, + "learning_rate": 6.428079811047781e-06, + "loss": 0.8123, + "step": 10226 + }, + { + "epoch": 0.627827741796863, + "grad_norm": 0.7993606191390132, + "learning_rate": 6.426222701384876e-06, + "loss": 0.7982, + "step": 10227 + }, + { + "epoch": 0.6278891310353295, + "grad_norm": 0.8300374986283627, + "learning_rate": 6.424365733012503e-06, + "loss": 0.7729, + "step": 10228 + }, + { + "epoch": 0.627950520273796, + "grad_norm": 0.8522567471199625, + "learning_rate": 6.422508906004079e-06, + "loss": 0.7935, + "step": 10229 + }, + { + "epoch": 0.6280119095122625, + "grad_norm": 0.9095201248646002, + "learning_rate": 6.420652220433006e-06, + "loss": 0.8008, + "step": 10230 + }, + { + "epoch": 0.628073298750729, + "grad_norm": 0.8645829791422043, + "learning_rate": 6.418795676372698e-06, + "loss": 0.8194, + "step": 10231 + }, + { + "epoch": 0.6281346879891955, + "grad_norm": 0.9505161651497278, + "learning_rate": 6.416939273896547e-06, + "loss": 0.7642, + "step": 10232 + }, + { + "epoch": 0.628196077227662, + "grad_norm": 0.9120843029480259, + "learning_rate": 6.415083013077954e-06, + "loss": 0.7995, + "step": 10233 + }, + { + "epoch": 0.6282574664661285, + "grad_norm": 0.9133632496007794, + "learning_rate": 6.413226893990303e-06, + "loss": 0.824, + "step": 10234 + }, + { + "epoch": 0.628318855704595, + "grad_norm": 0.850317824548271, + "learning_rate": 6.411370916706976e-06, + "loss": 0.7318, + "step": 10235 + }, + { + "epoch": 0.6283802449430614, + "grad_norm": 0.8581465383972755, + "learning_rate": 6.409515081301347e-06, + "loss": 0.8074, + "step": 10236 + }, + { + "epoch": 0.628441634181528, + "grad_norm": 0.9701100675963231, + "learning_rate": 6.407659387846792e-06, + "loss": 0.8369, + "step": 10237 + }, + { + "epoch": 0.6285030234199944, + "grad_norm": 0.9712790316646794, + "learning_rate": 6.405803836416673e-06, + "loss": 0.7992, + "step": 10238 + }, + { + "epoch": 0.628564412658461, + "grad_norm": 0.8390731661303007, + "learning_rate": 6.403948427084356e-06, + "loss": 0.7829, + "step": 10239 + }, + { + "epoch": 0.6286258018969275, + "grad_norm": 0.5960610158046113, + "learning_rate": 6.402093159923188e-06, + "loss": 0.6696, + "step": 10240 + }, + { + "epoch": 0.628687191135394, + "grad_norm": 0.870546113746258, + "learning_rate": 6.400238035006519e-06, + "loss": 0.8228, + "step": 10241 + }, + { + "epoch": 0.6287485803738605, + "grad_norm": 0.8647699516004775, + "learning_rate": 6.398383052407695e-06, + "loss": 0.7861, + "step": 10242 + }, + { + "epoch": 0.6288099696123269, + "grad_norm": 0.7593358711416133, + "learning_rate": 6.396528212200048e-06, + "loss": 0.8023, + "step": 10243 + }, + { + "epoch": 0.6288713588507935, + "grad_norm": 0.9718724944193887, + "learning_rate": 6.3946735144569194e-06, + "loss": 0.7469, + "step": 10244 + }, + { + "epoch": 0.6289327480892599, + "grad_norm": 0.8587086726284697, + "learning_rate": 6.392818959251628e-06, + "loss": 0.7735, + "step": 10245 + }, + { + "epoch": 0.6289941373277265, + "grad_norm": 0.8366886939975205, + "learning_rate": 6.390964546657492e-06, + "loss": 0.7455, + "step": 10246 + }, + { + "epoch": 0.6290555265661929, + "grad_norm": 0.9177504065517996, + "learning_rate": 6.389110276747834e-06, + "loss": 0.7971, + "step": 10247 + }, + { + "epoch": 0.6291169158046594, + "grad_norm": 0.8869526170564443, + "learning_rate": 6.387256149595957e-06, + "loss": 0.779, + "step": 10248 + }, + { + "epoch": 0.6291783050431259, + "grad_norm": 0.8111406212088972, + "learning_rate": 6.38540216527517e-06, + "loss": 0.7401, + "step": 10249 + }, + { + "epoch": 0.6292396942815924, + "grad_norm": 0.9014236161129522, + "learning_rate": 6.3835483238587635e-06, + "loss": 0.7717, + "step": 10250 + }, + { + "epoch": 0.629301083520059, + "grad_norm": 0.9711891760392253, + "learning_rate": 6.3816946254200366e-06, + "loss": 0.7931, + "step": 10251 + }, + { + "epoch": 0.6293624727585254, + "grad_norm": 0.9653176752479766, + "learning_rate": 6.379841070032269e-06, + "loss": 0.7757, + "step": 10252 + }, + { + "epoch": 0.629423861996992, + "grad_norm": 0.8253670828637442, + "learning_rate": 6.3779876577687495e-06, + "loss": 0.7841, + "step": 10253 + }, + { + "epoch": 0.6294852512354584, + "grad_norm": 0.9524118878133555, + "learning_rate": 6.376134388702751e-06, + "loss": 0.8054, + "step": 10254 + }, + { + "epoch": 0.629546640473925, + "grad_norm": 0.8919375904233773, + "learning_rate": 6.374281262907538e-06, + "loss": 0.7926, + "step": 10255 + }, + { + "epoch": 0.6296080297123914, + "grad_norm": 0.8806456907384835, + "learning_rate": 6.372428280456382e-06, + "loss": 0.8141, + "step": 10256 + }, + { + "epoch": 0.6296694189508579, + "grad_norm": 0.9935078373597043, + "learning_rate": 6.370575441422533e-06, + "loss": 0.8342, + "step": 10257 + }, + { + "epoch": 0.6297308081893244, + "grad_norm": 0.7328057045545242, + "learning_rate": 6.368722745879252e-06, + "loss": 0.7925, + "step": 10258 + }, + { + "epoch": 0.6297921974277909, + "grad_norm": 0.9958431159831328, + "learning_rate": 6.366870193899784e-06, + "loss": 0.8283, + "step": 10259 + }, + { + "epoch": 0.6298535866662575, + "grad_norm": 0.791478590513215, + "learning_rate": 6.365017785557367e-06, + "loss": 0.8292, + "step": 10260 + }, + { + "epoch": 0.6299149759047239, + "grad_norm": 0.8499302782958407, + "learning_rate": 6.363165520925237e-06, + "loss": 0.7935, + "step": 10261 + }, + { + "epoch": 0.6299763651431904, + "grad_norm": 0.8980986810604847, + "learning_rate": 6.361313400076625e-06, + "loss": 0.7567, + "step": 10262 + }, + { + "epoch": 0.6300377543816569, + "grad_norm": 0.8887611825567626, + "learning_rate": 6.359461423084754e-06, + "loss": 0.775, + "step": 10263 + }, + { + "epoch": 0.6300991436201234, + "grad_norm": 0.8434995481022607, + "learning_rate": 6.357609590022849e-06, + "loss": 0.8061, + "step": 10264 + }, + { + "epoch": 0.6301605328585899, + "grad_norm": 0.7874072295456344, + "learning_rate": 6.3557579009641144e-06, + "loss": 0.8152, + "step": 10265 + }, + { + "epoch": 0.6302219220970564, + "grad_norm": 0.9200445194078501, + "learning_rate": 6.353906355981759e-06, + "loss": 0.7616, + "step": 10266 + }, + { + "epoch": 0.6302833113355228, + "grad_norm": 0.8377388336652357, + "learning_rate": 6.352054955148989e-06, + "loss": 0.7866, + "step": 10267 + }, + { + "epoch": 0.6303447005739894, + "grad_norm": 0.8851855555206781, + "learning_rate": 6.350203698538998e-06, + "loss": 0.7745, + "step": 10268 + }, + { + "epoch": 0.6304060898124558, + "grad_norm": 0.924684405578122, + "learning_rate": 6.348352586224972e-06, + "loss": 0.8066, + "step": 10269 + }, + { + "epoch": 0.6304674790509224, + "grad_norm": 0.8823050878027162, + "learning_rate": 6.346501618280101e-06, + "loss": 0.8096, + "step": 10270 + }, + { + "epoch": 0.6305288682893889, + "grad_norm": 0.8870471721723493, + "learning_rate": 6.344650794777558e-06, + "loss": 0.8163, + "step": 10271 + }, + { + "epoch": 0.6305902575278554, + "grad_norm": 0.9119723407232712, + "learning_rate": 6.342800115790522e-06, + "loss": 0.817, + "step": 10272 + }, + { + "epoch": 0.6306516467663219, + "grad_norm": 0.8540909113480227, + "learning_rate": 6.340949581392159e-06, + "loss": 0.7456, + "step": 10273 + }, + { + "epoch": 0.6307130360047883, + "grad_norm": 0.9211762027556003, + "learning_rate": 6.339099191655629e-06, + "loss": 0.8426, + "step": 10274 + }, + { + "epoch": 0.6307744252432549, + "grad_norm": 0.8583005891114804, + "learning_rate": 6.337248946654084e-06, + "loss": 0.8348, + "step": 10275 + }, + { + "epoch": 0.6308358144817213, + "grad_norm": 0.9399924928000735, + "learning_rate": 6.33539884646068e-06, + "loss": 0.8145, + "step": 10276 + }, + { + "epoch": 0.6308972037201879, + "grad_norm": 0.8570825640320707, + "learning_rate": 6.333548891148558e-06, + "loss": 0.7983, + "step": 10277 + }, + { + "epoch": 0.6309585929586543, + "grad_norm": 0.9051271077464266, + "learning_rate": 6.331699080790861e-06, + "loss": 0.786, + "step": 10278 + }, + { + "epoch": 0.6310199821971209, + "grad_norm": 0.9668216802843782, + "learning_rate": 6.3298494154607175e-06, + "loss": 0.8323, + "step": 10279 + }, + { + "epoch": 0.6310813714355873, + "grad_norm": 0.92726835653731, + "learning_rate": 6.327999895231254e-06, + "loss": 0.7738, + "step": 10280 + }, + { + "epoch": 0.6311427606740538, + "grad_norm": 0.9288062970148904, + "learning_rate": 6.326150520175596e-06, + "loss": 0.789, + "step": 10281 + }, + { + "epoch": 0.6312041499125204, + "grad_norm": 0.8840187548360893, + "learning_rate": 6.324301290366854e-06, + "loss": 0.7718, + "step": 10282 + }, + { + "epoch": 0.6312655391509868, + "grad_norm": 0.9148805916898946, + "learning_rate": 6.3224522058781455e-06, + "loss": 0.7839, + "step": 10283 + }, + { + "epoch": 0.6313269283894534, + "grad_norm": 0.8226102840914459, + "learning_rate": 6.320603266782568e-06, + "loss": 0.7527, + "step": 10284 + }, + { + "epoch": 0.6313883176279198, + "grad_norm": 0.8597896373882474, + "learning_rate": 6.318754473153221e-06, + "loss": 0.8385, + "step": 10285 + }, + { + "epoch": 0.6314497068663864, + "grad_norm": 0.939824155806749, + "learning_rate": 6.3169058250631995e-06, + "loss": 0.7901, + "step": 10286 + }, + { + "epoch": 0.6315110961048528, + "grad_norm": 0.8674374069378168, + "learning_rate": 6.315057322585589e-06, + "loss": 0.8205, + "step": 10287 + }, + { + "epoch": 0.6315724853433193, + "grad_norm": 0.640047543048391, + "learning_rate": 6.313208965793474e-06, + "loss": 0.7206, + "step": 10288 + }, + { + "epoch": 0.6316338745817858, + "grad_norm": 0.9452848274516523, + "learning_rate": 6.311360754759923e-06, + "loss": 0.781, + "step": 10289 + }, + { + "epoch": 0.6316952638202523, + "grad_norm": 0.8701789628104069, + "learning_rate": 6.309512689558012e-06, + "loss": 0.7882, + "step": 10290 + }, + { + "epoch": 0.6317566530587188, + "grad_norm": 0.6051168476415164, + "learning_rate": 6.307664770260799e-06, + "loss": 0.6532, + "step": 10291 + }, + { + "epoch": 0.6318180422971853, + "grad_norm": 0.9174254712531463, + "learning_rate": 6.3058169969413484e-06, + "loss": 0.7562, + "step": 10292 + }, + { + "epoch": 0.6318794315356518, + "grad_norm": 0.9812872933361175, + "learning_rate": 6.303969369672712e-06, + "loss": 0.8215, + "step": 10293 + }, + { + "epoch": 0.6319408207741183, + "grad_norm": 0.8325595629151409, + "learning_rate": 6.30212188852793e-06, + "loss": 0.7748, + "step": 10294 + }, + { + "epoch": 0.6320022100125848, + "grad_norm": 0.9562875179711356, + "learning_rate": 6.300274553580049e-06, + "loss": 0.7795, + "step": 10295 + }, + { + "epoch": 0.6320635992510513, + "grad_norm": 0.9027683900757834, + "learning_rate": 6.298427364902101e-06, + "loss": 0.811, + "step": 10296 + }, + { + "epoch": 0.6321249884895178, + "grad_norm": 0.8678202428155115, + "learning_rate": 6.296580322567119e-06, + "loss": 0.8137, + "step": 10297 + }, + { + "epoch": 0.6321863777279843, + "grad_norm": 0.9373379956245854, + "learning_rate": 6.294733426648125e-06, + "loss": 0.8091, + "step": 10298 + }, + { + "epoch": 0.6322477669664508, + "grad_norm": 0.8902294102640398, + "learning_rate": 6.292886677218134e-06, + "loss": 0.7901, + "step": 10299 + }, + { + "epoch": 0.6323091562049172, + "grad_norm": 0.9092252206354962, + "learning_rate": 6.291040074350159e-06, + "loss": 0.7606, + "step": 10300 + }, + { + "epoch": 0.6323705454433838, + "grad_norm": 0.920534393518629, + "learning_rate": 6.289193618117207e-06, + "loss": 0.8205, + "step": 10301 + }, + { + "epoch": 0.6324319346818502, + "grad_norm": 0.8883117575831971, + "learning_rate": 6.287347308592277e-06, + "loss": 0.7941, + "step": 10302 + }, + { + "epoch": 0.6324933239203168, + "grad_norm": 0.8695869184267124, + "learning_rate": 6.285501145848368e-06, + "loss": 0.7712, + "step": 10303 + }, + { + "epoch": 0.6325547131587833, + "grad_norm": 0.8539012641362607, + "learning_rate": 6.283655129958463e-06, + "loss": 0.7394, + "step": 10304 + }, + { + "epoch": 0.6326161023972497, + "grad_norm": 0.88343267943547, + "learning_rate": 6.2818092609955465e-06, + "loss": 0.8151, + "step": 10305 + }, + { + "epoch": 0.6326774916357163, + "grad_norm": 0.8451893105733421, + "learning_rate": 6.279963539032597e-06, + "loss": 0.8114, + "step": 10306 + }, + { + "epoch": 0.6327388808741827, + "grad_norm": 0.9097112140981782, + "learning_rate": 6.278117964142584e-06, + "loss": 0.7788, + "step": 10307 + }, + { + "epoch": 0.6328002701126493, + "grad_norm": 0.8740087441031624, + "learning_rate": 6.276272536398478e-06, + "loss": 0.8386, + "step": 10308 + }, + { + "epoch": 0.6328616593511157, + "grad_norm": 0.8861195359611189, + "learning_rate": 6.274427255873231e-06, + "loss": 0.8132, + "step": 10309 + }, + { + "epoch": 0.6329230485895823, + "grad_norm": 0.8993709267491602, + "learning_rate": 6.272582122639799e-06, + "loss": 0.7654, + "step": 10310 + }, + { + "epoch": 0.6329844378280487, + "grad_norm": 0.895902165164412, + "learning_rate": 6.2707371367711345e-06, + "loss": 0.7751, + "step": 10311 + }, + { + "epoch": 0.6330458270665152, + "grad_norm": 0.5951479739414024, + "learning_rate": 6.268892298340173e-06, + "loss": 0.6835, + "step": 10312 + }, + { + "epoch": 0.6331072163049818, + "grad_norm": 0.8226763379475319, + "learning_rate": 6.2670476074198606e-06, + "loss": 0.784, + "step": 10313 + }, + { + "epoch": 0.6331686055434482, + "grad_norm": 0.8883077333893625, + "learning_rate": 6.265203064083117e-06, + "loss": 0.8203, + "step": 10314 + }, + { + "epoch": 0.6332299947819148, + "grad_norm": 0.8338829173214521, + "learning_rate": 6.2633586684028705e-06, + "loss": 0.7606, + "step": 10315 + }, + { + "epoch": 0.6332913840203812, + "grad_norm": 0.8386059377758874, + "learning_rate": 6.261514420452041e-06, + "loss": 0.7087, + "step": 10316 + }, + { + "epoch": 0.6333527732588478, + "grad_norm": 0.976671958555953, + "learning_rate": 6.259670320303542e-06, + "loss": 0.7673, + "step": 10317 + }, + { + "epoch": 0.6334141624973142, + "grad_norm": 0.892530105327169, + "learning_rate": 6.257826368030283e-06, + "loss": 0.8008, + "step": 10318 + }, + { + "epoch": 0.6334755517357807, + "grad_norm": 0.9102609993663229, + "learning_rate": 6.255982563705159e-06, + "loss": 0.7924, + "step": 10319 + }, + { + "epoch": 0.6335369409742472, + "grad_norm": 0.8908780518333891, + "learning_rate": 6.254138907401068e-06, + "loss": 0.7443, + "step": 10320 + }, + { + "epoch": 0.6335983302127137, + "grad_norm": 0.9970198814321561, + "learning_rate": 6.252295399190899e-06, + "loss": 0.8398, + "step": 10321 + }, + { + "epoch": 0.6336597194511802, + "grad_norm": 0.935148935550805, + "learning_rate": 6.250452039147541e-06, + "loss": 0.7498, + "step": 10322 + }, + { + "epoch": 0.6337211086896467, + "grad_norm": 0.8753997896724978, + "learning_rate": 6.248608827343868e-06, + "loss": 0.7669, + "step": 10323 + }, + { + "epoch": 0.6337824979281133, + "grad_norm": 0.8265988044366377, + "learning_rate": 6.246765763852749e-06, + "loss": 0.7806, + "step": 10324 + }, + { + "epoch": 0.6338438871665797, + "grad_norm": 0.9154984204021466, + "learning_rate": 6.244922848747055e-06, + "loss": 0.8337, + "step": 10325 + }, + { + "epoch": 0.6339052764050462, + "grad_norm": 0.8519878859054266, + "learning_rate": 6.243080082099644e-06, + "loss": 0.775, + "step": 10326 + }, + { + "epoch": 0.6339666656435127, + "grad_norm": 0.8178217291676131, + "learning_rate": 6.2412374639833685e-06, + "loss": 0.7747, + "step": 10327 + }, + { + "epoch": 0.6340280548819792, + "grad_norm": 0.953010643980257, + "learning_rate": 6.239394994471084e-06, + "loss": 0.7975, + "step": 10328 + }, + { + "epoch": 0.6340894441204457, + "grad_norm": 0.8391139232379359, + "learning_rate": 6.237552673635625e-06, + "loss": 0.7942, + "step": 10329 + }, + { + "epoch": 0.6341508333589122, + "grad_norm": 0.8853063582905237, + "learning_rate": 6.235710501549832e-06, + "loss": 0.7948, + "step": 10330 + }, + { + "epoch": 0.6342122225973786, + "grad_norm": 0.8527165891012569, + "learning_rate": 6.233868478286536e-06, + "loss": 0.7681, + "step": 10331 + }, + { + "epoch": 0.6342736118358452, + "grad_norm": 0.9592111592789807, + "learning_rate": 6.232026603918564e-06, + "loss": 0.7689, + "step": 10332 + }, + { + "epoch": 0.6343350010743116, + "grad_norm": 0.9322367826698182, + "learning_rate": 6.23018487851873e-06, + "loss": 0.7999, + "step": 10333 + }, + { + "epoch": 0.6343963903127782, + "grad_norm": 0.8955875889863689, + "learning_rate": 6.228343302159852e-06, + "loss": 0.8461, + "step": 10334 + }, + { + "epoch": 0.6344577795512447, + "grad_norm": 0.9359966333680227, + "learning_rate": 6.226501874914732e-06, + "loss": 0.8308, + "step": 10335 + }, + { + "epoch": 0.6345191687897112, + "grad_norm": 0.9251457734188218, + "learning_rate": 6.224660596856178e-06, + "loss": 0.7777, + "step": 10336 + }, + { + "epoch": 0.6345805580281777, + "grad_norm": 0.9263171971016936, + "learning_rate": 6.222819468056984e-06, + "loss": 0.835, + "step": 10337 + }, + { + "epoch": 0.6346419472666441, + "grad_norm": 0.7788185830735653, + "learning_rate": 6.220978488589937e-06, + "loss": 0.7882, + "step": 10338 + }, + { + "epoch": 0.6347033365051107, + "grad_norm": 0.8522942960567667, + "learning_rate": 6.219137658527819e-06, + "loss": 0.8237, + "step": 10339 + }, + { + "epoch": 0.6347647257435771, + "grad_norm": 0.8928448953499376, + "learning_rate": 6.2172969779434135e-06, + "loss": 0.7573, + "step": 10340 + }, + { + "epoch": 0.6348261149820437, + "grad_norm": 0.944137043837663, + "learning_rate": 6.215456446909487e-06, + "loss": 0.7006, + "step": 10341 + }, + { + "epoch": 0.6348875042205101, + "grad_norm": 0.9160519657658088, + "learning_rate": 6.213616065498813e-06, + "loss": 0.7913, + "step": 10342 + }, + { + "epoch": 0.6349488934589766, + "grad_norm": 0.8092080915341989, + "learning_rate": 6.211775833784146e-06, + "loss": 0.7627, + "step": 10343 + }, + { + "epoch": 0.6350102826974431, + "grad_norm": 0.8728915120190462, + "learning_rate": 6.209935751838238e-06, + "loss": 0.8184, + "step": 10344 + }, + { + "epoch": 0.6350716719359096, + "grad_norm": 0.8464438981850354, + "learning_rate": 6.2080958197338415e-06, + "loss": 0.8379, + "step": 10345 + }, + { + "epoch": 0.6351330611743762, + "grad_norm": 0.7832721714740196, + "learning_rate": 6.206256037543697e-06, + "loss": 0.7537, + "step": 10346 + }, + { + "epoch": 0.6351944504128426, + "grad_norm": 0.8682818058427894, + "learning_rate": 6.204416405340546e-06, + "loss": 0.7932, + "step": 10347 + }, + { + "epoch": 0.6352558396513092, + "grad_norm": 0.9180185107071973, + "learning_rate": 6.202576923197112e-06, + "loss": 0.7948, + "step": 10348 + }, + { + "epoch": 0.6353172288897756, + "grad_norm": 0.9388151410861069, + "learning_rate": 6.20073759118612e-06, + "loss": 0.7766, + "step": 10349 + }, + { + "epoch": 0.6353786181282421, + "grad_norm": 0.986482787474881, + "learning_rate": 6.198898409380294e-06, + "loss": 0.789, + "step": 10350 + }, + { + "epoch": 0.6354400073667086, + "grad_norm": 0.9078241183186285, + "learning_rate": 6.19705937785234e-06, + "loss": 0.7626, + "step": 10351 + }, + { + "epoch": 0.6355013966051751, + "grad_norm": 0.9378048174008242, + "learning_rate": 6.195220496674976e-06, + "loss": 0.767, + "step": 10352 + }, + { + "epoch": 0.6355627858436416, + "grad_norm": 0.8509671094544221, + "learning_rate": 6.193381765920888e-06, + "loss": 0.7833, + "step": 10353 + }, + { + "epoch": 0.6356241750821081, + "grad_norm": 0.837589452940642, + "learning_rate": 6.191543185662781e-06, + "loss": 0.7797, + "step": 10354 + }, + { + "epoch": 0.6356855643205747, + "grad_norm": 0.8430037066869491, + "learning_rate": 6.189704755973338e-06, + "loss": 0.766, + "step": 10355 + }, + { + "epoch": 0.6357469535590411, + "grad_norm": 0.92453754008418, + "learning_rate": 6.1878664769252476e-06, + "loss": 0.8351, + "step": 10356 + }, + { + "epoch": 0.6358083427975076, + "grad_norm": 0.840901348147174, + "learning_rate": 6.1860283485911854e-06, + "loss": 0.7845, + "step": 10357 + }, + { + "epoch": 0.6358697320359741, + "grad_norm": 0.906652470528547, + "learning_rate": 6.184190371043817e-06, + "loss": 0.762, + "step": 10358 + }, + { + "epoch": 0.6359311212744406, + "grad_norm": 0.9017766427540128, + "learning_rate": 6.182352544355814e-06, + "loss": 0.7527, + "step": 10359 + }, + { + "epoch": 0.6359925105129071, + "grad_norm": 0.9524705188076581, + "learning_rate": 6.180514868599832e-06, + "loss": 0.8017, + "step": 10360 + }, + { + "epoch": 0.6360538997513736, + "grad_norm": 0.8598018487898846, + "learning_rate": 6.1786773438485274e-06, + "loss": 0.7531, + "step": 10361 + }, + { + "epoch": 0.63611528898984, + "grad_norm": 0.7501005938239074, + "learning_rate": 6.176839970174545e-06, + "loss": 0.7313, + "step": 10362 + }, + { + "epoch": 0.6361766782283066, + "grad_norm": 0.918810388332303, + "learning_rate": 6.175002747650524e-06, + "loss": 0.7984, + "step": 10363 + }, + { + "epoch": 0.636238067466773, + "grad_norm": 0.9385776462255326, + "learning_rate": 6.173165676349103e-06, + "loss": 0.7771, + "step": 10364 + }, + { + "epoch": 0.6362994567052396, + "grad_norm": 0.7794522693840465, + "learning_rate": 6.171328756342911e-06, + "loss": 0.7502, + "step": 10365 + }, + { + "epoch": 0.6363608459437061, + "grad_norm": 0.8303642450326206, + "learning_rate": 6.169491987704568e-06, + "loss": 0.8143, + "step": 10366 + }, + { + "epoch": 0.6364222351821726, + "grad_norm": 0.8911394359741833, + "learning_rate": 6.167655370506698e-06, + "loss": 0.799, + "step": 10367 + }, + { + "epoch": 0.6364836244206391, + "grad_norm": 0.9295710370536137, + "learning_rate": 6.165818904821906e-06, + "loss": 0.7899, + "step": 10368 + }, + { + "epoch": 0.6365450136591055, + "grad_norm": 0.8902150182341565, + "learning_rate": 6.1639825907227964e-06, + "loss": 0.7963, + "step": 10369 + }, + { + "epoch": 0.6366064028975721, + "grad_norm": 0.9564349609251565, + "learning_rate": 6.162146428281976e-06, + "loss": 0.8343, + "step": 10370 + }, + { + "epoch": 0.6366677921360385, + "grad_norm": 0.9503485196757707, + "learning_rate": 6.1603104175720286e-06, + "loss": 0.832, + "step": 10371 + }, + { + "epoch": 0.6367291813745051, + "grad_norm": 0.9546158663371994, + "learning_rate": 6.1584745586655526e-06, + "loss": 0.7889, + "step": 10372 + }, + { + "epoch": 0.6367905706129715, + "grad_norm": 0.927388583462173, + "learning_rate": 6.156638851635121e-06, + "loss": 0.8116, + "step": 10373 + }, + { + "epoch": 0.636851959851438, + "grad_norm": 0.9277487370730364, + "learning_rate": 6.154803296553307e-06, + "loss": 0.8032, + "step": 10374 + }, + { + "epoch": 0.6369133490899045, + "grad_norm": 0.8434696309228337, + "learning_rate": 6.15296789349269e-06, + "loss": 0.8247, + "step": 10375 + }, + { + "epoch": 0.636974738328371, + "grad_norm": 0.9217040652402541, + "learning_rate": 6.151132642525822e-06, + "loss": 0.782, + "step": 10376 + }, + { + "epoch": 0.6370361275668376, + "grad_norm": 0.8862037277624202, + "learning_rate": 6.149297543725274e-06, + "loss": 0.7605, + "step": 10377 + }, + { + "epoch": 0.637097516805304, + "grad_norm": 0.8243752681392946, + "learning_rate": 6.147462597163583e-06, + "loss": 0.778, + "step": 10378 + }, + { + "epoch": 0.6371589060437706, + "grad_norm": 0.6074878791350038, + "learning_rate": 6.145627802913301e-06, + "loss": 0.7185, + "step": 10379 + }, + { + "epoch": 0.637220295282237, + "grad_norm": 0.915126700408988, + "learning_rate": 6.143793161046965e-06, + "loss": 0.7834, + "step": 10380 + }, + { + "epoch": 0.6372816845207036, + "grad_norm": 0.8717333112635167, + "learning_rate": 6.141958671637112e-06, + "loss": 0.7926, + "step": 10381 + }, + { + "epoch": 0.63734307375917, + "grad_norm": 0.882529993002439, + "learning_rate": 6.14012433475627e-06, + "loss": 0.7557, + "step": 10382 + }, + { + "epoch": 0.6374044629976365, + "grad_norm": 0.9427767016765921, + "learning_rate": 6.138290150476952e-06, + "loss": 0.8421, + "step": 10383 + }, + { + "epoch": 0.637465852236103, + "grad_norm": 1.0264144236105917, + "learning_rate": 6.136456118871681e-06, + "loss": 0.856, + "step": 10384 + }, + { + "epoch": 0.6375272414745695, + "grad_norm": 0.9489117118336464, + "learning_rate": 6.1346222400129595e-06, + "loss": 0.7974, + "step": 10385 + }, + { + "epoch": 0.637588630713036, + "grad_norm": 0.9148592165678417, + "learning_rate": 6.132788513973298e-06, + "loss": 0.8081, + "step": 10386 + }, + { + "epoch": 0.6376500199515025, + "grad_norm": 0.8101839568823842, + "learning_rate": 6.130954940825191e-06, + "loss": 0.7401, + "step": 10387 + }, + { + "epoch": 0.637711409189969, + "grad_norm": 0.7841507009676094, + "learning_rate": 6.129121520641126e-06, + "loss": 0.7641, + "step": 10388 + }, + { + "epoch": 0.6377727984284355, + "grad_norm": 0.8949261655489413, + "learning_rate": 6.127288253493591e-06, + "loss": 0.7339, + "step": 10389 + }, + { + "epoch": 0.637834187666902, + "grad_norm": 0.8639930041534247, + "learning_rate": 6.125455139455061e-06, + "loss": 0.8208, + "step": 10390 + }, + { + "epoch": 0.6378955769053685, + "grad_norm": 0.9179582633028258, + "learning_rate": 6.123622178598015e-06, + "loss": 0.8177, + "step": 10391 + }, + { + "epoch": 0.637956966143835, + "grad_norm": 0.8015809781334382, + "learning_rate": 6.1217893709949196e-06, + "loss": 0.7675, + "step": 10392 + }, + { + "epoch": 0.6380183553823014, + "grad_norm": 0.9816760926830116, + "learning_rate": 6.11995671671823e-06, + "loss": 0.8205, + "step": 10393 + }, + { + "epoch": 0.638079744620768, + "grad_norm": 0.8541102012237467, + "learning_rate": 6.1181242158404e-06, + "loss": 0.7734, + "step": 10394 + }, + { + "epoch": 0.6381411338592344, + "grad_norm": 0.5960354736455087, + "learning_rate": 6.116291868433883e-06, + "loss": 0.6221, + "step": 10395 + }, + { + "epoch": 0.638202523097701, + "grad_norm": 0.7690077534144532, + "learning_rate": 6.11445967457112e-06, + "loss": 0.7588, + "step": 10396 + }, + { + "epoch": 0.6382639123361674, + "grad_norm": 0.9047372275876974, + "learning_rate": 6.112627634324551e-06, + "loss": 0.7816, + "step": 10397 + }, + { + "epoch": 0.638325301574634, + "grad_norm": 0.894813968821997, + "learning_rate": 6.1107957477666e-06, + "loss": 0.814, + "step": 10398 + }, + { + "epoch": 0.6383866908131005, + "grad_norm": 0.8715763962737285, + "learning_rate": 6.108964014969691e-06, + "loss": 0.781, + "step": 10399 + }, + { + "epoch": 0.638448080051567, + "grad_norm": 0.9767771505896992, + "learning_rate": 6.107132436006249e-06, + "loss": 0.7811, + "step": 10400 + }, + { + "epoch": 0.6385094692900335, + "grad_norm": 0.8984850762374383, + "learning_rate": 6.105301010948684e-06, + "loss": 0.7873, + "step": 10401 + }, + { + "epoch": 0.6385708585284999, + "grad_norm": 0.9736760437353259, + "learning_rate": 6.103469739869397e-06, + "loss": 0.8544, + "step": 10402 + }, + { + "epoch": 0.6386322477669665, + "grad_norm": 0.7852946259520245, + "learning_rate": 6.101638622840792e-06, + "loss": 0.7227, + "step": 10403 + }, + { + "epoch": 0.6386936370054329, + "grad_norm": 0.9093215073860574, + "learning_rate": 6.099807659935263e-06, + "loss": 0.8241, + "step": 10404 + }, + { + "epoch": 0.6387550262438995, + "grad_norm": 0.7577062282265684, + "learning_rate": 6.097976851225194e-06, + "loss": 0.7809, + "step": 10405 + }, + { + "epoch": 0.6388164154823659, + "grad_norm": 0.8865622787657056, + "learning_rate": 6.096146196782975e-06, + "loss": 0.7558, + "step": 10406 + }, + { + "epoch": 0.6388778047208324, + "grad_norm": 0.8061308790804619, + "learning_rate": 6.0943156966809726e-06, + "loss": 0.7527, + "step": 10407 + }, + { + "epoch": 0.638939193959299, + "grad_norm": 0.5866915368985114, + "learning_rate": 6.092485350991558e-06, + "loss": 0.6622, + "step": 10408 + }, + { + "epoch": 0.6390005831977654, + "grad_norm": 0.8212731192650815, + "learning_rate": 6.0906551597871e-06, + "loss": 0.7793, + "step": 10409 + }, + { + "epoch": 0.639061972436232, + "grad_norm": 1.0562905161233287, + "learning_rate": 6.0888251231399474e-06, + "loss": 0.7753, + "step": 10410 + }, + { + "epoch": 0.6391233616746984, + "grad_norm": 0.9076586607138392, + "learning_rate": 6.086995241122462e-06, + "loss": 0.7938, + "step": 10411 + }, + { + "epoch": 0.639184750913165, + "grad_norm": 0.7527011663543506, + "learning_rate": 6.085165513806981e-06, + "loss": 0.7599, + "step": 10412 + }, + { + "epoch": 0.6392461401516314, + "grad_norm": 0.9376360305599849, + "learning_rate": 6.083335941265842e-06, + "loss": 0.8054, + "step": 10413 + }, + { + "epoch": 0.6393075293900979, + "grad_norm": 0.8699017127695797, + "learning_rate": 6.081506523571384e-06, + "loss": 0.8089, + "step": 10414 + }, + { + "epoch": 0.6393689186285644, + "grad_norm": 0.9024019977316973, + "learning_rate": 6.079677260795929e-06, + "loss": 0.8106, + "step": 10415 + }, + { + "epoch": 0.6394303078670309, + "grad_norm": 1.0110364174252808, + "learning_rate": 6.077848153011805e-06, + "loss": 0.8113, + "step": 10416 + }, + { + "epoch": 0.6394916971054974, + "grad_norm": 0.92189601518916, + "learning_rate": 6.076019200291314e-06, + "loss": 0.7825, + "step": 10417 + }, + { + "epoch": 0.6395530863439639, + "grad_norm": 0.8665758371650675, + "learning_rate": 6.074190402706774e-06, + "loss": 0.7833, + "step": 10418 + }, + { + "epoch": 0.6396144755824305, + "grad_norm": 0.9847415163734965, + "learning_rate": 6.072361760330481e-06, + "loss": 0.7293, + "step": 10419 + }, + { + "epoch": 0.6396758648208969, + "grad_norm": 1.0554080146912013, + "learning_rate": 6.070533273234737e-06, + "loss": 0.7943, + "step": 10420 + }, + { + "epoch": 0.6397372540593634, + "grad_norm": 0.9010132018812312, + "learning_rate": 6.06870494149183e-06, + "loss": 0.7994, + "step": 10421 + }, + { + "epoch": 0.6397986432978299, + "grad_norm": 0.9245891793418624, + "learning_rate": 6.066876765174039e-06, + "loss": 0.7663, + "step": 10422 + }, + { + "epoch": 0.6398600325362964, + "grad_norm": 0.7969256088519383, + "learning_rate": 6.0650487443536474e-06, + "loss": 0.779, + "step": 10423 + }, + { + "epoch": 0.6399214217747629, + "grad_norm": 0.8447868287459404, + "learning_rate": 6.063220879102924e-06, + "loss": 0.7527, + "step": 10424 + }, + { + "epoch": 0.6399828110132294, + "grad_norm": 0.883309274773421, + "learning_rate": 6.061393169494134e-06, + "loss": 0.7933, + "step": 10425 + }, + { + "epoch": 0.6400442002516958, + "grad_norm": 0.9111585852453616, + "learning_rate": 6.059565615599541e-06, + "loss": 0.8115, + "step": 10426 + }, + { + "epoch": 0.6401055894901624, + "grad_norm": 0.9570837141641468, + "learning_rate": 6.057738217491389e-06, + "loss": 0.8249, + "step": 10427 + }, + { + "epoch": 0.6401669787286288, + "grad_norm": 0.8392052514353376, + "learning_rate": 6.055910975241933e-06, + "loss": 0.8116, + "step": 10428 + }, + { + "epoch": 0.6402283679670954, + "grad_norm": 0.862647709799252, + "learning_rate": 6.0540838889234076e-06, + "loss": 0.7436, + "step": 10429 + }, + { + "epoch": 0.6402897572055619, + "grad_norm": 0.8703275886779651, + "learning_rate": 6.052256958608054e-06, + "loss": 0.7341, + "step": 10430 + }, + { + "epoch": 0.6403511464440284, + "grad_norm": 0.9451650112784169, + "learning_rate": 6.050430184368097e-06, + "loss": 0.8032, + "step": 10431 + }, + { + "epoch": 0.6404125356824949, + "grad_norm": 0.991148429959784, + "learning_rate": 6.048603566275757e-06, + "loss": 0.7876, + "step": 10432 + }, + { + "epoch": 0.6404739249209613, + "grad_norm": 0.9168897085957773, + "learning_rate": 6.04677710440325e-06, + "loss": 0.7846, + "step": 10433 + }, + { + "epoch": 0.6405353141594279, + "grad_norm": 0.933248542116053, + "learning_rate": 6.044950798822789e-06, + "loss": 0.8085, + "step": 10434 + }, + { + "epoch": 0.6405967033978943, + "grad_norm": 1.0613410670935293, + "learning_rate": 6.043124649606575e-06, + "loss": 0.7998, + "step": 10435 + }, + { + "epoch": 0.6406580926363609, + "grad_norm": 0.8273775769041479, + "learning_rate": 6.04129865682681e-06, + "loss": 0.8104, + "step": 10436 + }, + { + "epoch": 0.6407194818748273, + "grad_norm": 0.8684028275379765, + "learning_rate": 6.0394728205556795e-06, + "loss": 0.761, + "step": 10437 + }, + { + "epoch": 0.6407808711132938, + "grad_norm": 0.998259193667824, + "learning_rate": 6.037647140865368e-06, + "loss": 0.8565, + "step": 10438 + }, + { + "epoch": 0.6408422603517603, + "grad_norm": 0.9246622447398116, + "learning_rate": 6.03582161782806e-06, + "loss": 0.7851, + "step": 10439 + }, + { + "epoch": 0.6409036495902268, + "grad_norm": 0.9547677709070885, + "learning_rate": 6.033996251515924e-06, + "loss": 0.8389, + "step": 10440 + }, + { + "epoch": 0.6409650388286934, + "grad_norm": 0.8352886089170941, + "learning_rate": 6.032171042001132e-06, + "loss": 0.7805, + "step": 10441 + }, + { + "epoch": 0.6410264280671598, + "grad_norm": 0.9542572765585318, + "learning_rate": 6.030345989355837e-06, + "loss": 0.7514, + "step": 10442 + }, + { + "epoch": 0.6410878173056264, + "grad_norm": 0.8723989296639303, + "learning_rate": 6.028521093652195e-06, + "loss": 0.7621, + "step": 10443 + }, + { + "epoch": 0.6411492065440928, + "grad_norm": 0.9599891478335648, + "learning_rate": 6.026696354962356e-06, + "loss": 0.8185, + "step": 10444 + }, + { + "epoch": 0.6412105957825593, + "grad_norm": 0.9238986483566641, + "learning_rate": 6.024871773358461e-06, + "loss": 0.7851, + "step": 10445 + }, + { + "epoch": 0.6412719850210258, + "grad_norm": 0.820387092098579, + "learning_rate": 6.0230473489126475e-06, + "loss": 0.8136, + "step": 10446 + }, + { + "epoch": 0.6413333742594923, + "grad_norm": 0.9188428198623012, + "learning_rate": 6.021223081697039e-06, + "loss": 0.809, + "step": 10447 + }, + { + "epoch": 0.6413947634979588, + "grad_norm": 0.81574349837035, + "learning_rate": 6.019398971783764e-06, + "loss": 0.7744, + "step": 10448 + }, + { + "epoch": 0.6414561527364253, + "grad_norm": 0.8954076526856806, + "learning_rate": 6.017575019244935e-06, + "loss": 0.7719, + "step": 10449 + }, + { + "epoch": 0.6415175419748917, + "grad_norm": 0.7998215764037467, + "learning_rate": 6.0157512241526685e-06, + "loss": 0.7545, + "step": 10450 + }, + { + "epoch": 0.6415789312133583, + "grad_norm": 0.965076033435866, + "learning_rate": 6.013927586579065e-06, + "loss": 0.8162, + "step": 10451 + }, + { + "epoch": 0.6416403204518248, + "grad_norm": 0.9102911462980732, + "learning_rate": 6.0121041065962204e-06, + "loss": 0.7781, + "step": 10452 + }, + { + "epoch": 0.6417017096902913, + "grad_norm": 0.8309997732976389, + "learning_rate": 6.0102807842762315e-06, + "loss": 0.7786, + "step": 10453 + }, + { + "epoch": 0.6417630989287578, + "grad_norm": 0.878883848462516, + "learning_rate": 6.0084576196911796e-06, + "loss": 0.8145, + "step": 10454 + }, + { + "epoch": 0.6418244881672243, + "grad_norm": 0.8537240256827271, + "learning_rate": 6.006634612913147e-06, + "loss": 0.7477, + "step": 10455 + }, + { + "epoch": 0.6418858774056908, + "grad_norm": 0.9080527879192556, + "learning_rate": 6.0048117640142085e-06, + "loss": 0.8491, + "step": 10456 + }, + { + "epoch": 0.6419472666441572, + "grad_norm": 0.8886203146987481, + "learning_rate": 6.002989073066427e-06, + "loss": 0.7951, + "step": 10457 + }, + { + "epoch": 0.6420086558826238, + "grad_norm": 0.9337646279156596, + "learning_rate": 6.001166540141864e-06, + "loss": 0.8008, + "step": 10458 + }, + { + "epoch": 0.6420700451210902, + "grad_norm": 0.9000708293813589, + "learning_rate": 5.999344165312576e-06, + "loss": 0.7984, + "step": 10459 + }, + { + "epoch": 0.6421314343595568, + "grad_norm": 0.9776000125742687, + "learning_rate": 5.997521948650609e-06, + "loss": 0.8153, + "step": 10460 + }, + { + "epoch": 0.6421928235980233, + "grad_norm": 0.9369057714961934, + "learning_rate": 5.995699890228008e-06, + "loss": 0.7814, + "step": 10461 + }, + { + "epoch": 0.6422542128364898, + "grad_norm": 0.856223334026813, + "learning_rate": 5.993877990116808e-06, + "loss": 0.7601, + "step": 10462 + }, + { + "epoch": 0.6423156020749563, + "grad_norm": 0.9044376522231166, + "learning_rate": 5.992056248389033e-06, + "loss": 0.7951, + "step": 10463 + }, + { + "epoch": 0.6423769913134227, + "grad_norm": 0.9101301306129528, + "learning_rate": 5.990234665116713e-06, + "loss": 0.8096, + "step": 10464 + }, + { + "epoch": 0.6424383805518893, + "grad_norm": 0.9542727586439006, + "learning_rate": 5.988413240371864e-06, + "loss": 0.7833, + "step": 10465 + }, + { + "epoch": 0.6424997697903557, + "grad_norm": 0.8520298949418355, + "learning_rate": 5.986591974226492e-06, + "loss": 0.7625, + "step": 10466 + }, + { + "epoch": 0.6425611590288223, + "grad_norm": 0.9299452244117525, + "learning_rate": 5.984770866752606e-06, + "loss": 0.8024, + "step": 10467 + }, + { + "epoch": 0.6426225482672887, + "grad_norm": 0.9178240187637792, + "learning_rate": 5.982949918022201e-06, + "loss": 0.7919, + "step": 10468 + }, + { + "epoch": 0.6426839375057553, + "grad_norm": 0.7963499101790086, + "learning_rate": 5.9811291281072725e-06, + "loss": 0.7297, + "step": 10469 + }, + { + "epoch": 0.6427453267442217, + "grad_norm": 0.8824126857326974, + "learning_rate": 5.979308497079805e-06, + "loss": 0.7957, + "step": 10470 + }, + { + "epoch": 0.6428067159826882, + "grad_norm": 0.9539378006823412, + "learning_rate": 5.9774880250117755e-06, + "loss": 0.7799, + "step": 10471 + }, + { + "epoch": 0.6428681052211548, + "grad_norm": 0.9155081402901355, + "learning_rate": 5.975667711975156e-06, + "loss": 0.7559, + "step": 10472 + }, + { + "epoch": 0.6429294944596212, + "grad_norm": 0.9384671293585958, + "learning_rate": 5.973847558041917e-06, + "loss": 0.7789, + "step": 10473 + }, + { + "epoch": 0.6429908836980878, + "grad_norm": 0.8655833455998778, + "learning_rate": 5.972027563284016e-06, + "loss": 0.8112, + "step": 10474 + }, + { + "epoch": 0.6430522729365542, + "grad_norm": 0.8352618164184669, + "learning_rate": 5.970207727773414e-06, + "loss": 0.7729, + "step": 10475 + }, + { + "epoch": 0.6431136621750208, + "grad_norm": 0.8565571158977259, + "learning_rate": 5.968388051582049e-06, + "loss": 0.765, + "step": 10476 + }, + { + "epoch": 0.6431750514134872, + "grad_norm": 0.7378049489816492, + "learning_rate": 5.966568534781866e-06, + "loss": 0.7664, + "step": 10477 + }, + { + "epoch": 0.6432364406519537, + "grad_norm": 0.8563627791551824, + "learning_rate": 5.964749177444803e-06, + "loss": 0.7763, + "step": 10478 + }, + { + "epoch": 0.6432978298904202, + "grad_norm": 0.7748701392359992, + "learning_rate": 5.962929979642784e-06, + "loss": 0.7374, + "step": 10479 + }, + { + "epoch": 0.6433592191288867, + "grad_norm": 0.8654988606564207, + "learning_rate": 5.961110941447741e-06, + "loss": 0.7557, + "step": 10480 + }, + { + "epoch": 0.6434206083673532, + "grad_norm": 1.03445590496987, + "learning_rate": 5.959292062931581e-06, + "loss": 0.8334, + "step": 10481 + }, + { + "epoch": 0.6434819976058197, + "grad_norm": 0.9041858470682888, + "learning_rate": 5.957473344166216e-06, + "loss": 0.8325, + "step": 10482 + }, + { + "epoch": 0.6435433868442862, + "grad_norm": 0.9098235052543937, + "learning_rate": 5.955654785223549e-06, + "loss": 0.8312, + "step": 10483 + }, + { + "epoch": 0.6436047760827527, + "grad_norm": 0.9187914488679407, + "learning_rate": 5.9538363861754825e-06, + "loss": 0.7748, + "step": 10484 + }, + { + "epoch": 0.6436661653212192, + "grad_norm": 0.8632188567464143, + "learning_rate": 5.952018147093904e-06, + "loss": 0.7523, + "step": 10485 + }, + { + "epoch": 0.6437275545596857, + "grad_norm": 0.9683972123901504, + "learning_rate": 5.950200068050696e-06, + "loss": 0.7739, + "step": 10486 + }, + { + "epoch": 0.6437889437981522, + "grad_norm": 1.0040981031007536, + "learning_rate": 5.948382149117739e-06, + "loss": 0.8359, + "step": 10487 + }, + { + "epoch": 0.6438503330366186, + "grad_norm": 0.7790735269105342, + "learning_rate": 5.946564390366905e-06, + "loss": 0.7837, + "step": 10488 + }, + { + "epoch": 0.6439117222750852, + "grad_norm": 0.8221689203170243, + "learning_rate": 5.944746791870062e-06, + "loss": 0.7356, + "step": 10489 + }, + { + "epoch": 0.6439731115135516, + "grad_norm": 0.809772948052486, + "learning_rate": 5.9429293536990685e-06, + "loss": 0.7873, + "step": 10490 + }, + { + "epoch": 0.6440345007520182, + "grad_norm": 0.8416452788880711, + "learning_rate": 5.941112075925773e-06, + "loss": 0.7724, + "step": 10491 + }, + { + "epoch": 0.6440958899904846, + "grad_norm": 0.9653948356499846, + "learning_rate": 5.939294958622026e-06, + "loss": 0.771, + "step": 10492 + }, + { + "epoch": 0.6441572792289512, + "grad_norm": 0.8641710169059187, + "learning_rate": 5.937478001859668e-06, + "loss": 0.7747, + "step": 10493 + }, + { + "epoch": 0.6442186684674177, + "grad_norm": 1.0093139499143575, + "learning_rate": 5.935661205710532e-06, + "loss": 0.83, + "step": 10494 + }, + { + "epoch": 0.6442800577058841, + "grad_norm": 0.8841386248976643, + "learning_rate": 5.93384457024645e-06, + "loss": 0.8171, + "step": 10495 + }, + { + "epoch": 0.6443414469443507, + "grad_norm": 0.9378522912162693, + "learning_rate": 5.932028095539237e-06, + "loss": 0.7836, + "step": 10496 + }, + { + "epoch": 0.6444028361828171, + "grad_norm": 0.9216785117050771, + "learning_rate": 5.930211781660708e-06, + "loss": 0.7487, + "step": 10497 + }, + { + "epoch": 0.6444642254212837, + "grad_norm": 0.8453980394540478, + "learning_rate": 5.928395628682677e-06, + "loss": 0.8004, + "step": 10498 + }, + { + "epoch": 0.6445256146597501, + "grad_norm": 0.8106279033728527, + "learning_rate": 5.92657963667694e-06, + "loss": 0.7519, + "step": 10499 + }, + { + "epoch": 0.6445870038982167, + "grad_norm": 0.8638613068380635, + "learning_rate": 5.924763805715301e-06, + "loss": 0.8404, + "step": 10500 + }, + { + "epoch": 0.6446483931366831, + "grad_norm": 0.8889231956225655, + "learning_rate": 5.9229481358695415e-06, + "loss": 0.7902, + "step": 10501 + }, + { + "epoch": 0.6447097823751496, + "grad_norm": 0.9011463596012379, + "learning_rate": 5.921132627211448e-06, + "loss": 0.7684, + "step": 10502 + }, + { + "epoch": 0.6447711716136161, + "grad_norm": 0.8669886909434421, + "learning_rate": 5.9193172798127975e-06, + "loss": 0.7608, + "step": 10503 + }, + { + "epoch": 0.6448325608520826, + "grad_norm": 0.886474723887245, + "learning_rate": 5.917502093745357e-06, + "loss": 0.7694, + "step": 10504 + }, + { + "epoch": 0.6448939500905492, + "grad_norm": 0.913075459708482, + "learning_rate": 5.9156870690809e-06, + "loss": 0.7511, + "step": 10505 + }, + { + "epoch": 0.6449553393290156, + "grad_norm": 0.8610388666803283, + "learning_rate": 5.913872205891174e-06, + "loss": 0.7674, + "step": 10506 + }, + { + "epoch": 0.6450167285674822, + "grad_norm": 0.9652686634613693, + "learning_rate": 5.912057504247935e-06, + "loss": 0.7884, + "step": 10507 + }, + { + "epoch": 0.6450781178059486, + "grad_norm": 0.9100328292162335, + "learning_rate": 5.910242964222923e-06, + "loss": 0.7633, + "step": 10508 + }, + { + "epoch": 0.6451395070444151, + "grad_norm": 0.9679939950356741, + "learning_rate": 5.9084285858878835e-06, + "loss": 0.7828, + "step": 10509 + }, + { + "epoch": 0.6452008962828816, + "grad_norm": 0.9090989230405762, + "learning_rate": 5.906614369314548e-06, + "loss": 0.8003, + "step": 10510 + }, + { + "epoch": 0.6452622855213481, + "grad_norm": 0.9373794093166874, + "learning_rate": 5.904800314574632e-06, + "loss": 0.7732, + "step": 10511 + }, + { + "epoch": 0.6453236747598146, + "grad_norm": 0.8840562684125022, + "learning_rate": 5.902986421739867e-06, + "loss": 0.7548, + "step": 10512 + }, + { + "epoch": 0.6453850639982811, + "grad_norm": 0.8600039033724755, + "learning_rate": 5.901172690881959e-06, + "loss": 0.7647, + "step": 10513 + }, + { + "epoch": 0.6454464532367477, + "grad_norm": 0.8876937519842396, + "learning_rate": 5.899359122072617e-06, + "loss": 0.7679, + "step": 10514 + }, + { + "epoch": 0.6455078424752141, + "grad_norm": 0.8649321490980959, + "learning_rate": 5.897545715383545e-06, + "loss": 0.7898, + "step": 10515 + }, + { + "epoch": 0.6455692317136806, + "grad_norm": 0.8897040791797356, + "learning_rate": 5.895732470886426e-06, + "loss": 0.7367, + "step": 10516 + }, + { + "epoch": 0.6456306209521471, + "grad_norm": 0.5903987467653599, + "learning_rate": 5.893919388652957e-06, + "loss": 0.7562, + "step": 10517 + }, + { + "epoch": 0.6456920101906136, + "grad_norm": 0.8741077237380679, + "learning_rate": 5.892106468754815e-06, + "loss": 0.7757, + "step": 10518 + }, + { + "epoch": 0.64575339942908, + "grad_norm": 0.8909534375389936, + "learning_rate": 5.890293711263674e-06, + "loss": 0.7526, + "step": 10519 + }, + { + "epoch": 0.6458147886675466, + "grad_norm": 0.9670141629049543, + "learning_rate": 5.8884811162512055e-06, + "loss": 0.7739, + "step": 10520 + }, + { + "epoch": 0.645876177906013, + "grad_norm": 0.9189888184450713, + "learning_rate": 5.886668683789067e-06, + "loss": 0.8147, + "step": 10521 + }, + { + "epoch": 0.6459375671444796, + "grad_norm": 0.9676367076857078, + "learning_rate": 5.884856413948913e-06, + "loss": 0.8007, + "step": 10522 + }, + { + "epoch": 0.645998956382946, + "grad_norm": 0.8572684849470059, + "learning_rate": 5.883044306802397e-06, + "loss": 0.7726, + "step": 10523 + }, + { + "epoch": 0.6460603456214126, + "grad_norm": 0.9481984274187927, + "learning_rate": 5.881232362421154e-06, + "loss": 0.8149, + "step": 10524 + }, + { + "epoch": 0.6461217348598791, + "grad_norm": 0.9326261111857782, + "learning_rate": 5.879420580876831e-06, + "loss": 0.8006, + "step": 10525 + }, + { + "epoch": 0.6461831240983456, + "grad_norm": 0.8440426933934527, + "learning_rate": 5.877608962241048e-06, + "loss": 0.7872, + "step": 10526 + }, + { + "epoch": 0.6462445133368121, + "grad_norm": 0.9171522879494947, + "learning_rate": 5.875797506585429e-06, + "loss": 0.7875, + "step": 10527 + }, + { + "epoch": 0.6463059025752785, + "grad_norm": 1.019892603040472, + "learning_rate": 5.873986213981595e-06, + "loss": 0.8127, + "step": 10528 + }, + { + "epoch": 0.6463672918137451, + "grad_norm": 0.8618083102343215, + "learning_rate": 5.872175084501154e-06, + "loss": 0.7439, + "step": 10529 + }, + { + "epoch": 0.6464286810522115, + "grad_norm": 0.8685225954977457, + "learning_rate": 5.870364118215706e-06, + "loss": 0.8218, + "step": 10530 + }, + { + "epoch": 0.6464900702906781, + "grad_norm": 0.9094967500941457, + "learning_rate": 5.868553315196852e-06, + "loss": 0.8189, + "step": 10531 + }, + { + "epoch": 0.6465514595291445, + "grad_norm": 0.9072701339607884, + "learning_rate": 5.866742675516182e-06, + "loss": 0.827, + "step": 10532 + }, + { + "epoch": 0.646612848767611, + "grad_norm": 0.9281612543895693, + "learning_rate": 5.864932199245281e-06, + "loss": 0.7344, + "step": 10533 + }, + { + "epoch": 0.6466742380060775, + "grad_norm": 0.7821489150144505, + "learning_rate": 5.863121886455728e-06, + "loss": 0.7593, + "step": 10534 + }, + { + "epoch": 0.646735627244544, + "grad_norm": 0.9490644764355117, + "learning_rate": 5.861311737219091e-06, + "loss": 0.8075, + "step": 10535 + }, + { + "epoch": 0.6467970164830106, + "grad_norm": 0.8386681123648859, + "learning_rate": 5.859501751606933e-06, + "loss": 0.8316, + "step": 10536 + }, + { + "epoch": 0.646858405721477, + "grad_norm": 0.9525724724794913, + "learning_rate": 5.857691929690819e-06, + "loss": 0.8541, + "step": 10537 + }, + { + "epoch": 0.6469197949599436, + "grad_norm": 0.9772741555641614, + "learning_rate": 5.855882271542296e-06, + "loss": 0.8589, + "step": 10538 + }, + { + "epoch": 0.64698118419841, + "grad_norm": 0.9326925288300809, + "learning_rate": 5.854072777232914e-06, + "loss": 0.7796, + "step": 10539 + }, + { + "epoch": 0.6470425734368765, + "grad_norm": 0.8760764222581429, + "learning_rate": 5.852263446834208e-06, + "loss": 0.777, + "step": 10540 + }, + { + "epoch": 0.647103962675343, + "grad_norm": 0.8668947239517709, + "learning_rate": 5.850454280417709e-06, + "loss": 0.7595, + "step": 10541 + }, + { + "epoch": 0.6471653519138095, + "grad_norm": 0.8618897284098249, + "learning_rate": 5.848645278054947e-06, + "loss": 0.7621, + "step": 10542 + }, + { + "epoch": 0.647226741152276, + "grad_norm": 0.6084500558728578, + "learning_rate": 5.8468364398174395e-06, + "loss": 0.675, + "step": 10543 + }, + { + "epoch": 0.6472881303907425, + "grad_norm": 0.8323118704617027, + "learning_rate": 5.845027765776703e-06, + "loss": 0.8214, + "step": 10544 + }, + { + "epoch": 0.647349519629209, + "grad_norm": 0.9212220997706897, + "learning_rate": 5.84321925600424e-06, + "loss": 0.8033, + "step": 10545 + }, + { + "epoch": 0.6474109088676755, + "grad_norm": 0.9845447281900257, + "learning_rate": 5.841410910571552e-06, + "loss": 0.8111, + "step": 10546 + }, + { + "epoch": 0.647472298106142, + "grad_norm": 0.9796164805595912, + "learning_rate": 5.83960272955013e-06, + "loss": 0.7764, + "step": 10547 + }, + { + "epoch": 0.6475336873446085, + "grad_norm": 0.7516505033790559, + "learning_rate": 5.837794713011465e-06, + "loss": 0.8209, + "step": 10548 + }, + { + "epoch": 0.647595076583075, + "grad_norm": 0.9441838512073126, + "learning_rate": 5.835986861027038e-06, + "loss": 0.7394, + "step": 10549 + }, + { + "epoch": 0.6476564658215415, + "grad_norm": 0.9188123927491283, + "learning_rate": 5.834179173668321e-06, + "loss": 0.7801, + "step": 10550 + }, + { + "epoch": 0.647717855060008, + "grad_norm": 0.8135992581801509, + "learning_rate": 5.832371651006776e-06, + "loss": 0.7991, + "step": 10551 + }, + { + "epoch": 0.6477792442984744, + "grad_norm": 0.9225464678533808, + "learning_rate": 5.830564293113874e-06, + "loss": 0.7805, + "step": 10552 + }, + { + "epoch": 0.647840633536941, + "grad_norm": 0.9303185478758239, + "learning_rate": 5.828757100061067e-06, + "loss": 0.7831, + "step": 10553 + }, + { + "epoch": 0.6479020227754074, + "grad_norm": 0.8682407631895659, + "learning_rate": 5.826950071919798e-06, + "loss": 0.7917, + "step": 10554 + }, + { + "epoch": 0.647963412013874, + "grad_norm": 0.8843436748511894, + "learning_rate": 5.8251432087615135e-06, + "loss": 0.8148, + "step": 10555 + }, + { + "epoch": 0.6480248012523404, + "grad_norm": 0.8557516578453421, + "learning_rate": 5.823336510657647e-06, + "loss": 0.729, + "step": 10556 + }, + { + "epoch": 0.648086190490807, + "grad_norm": 0.9532569942893105, + "learning_rate": 5.821529977679625e-06, + "loss": 0.8226, + "step": 10557 + }, + { + "epoch": 0.6481475797292735, + "grad_norm": 0.5613418078921977, + "learning_rate": 5.819723609898869e-06, + "loss": 0.6404, + "step": 10558 + }, + { + "epoch": 0.6482089689677399, + "grad_norm": 0.9058528792207378, + "learning_rate": 5.817917407386802e-06, + "loss": 0.7978, + "step": 10559 + }, + { + "epoch": 0.6482703582062065, + "grad_norm": 0.8295272415982451, + "learning_rate": 5.816111370214825e-06, + "loss": 0.7725, + "step": 10560 + }, + { + "epoch": 0.6483317474446729, + "grad_norm": 1.0149391310039244, + "learning_rate": 5.814305498454342e-06, + "loss": 0.7961, + "step": 10561 + }, + { + "epoch": 0.6483931366831395, + "grad_norm": 0.9195513781781273, + "learning_rate": 5.812499792176744e-06, + "loss": 0.7551, + "step": 10562 + }, + { + "epoch": 0.6484545259216059, + "grad_norm": 0.965830612041751, + "learning_rate": 5.8106942514534325e-06, + "loss": 0.8516, + "step": 10563 + }, + { + "epoch": 0.6485159151600725, + "grad_norm": 1.0092472262396595, + "learning_rate": 5.808888876355785e-06, + "loss": 0.7943, + "step": 10564 + }, + { + "epoch": 0.6485773043985389, + "grad_norm": 0.8309137202063501, + "learning_rate": 5.807083666955169e-06, + "loss": 0.7858, + "step": 10565 + }, + { + "epoch": 0.6486386936370054, + "grad_norm": 0.9056375190090274, + "learning_rate": 5.805278623322964e-06, + "loss": 0.8067, + "step": 10566 + }, + { + "epoch": 0.648700082875472, + "grad_norm": 0.8533902837993882, + "learning_rate": 5.80347374553053e-06, + "loss": 0.805, + "step": 10567 + }, + { + "epoch": 0.6487614721139384, + "grad_norm": 0.8580445328611921, + "learning_rate": 5.801669033649224e-06, + "loss": 0.7294, + "step": 10568 + }, + { + "epoch": 0.648822861352405, + "grad_norm": 0.8370681854671603, + "learning_rate": 5.799864487750395e-06, + "loss": 0.754, + "step": 10569 + }, + { + "epoch": 0.6488842505908714, + "grad_norm": 0.8623992081815922, + "learning_rate": 5.798060107905387e-06, + "loss": 0.7758, + "step": 10570 + }, + { + "epoch": 0.648945639829338, + "grad_norm": 0.8365056824271637, + "learning_rate": 5.796255894185538e-06, + "loss": 0.7556, + "step": 10571 + }, + { + "epoch": 0.6490070290678044, + "grad_norm": 0.7964317024146118, + "learning_rate": 5.79445184666217e-06, + "loss": 0.7601, + "step": 10572 + }, + { + "epoch": 0.6490684183062709, + "grad_norm": 0.9291878174114618, + "learning_rate": 5.7926479654066195e-06, + "loss": 0.8188, + "step": 10573 + }, + { + "epoch": 0.6491298075447374, + "grad_norm": 0.9060559571293193, + "learning_rate": 5.7908442504902e-06, + "loss": 0.833, + "step": 10574 + }, + { + "epoch": 0.6491911967832039, + "grad_norm": 0.956666245566008, + "learning_rate": 5.789040701984215e-06, + "loss": 0.8006, + "step": 10575 + }, + { + "epoch": 0.6492525860216704, + "grad_norm": 0.9505249346845352, + "learning_rate": 5.787237319959971e-06, + "loss": 0.7639, + "step": 10576 + }, + { + "epoch": 0.6493139752601369, + "grad_norm": 0.9689462251475817, + "learning_rate": 5.78543410448877e-06, + "loss": 0.8288, + "step": 10577 + }, + { + "epoch": 0.6493753644986034, + "grad_norm": 0.9152648433758056, + "learning_rate": 5.783631055641898e-06, + "loss": 0.7818, + "step": 10578 + }, + { + "epoch": 0.6494367537370699, + "grad_norm": 0.8934684877801871, + "learning_rate": 5.781828173490644e-06, + "loss": 0.7529, + "step": 10579 + }, + { + "epoch": 0.6494981429755364, + "grad_norm": 0.8900948187710452, + "learning_rate": 5.780025458106282e-06, + "loss": 0.7842, + "step": 10580 + }, + { + "epoch": 0.6495595322140029, + "grad_norm": 0.9620310642141136, + "learning_rate": 5.778222909560083e-06, + "loss": 0.7955, + "step": 10581 + }, + { + "epoch": 0.6496209214524694, + "grad_norm": 0.9102238469518718, + "learning_rate": 5.776420527923312e-06, + "loss": 0.7678, + "step": 10582 + }, + { + "epoch": 0.6496823106909358, + "grad_norm": 0.9587426082378254, + "learning_rate": 5.774618313267223e-06, + "loss": 0.8166, + "step": 10583 + }, + { + "epoch": 0.6497436999294024, + "grad_norm": 0.8955117962310656, + "learning_rate": 5.7728162656630795e-06, + "loss": 0.8002, + "step": 10584 + }, + { + "epoch": 0.6498050891678688, + "grad_norm": 0.8541138095180167, + "learning_rate": 5.771014385182112e-06, + "loss": 0.7725, + "step": 10585 + }, + { + "epoch": 0.6498664784063354, + "grad_norm": 0.9137692763182302, + "learning_rate": 5.769212671895565e-06, + "loss": 0.7721, + "step": 10586 + }, + { + "epoch": 0.6499278676448018, + "grad_norm": 0.9018944695769898, + "learning_rate": 5.767411125874665e-06, + "loss": 0.8063, + "step": 10587 + }, + { + "epoch": 0.6499892568832684, + "grad_norm": 0.8641670923552558, + "learning_rate": 5.765609747190646e-06, + "loss": 0.804, + "step": 10588 + }, + { + "epoch": 0.6500506461217349, + "grad_norm": 0.9130335407911386, + "learning_rate": 5.7638085359147235e-06, + "loss": 0.757, + "step": 10589 + }, + { + "epoch": 0.6501120353602013, + "grad_norm": 0.7774706276562033, + "learning_rate": 5.762007492118098e-06, + "loss": 0.751, + "step": 10590 + }, + { + "epoch": 0.6501734245986679, + "grad_norm": 0.8859136434977205, + "learning_rate": 5.760206615871987e-06, + "loss": 0.7829, + "step": 10591 + }, + { + "epoch": 0.6502348138371343, + "grad_norm": 0.5896525040011854, + "learning_rate": 5.758405907247585e-06, + "loss": 0.6556, + "step": 10592 + }, + { + "epoch": 0.6502962030756009, + "grad_norm": 0.9127963726393274, + "learning_rate": 5.7566053663160825e-06, + "loss": 0.7521, + "step": 10593 + }, + { + "epoch": 0.6503575923140673, + "grad_norm": 0.960803362587223, + "learning_rate": 5.754804993148666e-06, + "loss": 0.8174, + "step": 10594 + }, + { + "epoch": 0.6504189815525339, + "grad_norm": 0.8151251626494403, + "learning_rate": 5.753004787816512e-06, + "loss": 0.7262, + "step": 10595 + }, + { + "epoch": 0.6504803707910003, + "grad_norm": 0.9910515742147301, + "learning_rate": 5.751204750390793e-06, + "loss": 0.8531, + "step": 10596 + }, + { + "epoch": 0.6505417600294668, + "grad_norm": 0.8213828120330533, + "learning_rate": 5.749404880942672e-06, + "loss": 0.7764, + "step": 10597 + }, + { + "epoch": 0.6506031492679333, + "grad_norm": 0.9620809662615833, + "learning_rate": 5.747605179543317e-06, + "loss": 0.7863, + "step": 10598 + }, + { + "epoch": 0.6506645385063998, + "grad_norm": 0.8655520603015632, + "learning_rate": 5.745805646263868e-06, + "loss": 0.8127, + "step": 10599 + }, + { + "epoch": 0.6507259277448664, + "grad_norm": 0.951094882180742, + "learning_rate": 5.744006281175476e-06, + "loss": 0.8056, + "step": 10600 + }, + { + "epoch": 0.6507873169833328, + "grad_norm": 0.906583642017596, + "learning_rate": 5.742207084349274e-06, + "loss": 0.7621, + "step": 10601 + }, + { + "epoch": 0.6508487062217994, + "grad_norm": 0.8732103933292884, + "learning_rate": 5.740408055856401e-06, + "loss": 0.8183, + "step": 10602 + }, + { + "epoch": 0.6509100954602658, + "grad_norm": 0.8583931814676656, + "learning_rate": 5.7386091957679844e-06, + "loss": 0.7734, + "step": 10603 + }, + { + "epoch": 0.6509714846987323, + "grad_norm": 0.9410578027420051, + "learning_rate": 5.7368105041551305e-06, + "loss": 0.7356, + "step": 10604 + }, + { + "epoch": 0.6510328739371988, + "grad_norm": 0.6549900407013067, + "learning_rate": 5.735011981088962e-06, + "loss": 0.717, + "step": 10605 + }, + { + "epoch": 0.6510942631756653, + "grad_norm": 0.8816910255969611, + "learning_rate": 5.733213626640579e-06, + "loss": 0.7859, + "step": 10606 + }, + { + "epoch": 0.6511556524141318, + "grad_norm": 0.9121800371510468, + "learning_rate": 5.731415440881084e-06, + "loss": 0.7646, + "step": 10607 + }, + { + "epoch": 0.6512170416525983, + "grad_norm": 0.9124834650410584, + "learning_rate": 5.729617423881566e-06, + "loss": 0.7832, + "step": 10608 + }, + { + "epoch": 0.6512784308910647, + "grad_norm": 0.7545452064556845, + "learning_rate": 5.72781957571311e-06, + "loss": 0.7433, + "step": 10609 + }, + { + "epoch": 0.6513398201295313, + "grad_norm": 0.8324825204109315, + "learning_rate": 5.726021896446796e-06, + "loss": 0.7561, + "step": 10610 + }, + { + "epoch": 0.6514012093679978, + "grad_norm": 0.9470360174208602, + "learning_rate": 5.724224386153692e-06, + "loss": 0.8178, + "step": 10611 + }, + { + "epoch": 0.6514625986064643, + "grad_norm": 0.9844768692400225, + "learning_rate": 5.72242704490487e-06, + "loss": 0.8351, + "step": 10612 + }, + { + "epoch": 0.6515239878449308, + "grad_norm": 0.8166927370666666, + "learning_rate": 5.7206298727713885e-06, + "loss": 0.7481, + "step": 10613 + }, + { + "epoch": 0.6515853770833973, + "grad_norm": 0.8085653748963395, + "learning_rate": 5.718832869824291e-06, + "loss": 0.7689, + "step": 10614 + }, + { + "epoch": 0.6516467663218638, + "grad_norm": 0.8976553810587184, + "learning_rate": 5.717036036134625e-06, + "loss": 0.765, + "step": 10615 + }, + { + "epoch": 0.6517081555603302, + "grad_norm": 0.8891704627504866, + "learning_rate": 5.715239371773436e-06, + "loss": 0.7801, + "step": 10616 + }, + { + "epoch": 0.6517695447987968, + "grad_norm": 0.8751805010452658, + "learning_rate": 5.71344287681175e-06, + "loss": 0.7783, + "step": 10617 + }, + { + "epoch": 0.6518309340372632, + "grad_norm": 0.9931383878823649, + "learning_rate": 5.711646551320593e-06, + "loss": 0.7977, + "step": 10618 + }, + { + "epoch": 0.6518923232757298, + "grad_norm": 0.773049120939819, + "learning_rate": 5.709850395370984e-06, + "loss": 0.817, + "step": 10619 + }, + { + "epoch": 0.6519537125141963, + "grad_norm": 0.8559687915778633, + "learning_rate": 5.708054409033934e-06, + "loss": 0.756, + "step": 10620 + }, + { + "epoch": 0.6520151017526628, + "grad_norm": 1.037267419190704, + "learning_rate": 5.706258592380448e-06, + "loss": 0.7915, + "step": 10621 + }, + { + "epoch": 0.6520764909911293, + "grad_norm": 0.9539473097511519, + "learning_rate": 5.70446294548152e-06, + "loss": 0.8057, + "step": 10622 + }, + { + "epoch": 0.6521378802295957, + "grad_norm": 0.8783889983837886, + "learning_rate": 5.702667468408155e-06, + "loss": 0.7628, + "step": 10623 + }, + { + "epoch": 0.6521992694680623, + "grad_norm": 0.6153448246753261, + "learning_rate": 5.700872161231325e-06, + "loss": 0.6612, + "step": 10624 + }, + { + "epoch": 0.6522606587065287, + "grad_norm": 0.9297212739859444, + "learning_rate": 5.699077024022011e-06, + "loss": 0.7557, + "step": 10625 + }, + { + "epoch": 0.6523220479449953, + "grad_norm": 0.7628029882571357, + "learning_rate": 5.6972820568511815e-06, + "loss": 0.7662, + "step": 10626 + }, + { + "epoch": 0.6523834371834617, + "grad_norm": 0.9507403412680124, + "learning_rate": 5.695487259789807e-06, + "loss": 0.7945, + "step": 10627 + }, + { + "epoch": 0.6524448264219282, + "grad_norm": 0.9936025861660956, + "learning_rate": 5.693692632908849e-06, + "loss": 0.7676, + "step": 10628 + }, + { + "epoch": 0.6525062156603947, + "grad_norm": 0.929071591400881, + "learning_rate": 5.6918981762792446e-06, + "loss": 0.7729, + "step": 10629 + }, + { + "epoch": 0.6525676048988612, + "grad_norm": 0.9034847968707451, + "learning_rate": 5.690103889971952e-06, + "loss": 0.7975, + "step": 10630 + }, + { + "epoch": 0.6526289941373278, + "grad_norm": 0.9493944403002119, + "learning_rate": 5.688309774057902e-06, + "loss": 0.7469, + "step": 10631 + }, + { + "epoch": 0.6526903833757942, + "grad_norm": 0.919964883466254, + "learning_rate": 5.686515828608028e-06, + "loss": 0.7606, + "step": 10632 + }, + { + "epoch": 0.6527517726142608, + "grad_norm": 0.8874795013852017, + "learning_rate": 5.684722053693253e-06, + "loss": 0.7739, + "step": 10633 + }, + { + "epoch": 0.6528131618527272, + "grad_norm": 0.8638093750370643, + "learning_rate": 5.682928449384495e-06, + "loss": 0.7835, + "step": 10634 + }, + { + "epoch": 0.6528745510911937, + "grad_norm": 0.9351108355519716, + "learning_rate": 5.6811350157526635e-06, + "loss": 0.7945, + "step": 10635 + }, + { + "epoch": 0.6529359403296602, + "grad_norm": 0.8932591199507255, + "learning_rate": 5.679341752868661e-06, + "loss": 0.8195, + "step": 10636 + }, + { + "epoch": 0.6529973295681267, + "grad_norm": 0.8563246920881528, + "learning_rate": 5.6775486608033915e-06, + "loss": 0.8087, + "step": 10637 + }, + { + "epoch": 0.6530587188065932, + "grad_norm": 0.8308905054939629, + "learning_rate": 5.675755739627747e-06, + "loss": 0.7562, + "step": 10638 + }, + { + "epoch": 0.6531201080450597, + "grad_norm": 0.9088327729810933, + "learning_rate": 5.673962989412599e-06, + "loss": 0.77, + "step": 10639 + }, + { + "epoch": 0.6531814972835261, + "grad_norm": 0.8415682543633494, + "learning_rate": 5.672170410228829e-06, + "loss": 0.7761, + "step": 10640 + }, + { + "epoch": 0.6532428865219927, + "grad_norm": 0.911950340336759, + "learning_rate": 5.670378002147313e-06, + "loss": 0.755, + "step": 10641 + }, + { + "epoch": 0.6533042757604592, + "grad_norm": 0.9658187149317959, + "learning_rate": 5.668585765238912e-06, + "loss": 0.8249, + "step": 10642 + }, + { + "epoch": 0.6533656649989257, + "grad_norm": 0.821459570677332, + "learning_rate": 5.6667936995744796e-06, + "loss": 0.7467, + "step": 10643 + }, + { + "epoch": 0.6534270542373922, + "grad_norm": 0.8989218583584266, + "learning_rate": 5.66500180522487e-06, + "loss": 0.7599, + "step": 10644 + }, + { + "epoch": 0.6534884434758587, + "grad_norm": 0.8153345682856808, + "learning_rate": 5.663210082260924e-06, + "loss": 0.7818, + "step": 10645 + }, + { + "epoch": 0.6535498327143252, + "grad_norm": 0.9690898848162649, + "learning_rate": 5.661418530753477e-06, + "loss": 0.8188, + "step": 10646 + }, + { + "epoch": 0.6536112219527916, + "grad_norm": 0.8714356059271295, + "learning_rate": 5.659627150773357e-06, + "loss": 0.8016, + "step": 10647 + }, + { + "epoch": 0.6536726111912582, + "grad_norm": 0.8529703569514081, + "learning_rate": 5.6578359423913966e-06, + "loss": 0.7631, + "step": 10648 + }, + { + "epoch": 0.6537340004297246, + "grad_norm": 0.8774239943017326, + "learning_rate": 5.656044905678402e-06, + "loss": 0.7959, + "step": 10649 + }, + { + "epoch": 0.6537953896681912, + "grad_norm": 0.8461644852528065, + "learning_rate": 5.654254040705184e-06, + "loss": 0.7981, + "step": 10650 + }, + { + "epoch": 0.6538567789066576, + "grad_norm": 0.9870714938301225, + "learning_rate": 5.652463347542543e-06, + "loss": 0.7796, + "step": 10651 + }, + { + "epoch": 0.6539181681451242, + "grad_norm": 0.891960323016305, + "learning_rate": 5.650672826261283e-06, + "loss": 0.7746, + "step": 10652 + }, + { + "epoch": 0.6539795573835907, + "grad_norm": 0.8952886487086255, + "learning_rate": 5.648882476932192e-06, + "loss": 0.7265, + "step": 10653 + }, + { + "epoch": 0.6540409466220571, + "grad_norm": 0.919918042248514, + "learning_rate": 5.647092299626038e-06, + "loss": 0.7773, + "step": 10654 + }, + { + "epoch": 0.6541023358605237, + "grad_norm": 0.9996354729953602, + "learning_rate": 5.645302294413613e-06, + "loss": 0.7988, + "step": 10655 + }, + { + "epoch": 0.6541637250989901, + "grad_norm": 0.9637787555718393, + "learning_rate": 5.6435124613656764e-06, + "loss": 0.7855, + "step": 10656 + }, + { + "epoch": 0.6542251143374567, + "grad_norm": 0.9032313057581669, + "learning_rate": 5.641722800552994e-06, + "loss": 0.7605, + "step": 10657 + }, + { + "epoch": 0.6542865035759231, + "grad_norm": 0.8609373365325392, + "learning_rate": 5.63993331204632e-06, + "loss": 0.7695, + "step": 10658 + }, + { + "epoch": 0.6543478928143897, + "grad_norm": 0.9018509692695963, + "learning_rate": 5.6381439959164e-06, + "loss": 0.7937, + "step": 10659 + }, + { + "epoch": 0.6544092820528561, + "grad_norm": 0.8840064355510469, + "learning_rate": 5.636354852233976e-06, + "loss": 0.8077, + "step": 10660 + }, + { + "epoch": 0.6544706712913226, + "grad_norm": 0.8486762358115347, + "learning_rate": 5.63456588106978e-06, + "loss": 0.7941, + "step": 10661 + }, + { + "epoch": 0.6545320605297891, + "grad_norm": 0.8428136232331032, + "learning_rate": 5.632777082494551e-06, + "loss": 0.757, + "step": 10662 + }, + { + "epoch": 0.6545934497682556, + "grad_norm": 0.9715642366474873, + "learning_rate": 5.6309884565789974e-06, + "loss": 0.8326, + "step": 10663 + }, + { + "epoch": 0.6546548390067222, + "grad_norm": 0.8658892047271123, + "learning_rate": 5.629200003393838e-06, + "loss": 0.8372, + "step": 10664 + }, + { + "epoch": 0.6547162282451886, + "grad_norm": 0.9087059587712806, + "learning_rate": 5.627411723009772e-06, + "loss": 0.7616, + "step": 10665 + }, + { + "epoch": 0.6547776174836551, + "grad_norm": 0.7960700535510179, + "learning_rate": 5.625623615497514e-06, + "loss": 0.7838, + "step": 10666 + }, + { + "epoch": 0.6548390067221216, + "grad_norm": 0.9721631319741294, + "learning_rate": 5.623835680927754e-06, + "loss": 0.8052, + "step": 10667 + }, + { + "epoch": 0.6549003959605881, + "grad_norm": 0.9664860352855189, + "learning_rate": 5.622047919371165e-06, + "loss": 0.8177, + "step": 10668 + }, + { + "epoch": 0.6549617851990546, + "grad_norm": 0.8451959726616646, + "learning_rate": 5.620260330898441e-06, + "loss": 0.7618, + "step": 10669 + }, + { + "epoch": 0.6550231744375211, + "grad_norm": 0.9226935790223693, + "learning_rate": 5.618472915580253e-06, + "loss": 0.8014, + "step": 10670 + }, + { + "epoch": 0.6550845636759876, + "grad_norm": 0.8120718547407121, + "learning_rate": 5.616685673487263e-06, + "loss": 0.7641, + "step": 10671 + }, + { + "epoch": 0.6551459529144541, + "grad_norm": 0.8561248118847355, + "learning_rate": 5.614898604690132e-06, + "loss": 0.8328, + "step": 10672 + }, + { + "epoch": 0.6552073421529206, + "grad_norm": 0.9861811871805962, + "learning_rate": 5.613111709259512e-06, + "loss": 0.786, + "step": 10673 + }, + { + "epoch": 0.6552687313913871, + "grad_norm": 0.900501106163804, + "learning_rate": 5.611324987266049e-06, + "loss": 0.8131, + "step": 10674 + }, + { + "epoch": 0.6553301206298536, + "grad_norm": 0.9168365097696272, + "learning_rate": 5.609538438780378e-06, + "loss": 0.7643, + "step": 10675 + }, + { + "epoch": 0.6553915098683201, + "grad_norm": 0.8400158443336811, + "learning_rate": 5.607752063873139e-06, + "loss": 0.7861, + "step": 10676 + }, + { + "epoch": 0.6554528991067866, + "grad_norm": 0.9061050120751042, + "learning_rate": 5.605965862614955e-06, + "loss": 0.8444, + "step": 10677 + }, + { + "epoch": 0.655514288345253, + "grad_norm": 0.9476793729558444, + "learning_rate": 5.604179835076437e-06, + "loss": 0.7816, + "step": 10678 + }, + { + "epoch": 0.6555756775837196, + "grad_norm": 0.9243112689441771, + "learning_rate": 5.602393981328198e-06, + "loss": 0.8075, + "step": 10679 + }, + { + "epoch": 0.655637066822186, + "grad_norm": 0.9116889383330824, + "learning_rate": 5.600608301440848e-06, + "loss": 0.7553, + "step": 10680 + }, + { + "epoch": 0.6556984560606526, + "grad_norm": 0.9081143278881485, + "learning_rate": 5.5988227954849826e-06, + "loss": 0.7832, + "step": 10681 + }, + { + "epoch": 0.655759845299119, + "grad_norm": 0.8807019754874861, + "learning_rate": 5.5970374635311905e-06, + "loss": 0.8243, + "step": 10682 + }, + { + "epoch": 0.6558212345375856, + "grad_norm": 0.8745084162559592, + "learning_rate": 5.595252305650056e-06, + "loss": 0.7314, + "step": 10683 + }, + { + "epoch": 0.6558826237760521, + "grad_norm": 0.5652796597348249, + "learning_rate": 5.593467321912157e-06, + "loss": 0.6556, + "step": 10684 + }, + { + "epoch": 0.6559440130145185, + "grad_norm": 0.9015591527832526, + "learning_rate": 5.591682512388062e-06, + "loss": 0.7426, + "step": 10685 + }, + { + "epoch": 0.6560054022529851, + "grad_norm": 0.9748536642921046, + "learning_rate": 5.58989787714833e-06, + "loss": 0.7903, + "step": 10686 + }, + { + "epoch": 0.6560667914914515, + "grad_norm": 0.9099218556482283, + "learning_rate": 5.58811341626353e-06, + "loss": 0.7643, + "step": 10687 + }, + { + "epoch": 0.6561281807299181, + "grad_norm": 0.9699913915986409, + "learning_rate": 5.5863291298042e-06, + "loss": 0.8316, + "step": 10688 + }, + { + "epoch": 0.6561895699683845, + "grad_norm": 0.8849435370038021, + "learning_rate": 5.584545017840886e-06, + "loss": 0.7952, + "step": 10689 + }, + { + "epoch": 0.6562509592068511, + "grad_norm": 0.6021652414652429, + "learning_rate": 5.582761080444117e-06, + "loss": 0.6632, + "step": 10690 + }, + { + "epoch": 0.6563123484453175, + "grad_norm": 0.84803562121768, + "learning_rate": 5.5809773176844325e-06, + "loss": 0.7735, + "step": 10691 + }, + { + "epoch": 0.656373737683784, + "grad_norm": 0.8882947318826283, + "learning_rate": 5.579193729632353e-06, + "loss": 0.7767, + "step": 10692 + }, + { + "epoch": 0.6564351269222505, + "grad_norm": 0.8022308141434775, + "learning_rate": 5.57741031635838e-06, + "loss": 0.734, + "step": 10693 + }, + { + "epoch": 0.656496516160717, + "grad_norm": 0.8934455104180064, + "learning_rate": 5.575627077933038e-06, + "loss": 0.8284, + "step": 10694 + }, + { + "epoch": 0.6565579053991836, + "grad_norm": 0.9284501979162778, + "learning_rate": 5.573844014426819e-06, + "loss": 0.7992, + "step": 10695 + }, + { + "epoch": 0.65661929463765, + "grad_norm": 0.9247546750315797, + "learning_rate": 5.57206112591022e-06, + "loss": 0.8007, + "step": 10696 + }, + { + "epoch": 0.6566806838761166, + "grad_norm": 0.9196943394664004, + "learning_rate": 5.570278412453725e-06, + "loss": 0.758, + "step": 10697 + }, + { + "epoch": 0.656742073114583, + "grad_norm": 0.9568406551498556, + "learning_rate": 5.5684958741278175e-06, + "loss": 0.7614, + "step": 10698 + }, + { + "epoch": 0.6568034623530495, + "grad_norm": 0.9042977904512829, + "learning_rate": 5.566713511002969e-06, + "loss": 0.836, + "step": 10699 + }, + { + "epoch": 0.656864851591516, + "grad_norm": 0.837252661723295, + "learning_rate": 5.564931323149643e-06, + "loss": 0.774, + "step": 10700 + }, + { + "epoch": 0.6569262408299825, + "grad_norm": 0.9034521107625422, + "learning_rate": 5.563149310638305e-06, + "loss": 0.8175, + "step": 10701 + }, + { + "epoch": 0.656987630068449, + "grad_norm": 0.8596148085434002, + "learning_rate": 5.56136747353941e-06, + "loss": 0.8122, + "step": 10702 + }, + { + "epoch": 0.6570490193069155, + "grad_norm": 0.9119548268692262, + "learning_rate": 5.559585811923393e-06, + "loss": 0.8149, + "step": 10703 + }, + { + "epoch": 0.6571104085453819, + "grad_norm": 0.9144521259051341, + "learning_rate": 5.5578043258606955e-06, + "loss": 0.8046, + "step": 10704 + }, + { + "epoch": 0.6571717977838485, + "grad_norm": 0.9036104936285944, + "learning_rate": 5.556023015421755e-06, + "loss": 0.7396, + "step": 10705 + }, + { + "epoch": 0.657233187022315, + "grad_norm": 0.8961955338905715, + "learning_rate": 5.5542418806769915e-06, + "loss": 0.8121, + "step": 10706 + }, + { + "epoch": 0.6572945762607815, + "grad_norm": 0.891967921995613, + "learning_rate": 5.552460921696825e-06, + "loss": 0.7461, + "step": 10707 + }, + { + "epoch": 0.657355965499248, + "grad_norm": 0.8779060052176034, + "learning_rate": 5.550680138551665e-06, + "loss": 0.7523, + "step": 10708 + }, + { + "epoch": 0.6574173547377145, + "grad_norm": 1.0199907134963644, + "learning_rate": 5.548899531311915e-06, + "loss": 0.7591, + "step": 10709 + }, + { + "epoch": 0.657478743976181, + "grad_norm": 0.9270405395275274, + "learning_rate": 5.547119100047975e-06, + "loss": 0.789, + "step": 10710 + }, + { + "epoch": 0.6575401332146474, + "grad_norm": 0.9502966780465371, + "learning_rate": 5.545338844830227e-06, + "loss": 0.7569, + "step": 10711 + }, + { + "epoch": 0.657601522453114, + "grad_norm": 0.9713275591373542, + "learning_rate": 5.543558765729068e-06, + "loss": 0.783, + "step": 10712 + }, + { + "epoch": 0.6576629116915804, + "grad_norm": 0.9326580500734826, + "learning_rate": 5.541778862814862e-06, + "loss": 0.8094, + "step": 10713 + }, + { + "epoch": 0.657724300930047, + "grad_norm": 0.9974043383152075, + "learning_rate": 5.539999136157977e-06, + "loss": 0.7947, + "step": 10714 + }, + { + "epoch": 0.6577856901685135, + "grad_norm": 0.8813186423366625, + "learning_rate": 5.5382195858287844e-06, + "loss": 0.7603, + "step": 10715 + }, + { + "epoch": 0.65784707940698, + "grad_norm": 0.9921796768753928, + "learning_rate": 5.536440211897636e-06, + "loss": 0.83, + "step": 10716 + }, + { + "epoch": 0.6579084686454465, + "grad_norm": 0.9774365205104004, + "learning_rate": 5.534661014434881e-06, + "loss": 0.715, + "step": 10717 + }, + { + "epoch": 0.6579698578839129, + "grad_norm": 0.9409503267976341, + "learning_rate": 5.532881993510852e-06, + "loss": 0.7733, + "step": 10718 + }, + { + "epoch": 0.6580312471223795, + "grad_norm": 0.8568685355336867, + "learning_rate": 5.531103149195891e-06, + "loss": 0.7593, + "step": 10719 + }, + { + "epoch": 0.6580926363608459, + "grad_norm": 0.9577005886943318, + "learning_rate": 5.529324481560327e-06, + "loss": 0.7393, + "step": 10720 + }, + { + "epoch": 0.6581540255993125, + "grad_norm": 0.8899360170653986, + "learning_rate": 5.527545990674475e-06, + "loss": 0.7892, + "step": 10721 + }, + { + "epoch": 0.6582154148377789, + "grad_norm": 0.8644695882028727, + "learning_rate": 5.525767676608651e-06, + "loss": 0.79, + "step": 10722 + }, + { + "epoch": 0.6582768040762454, + "grad_norm": 0.9407567890715864, + "learning_rate": 5.523989539433161e-06, + "loss": 0.7848, + "step": 10723 + }, + { + "epoch": 0.6583381933147119, + "grad_norm": 0.921230010461309, + "learning_rate": 5.522211579218304e-06, + "loss": 0.7897, + "step": 10724 + }, + { + "epoch": 0.6583995825531784, + "grad_norm": 0.8552542248423589, + "learning_rate": 5.5204337960343666e-06, + "loss": 0.8002, + "step": 10725 + }, + { + "epoch": 0.658460971791645, + "grad_norm": 0.8495509949395943, + "learning_rate": 5.518656189951645e-06, + "loss": 0.8164, + "step": 10726 + }, + { + "epoch": 0.6585223610301114, + "grad_norm": 1.0160691771027741, + "learning_rate": 5.516878761040416e-06, + "loss": 0.8212, + "step": 10727 + }, + { + "epoch": 0.658583750268578, + "grad_norm": 0.916598026422667, + "learning_rate": 5.515101509370944e-06, + "loss": 0.7615, + "step": 10728 + }, + { + "epoch": 0.6586451395070444, + "grad_norm": 0.9230163557614192, + "learning_rate": 5.51332443501349e-06, + "loss": 0.8003, + "step": 10729 + }, + { + "epoch": 0.6587065287455109, + "grad_norm": 0.9679911177346209, + "learning_rate": 5.511547538038322e-06, + "loss": 0.7479, + "step": 10730 + }, + { + "epoch": 0.6587679179839774, + "grad_norm": 0.8885947900135485, + "learning_rate": 5.5097708185156914e-06, + "loss": 0.7506, + "step": 10731 + }, + { + "epoch": 0.6588293072224439, + "grad_norm": 0.7869309829433865, + "learning_rate": 5.5079942765158266e-06, + "loss": 0.7959, + "step": 10732 + }, + { + "epoch": 0.6588906964609104, + "grad_norm": 0.8998198835238027, + "learning_rate": 5.506217912108977e-06, + "loss": 0.7889, + "step": 10733 + }, + { + "epoch": 0.6589520856993769, + "grad_norm": 0.8542367714408199, + "learning_rate": 5.504441725365368e-06, + "loss": 0.7569, + "step": 10734 + }, + { + "epoch": 0.6590134749378433, + "grad_norm": 0.9489045298764754, + "learning_rate": 5.502665716355222e-06, + "loss": 0.7662, + "step": 10735 + }, + { + "epoch": 0.6590748641763099, + "grad_norm": 0.895190983334577, + "learning_rate": 5.500889885148752e-06, + "loss": 0.7737, + "step": 10736 + }, + { + "epoch": 0.6591362534147764, + "grad_norm": 0.972790012472864, + "learning_rate": 5.49911423181617e-06, + "loss": 0.7426, + "step": 10737 + }, + { + "epoch": 0.6591976426532429, + "grad_norm": 0.9473767618002347, + "learning_rate": 5.497338756427672e-06, + "loss": 0.791, + "step": 10738 + }, + { + "epoch": 0.6592590318917094, + "grad_norm": 0.8147923981871483, + "learning_rate": 5.495563459053455e-06, + "loss": 0.7666, + "step": 10739 + }, + { + "epoch": 0.6593204211301759, + "grad_norm": 0.9681001560872053, + "learning_rate": 5.493788339763706e-06, + "loss": 0.782, + "step": 10740 + }, + { + "epoch": 0.6593818103686424, + "grad_norm": 1.0267134537610538, + "learning_rate": 5.492013398628611e-06, + "loss": 0.7882, + "step": 10741 + }, + { + "epoch": 0.6594431996071088, + "grad_norm": 0.8636395411833998, + "learning_rate": 5.490238635718332e-06, + "loss": 0.7663, + "step": 10742 + }, + { + "epoch": 0.6595045888455754, + "grad_norm": 0.9578140391141747, + "learning_rate": 5.488464051103035e-06, + "loss": 0.763, + "step": 10743 + }, + { + "epoch": 0.6595659780840418, + "grad_norm": 0.899370854713087, + "learning_rate": 5.48668964485289e-06, + "loss": 0.7728, + "step": 10744 + }, + { + "epoch": 0.6596273673225084, + "grad_norm": 0.9725967588883098, + "learning_rate": 5.4849154170380395e-06, + "loss": 0.7943, + "step": 10745 + }, + { + "epoch": 0.6596887565609748, + "grad_norm": 0.9017839401419552, + "learning_rate": 5.483141367728631e-06, + "loss": 0.7539, + "step": 10746 + }, + { + "epoch": 0.6597501457994414, + "grad_norm": 0.9654210132839428, + "learning_rate": 5.481367496994804e-06, + "loss": 0.809, + "step": 10747 + }, + { + "epoch": 0.6598115350379079, + "grad_norm": 0.9653970721314405, + "learning_rate": 5.479593804906687e-06, + "loss": 0.7759, + "step": 10748 + }, + { + "epoch": 0.6598729242763743, + "grad_norm": 1.019627323017693, + "learning_rate": 5.477820291534401e-06, + "loss": 0.731, + "step": 10749 + }, + { + "epoch": 0.6599343135148409, + "grad_norm": 0.8853906416583472, + "learning_rate": 5.476046956948065e-06, + "loss": 0.7475, + "step": 10750 + }, + { + "epoch": 0.6599957027533073, + "grad_norm": 0.6042111567582674, + "learning_rate": 5.474273801217793e-06, + "loss": 0.6514, + "step": 10751 + }, + { + "epoch": 0.6600570919917739, + "grad_norm": 0.9500925050003646, + "learning_rate": 5.47250082441368e-06, + "loss": 0.8107, + "step": 10752 + }, + { + "epoch": 0.6601184812302403, + "grad_norm": 0.9987841152215181, + "learning_rate": 5.4707280266058215e-06, + "loss": 0.7756, + "step": 10753 + }, + { + "epoch": 0.6601798704687069, + "grad_norm": 1.044842459884791, + "learning_rate": 5.468955407864312e-06, + "loss": 0.844, + "step": 10754 + }, + { + "epoch": 0.6602412597071733, + "grad_norm": 0.8837116685396598, + "learning_rate": 5.4671829682592285e-06, + "loss": 0.8089, + "step": 10755 + }, + { + "epoch": 0.6603026489456398, + "grad_norm": 0.8224098890351619, + "learning_rate": 5.46541070786065e-06, + "loss": 0.7696, + "step": 10756 + }, + { + "epoch": 0.6603640381841063, + "grad_norm": 0.8964873459334335, + "learning_rate": 5.4636386267386295e-06, + "loss": 0.8031, + "step": 10757 + }, + { + "epoch": 0.6604254274225728, + "grad_norm": 0.9064694726816518, + "learning_rate": 5.461866724963242e-06, + "loss": 0.7913, + "step": 10758 + }, + { + "epoch": 0.6604868166610394, + "grad_norm": 0.9377594544153264, + "learning_rate": 5.460095002604533e-06, + "loss": 0.8057, + "step": 10759 + }, + { + "epoch": 0.6605482058995058, + "grad_norm": 0.8150623430109114, + "learning_rate": 5.458323459732551e-06, + "loss": 0.7613, + "step": 10760 + }, + { + "epoch": 0.6606095951379723, + "grad_norm": 0.8727661129327469, + "learning_rate": 5.4565520964173326e-06, + "loss": 0.8275, + "step": 10761 + }, + { + "epoch": 0.6606709843764388, + "grad_norm": 0.8373031669125306, + "learning_rate": 5.45478091272891e-06, + "loss": 0.7773, + "step": 10762 + }, + { + "epoch": 0.6607323736149053, + "grad_norm": 0.8599497535983192, + "learning_rate": 5.453009908737307e-06, + "loss": 0.8205, + "step": 10763 + }, + { + "epoch": 0.6607937628533718, + "grad_norm": 0.8839802752294194, + "learning_rate": 5.451239084512537e-06, + "loss": 0.7505, + "step": 10764 + }, + { + "epoch": 0.6608551520918383, + "grad_norm": 0.950494793302272, + "learning_rate": 5.449468440124619e-06, + "loss": 0.7694, + "step": 10765 + }, + { + "epoch": 0.6609165413303048, + "grad_norm": 0.9351701790810962, + "learning_rate": 5.447697975643556e-06, + "loss": 0.8187, + "step": 10766 + }, + { + "epoch": 0.6609779305687713, + "grad_norm": 0.8623523508717161, + "learning_rate": 5.445927691139336e-06, + "loss": 0.8255, + "step": 10767 + }, + { + "epoch": 0.6610393198072378, + "grad_norm": 0.8928093026381871, + "learning_rate": 5.444157586681947e-06, + "loss": 0.8163, + "step": 10768 + }, + { + "epoch": 0.6611007090457043, + "grad_norm": 0.8656228110692487, + "learning_rate": 5.442387662341377e-06, + "loss": 0.7687, + "step": 10769 + }, + { + "epoch": 0.6611620982841708, + "grad_norm": 0.8590896659806753, + "learning_rate": 5.440617918187601e-06, + "loss": 0.7173, + "step": 10770 + }, + { + "epoch": 0.6612234875226373, + "grad_norm": 0.9529112311620774, + "learning_rate": 5.4388483542905825e-06, + "loss": 0.7501, + "step": 10771 + }, + { + "epoch": 0.6612848767611038, + "grad_norm": 0.9716974797806572, + "learning_rate": 5.4370789707202835e-06, + "loss": 0.7957, + "step": 10772 + }, + { + "epoch": 0.6613462659995702, + "grad_norm": 0.9192743088255826, + "learning_rate": 5.435309767546657e-06, + "loss": 0.8232, + "step": 10773 + }, + { + "epoch": 0.6614076552380368, + "grad_norm": 0.9004251366275305, + "learning_rate": 5.4335407448396495e-06, + "loss": 0.8055, + "step": 10774 + }, + { + "epoch": 0.6614690444765032, + "grad_norm": 0.9267748910663872, + "learning_rate": 5.431771902669194e-06, + "loss": 0.8052, + "step": 10775 + }, + { + "epoch": 0.6615304337149698, + "grad_norm": 0.9755667010582217, + "learning_rate": 5.430003241105237e-06, + "loss": 0.8114, + "step": 10776 + }, + { + "epoch": 0.6615918229534362, + "grad_norm": 0.9523704855176632, + "learning_rate": 5.42823476021769e-06, + "loss": 0.7677, + "step": 10777 + }, + { + "epoch": 0.6616532121919028, + "grad_norm": 0.8589412935924966, + "learning_rate": 5.426466460076471e-06, + "loss": 0.7861, + "step": 10778 + }, + { + "epoch": 0.6617146014303693, + "grad_norm": 1.0007579530877289, + "learning_rate": 5.424698340751497e-06, + "loss": 0.7843, + "step": 10779 + }, + { + "epoch": 0.6617759906688357, + "grad_norm": 0.9770048483742659, + "learning_rate": 5.422930402312668e-06, + "loss": 0.7663, + "step": 10780 + }, + { + "epoch": 0.6618373799073023, + "grad_norm": 0.8668792600166816, + "learning_rate": 5.421162644829885e-06, + "loss": 0.747, + "step": 10781 + }, + { + "epoch": 0.6618987691457687, + "grad_norm": 0.8938126957281888, + "learning_rate": 5.419395068373024e-06, + "loss": 0.7957, + "step": 10782 + }, + { + "epoch": 0.6619601583842353, + "grad_norm": 0.9438892221703412, + "learning_rate": 5.417627673011977e-06, + "loss": 0.7274, + "step": 10783 + }, + { + "epoch": 0.6620215476227017, + "grad_norm": 1.0268063194224584, + "learning_rate": 5.415860458816617e-06, + "loss": 0.7865, + "step": 10784 + }, + { + "epoch": 0.6620829368611683, + "grad_norm": 0.9175349522515707, + "learning_rate": 5.4140934258568125e-06, + "loss": 0.8393, + "step": 10785 + }, + { + "epoch": 0.6621443260996347, + "grad_norm": 0.9561487008260463, + "learning_rate": 5.4123265742024204e-06, + "loss": 0.7863, + "step": 10786 + }, + { + "epoch": 0.6622057153381012, + "grad_norm": 0.8490727015917849, + "learning_rate": 5.410559903923296e-06, + "loss": 0.784, + "step": 10787 + }, + { + "epoch": 0.6622671045765677, + "grad_norm": 1.0197128742093764, + "learning_rate": 5.408793415089284e-06, + "loss": 0.784, + "step": 10788 + }, + { + "epoch": 0.6623284938150342, + "grad_norm": 0.9086815168371495, + "learning_rate": 5.40702710777022e-06, + "loss": 0.7612, + "step": 10789 + }, + { + "epoch": 0.6623898830535008, + "grad_norm": 0.9556539810268195, + "learning_rate": 5.405260982035943e-06, + "loss": 0.8002, + "step": 10790 + }, + { + "epoch": 0.6624512722919672, + "grad_norm": 0.9846094851137382, + "learning_rate": 5.403495037956279e-06, + "loss": 0.7894, + "step": 10791 + }, + { + "epoch": 0.6625126615304338, + "grad_norm": 0.8964024809381186, + "learning_rate": 5.401729275601031e-06, + "loss": 0.7677, + "step": 10792 + }, + { + "epoch": 0.6625740507689002, + "grad_norm": 0.9564757700685186, + "learning_rate": 5.399963695040022e-06, + "loss": 0.7865, + "step": 10793 + }, + { + "epoch": 0.6626354400073667, + "grad_norm": 0.8712072289497739, + "learning_rate": 5.398198296343051e-06, + "loss": 0.7656, + "step": 10794 + }, + { + "epoch": 0.6626968292458332, + "grad_norm": 0.8506635898951239, + "learning_rate": 5.396433079579918e-06, + "loss": 0.8175, + "step": 10795 + }, + { + "epoch": 0.6627582184842997, + "grad_norm": 0.9747173310154829, + "learning_rate": 5.3946680448204e-06, + "loss": 0.7846, + "step": 10796 + }, + { + "epoch": 0.6628196077227662, + "grad_norm": 0.8731753620344945, + "learning_rate": 5.392903192134287e-06, + "loss": 0.7382, + "step": 10797 + }, + { + "epoch": 0.6628809969612327, + "grad_norm": 0.919507645029337, + "learning_rate": 5.391138521591351e-06, + "loss": 0.8036, + "step": 10798 + }, + { + "epoch": 0.6629423861996991, + "grad_norm": 0.983398980365823, + "learning_rate": 5.389374033261361e-06, + "loss": 0.8044, + "step": 10799 + }, + { + "epoch": 0.6630037754381657, + "grad_norm": 0.9701355471491371, + "learning_rate": 5.387609727214073e-06, + "loss": 0.7664, + "step": 10800 + }, + { + "epoch": 0.6630651646766322, + "grad_norm": 0.9290449657044587, + "learning_rate": 5.3858456035192444e-06, + "loss": 0.7796, + "step": 10801 + }, + { + "epoch": 0.6631265539150987, + "grad_norm": 0.9789101581809396, + "learning_rate": 5.384081662246614e-06, + "loss": 0.8094, + "step": 10802 + }, + { + "epoch": 0.6631879431535652, + "grad_norm": 0.8982151601623779, + "learning_rate": 5.382317903465921e-06, + "loss": 0.7655, + "step": 10803 + }, + { + "epoch": 0.6632493323920317, + "grad_norm": 0.9494048806499412, + "learning_rate": 5.3805543272469014e-06, + "loss": 0.7986, + "step": 10804 + }, + { + "epoch": 0.6633107216304982, + "grad_norm": 0.9348806010227791, + "learning_rate": 5.3787909336592814e-06, + "loss": 0.7829, + "step": 10805 + }, + { + "epoch": 0.6633721108689646, + "grad_norm": 0.9482047612281024, + "learning_rate": 5.377027722772767e-06, + "loss": 0.8166, + "step": 10806 + }, + { + "epoch": 0.6634335001074312, + "grad_norm": 0.9077967046365325, + "learning_rate": 5.375264694657067e-06, + "loss": 0.7774, + "step": 10807 + }, + { + "epoch": 0.6634948893458976, + "grad_norm": 0.9673706120253518, + "learning_rate": 5.373501849381892e-06, + "loss": 0.7744, + "step": 10808 + }, + { + "epoch": 0.6635562785843642, + "grad_norm": 1.0854985444219767, + "learning_rate": 5.371739187016935e-06, + "loss": 0.7786, + "step": 10809 + }, + { + "epoch": 0.6636176678228306, + "grad_norm": 0.9352794063256747, + "learning_rate": 5.369976707631881e-06, + "loss": 0.7846, + "step": 10810 + }, + { + "epoch": 0.6636790570612972, + "grad_norm": 0.8923057287171685, + "learning_rate": 5.368214411296411e-06, + "loss": 0.7915, + "step": 10811 + }, + { + "epoch": 0.6637404462997637, + "grad_norm": 0.9599304686487775, + "learning_rate": 5.366452298080198e-06, + "loss": 0.774, + "step": 10812 + }, + { + "epoch": 0.6638018355382301, + "grad_norm": 0.7900594578806874, + "learning_rate": 5.364690368052907e-06, + "loss": 0.7514, + "step": 10813 + }, + { + "epoch": 0.6638632247766967, + "grad_norm": 1.001345908265695, + "learning_rate": 5.362928621284193e-06, + "loss": 0.7955, + "step": 10814 + }, + { + "epoch": 0.6639246140151631, + "grad_norm": 0.9440904092427489, + "learning_rate": 5.36116705784372e-06, + "loss": 0.7735, + "step": 10815 + }, + { + "epoch": 0.6639860032536297, + "grad_norm": 0.9389965422666635, + "learning_rate": 5.3594056778011196e-06, + "loss": 0.7837, + "step": 10816 + }, + { + "epoch": 0.6640473924920961, + "grad_norm": 0.9492744939726944, + "learning_rate": 5.357644481226027e-06, + "loss": 0.8015, + "step": 10817 + }, + { + "epoch": 0.6641087817305626, + "grad_norm": 0.9770677840972669, + "learning_rate": 5.355883468188083e-06, + "loss": 0.7424, + "step": 10818 + }, + { + "epoch": 0.6641701709690291, + "grad_norm": 0.9923951655517507, + "learning_rate": 5.354122638756903e-06, + "loss": 0.7665, + "step": 10819 + }, + { + "epoch": 0.6642315602074956, + "grad_norm": 0.8447836121232876, + "learning_rate": 5.352361993002108e-06, + "loss": 0.7849, + "step": 10820 + }, + { + "epoch": 0.6642929494459622, + "grad_norm": 0.9591891904386101, + "learning_rate": 5.350601530993291e-06, + "loss": 0.7764, + "step": 10821 + }, + { + "epoch": 0.6643543386844286, + "grad_norm": 0.9477596153786617, + "learning_rate": 5.348841252800068e-06, + "loss": 0.7461, + "step": 10822 + }, + { + "epoch": 0.6644157279228952, + "grad_norm": 0.9580038418555912, + "learning_rate": 5.347081158492025e-06, + "loss": 0.7885, + "step": 10823 + }, + { + "epoch": 0.6644771171613616, + "grad_norm": 1.0008644452752082, + "learning_rate": 5.345321248138749e-06, + "loss": 0.8086, + "step": 10824 + }, + { + "epoch": 0.6645385063998281, + "grad_norm": 0.8339236289221349, + "learning_rate": 5.3435615218098216e-06, + "loss": 0.7633, + "step": 10825 + }, + { + "epoch": 0.6645998956382946, + "grad_norm": 0.6198165506857659, + "learning_rate": 5.341801979574809e-06, + "loss": 0.6864, + "step": 10826 + }, + { + "epoch": 0.6646612848767611, + "grad_norm": 0.8500531356962542, + "learning_rate": 5.340042621503278e-06, + "loss": 0.7853, + "step": 10827 + }, + { + "epoch": 0.6647226741152276, + "grad_norm": 0.9119411021877678, + "learning_rate": 5.338283447664783e-06, + "loss": 0.7564, + "step": 10828 + }, + { + "epoch": 0.6647840633536941, + "grad_norm": 0.8578752315271968, + "learning_rate": 5.33652445812888e-06, + "loss": 0.7961, + "step": 10829 + }, + { + "epoch": 0.6648454525921605, + "grad_norm": 0.934865878657335, + "learning_rate": 5.334765652965109e-06, + "loss": 0.7573, + "step": 10830 + }, + { + "epoch": 0.6649068418306271, + "grad_norm": 0.8424003538457794, + "learning_rate": 5.333007032242997e-06, + "loss": 0.8062, + "step": 10831 + }, + { + "epoch": 0.6649682310690936, + "grad_norm": 0.9138505544071692, + "learning_rate": 5.331248596032082e-06, + "loss": 0.8236, + "step": 10832 + }, + { + "epoch": 0.6650296203075601, + "grad_norm": 0.9418511485901566, + "learning_rate": 5.32949034440188e-06, + "loss": 0.7819, + "step": 10833 + }, + { + "epoch": 0.6650910095460266, + "grad_norm": 0.9081817625513094, + "learning_rate": 5.327732277421903e-06, + "loss": 0.7737, + "step": 10834 + }, + { + "epoch": 0.6651523987844931, + "grad_norm": 0.6063907315747655, + "learning_rate": 5.3259743951616595e-06, + "loss": 0.6734, + "step": 10835 + }, + { + "epoch": 0.6652137880229596, + "grad_norm": 0.9729268836408631, + "learning_rate": 5.324216697690645e-06, + "loss": 0.8341, + "step": 10836 + }, + { + "epoch": 0.665275177261426, + "grad_norm": 0.9098851721300666, + "learning_rate": 5.322459185078355e-06, + "loss": 0.8313, + "step": 10837 + }, + { + "epoch": 0.6653365664998926, + "grad_norm": 0.8433726203263081, + "learning_rate": 5.3207018573942684e-06, + "loss": 0.7535, + "step": 10838 + }, + { + "epoch": 0.665397955738359, + "grad_norm": 0.891738252675692, + "learning_rate": 5.318944714707861e-06, + "loss": 0.7704, + "step": 10839 + }, + { + "epoch": 0.6654593449768256, + "grad_norm": 0.9441946580122298, + "learning_rate": 5.317187757088612e-06, + "loss": 0.7704, + "step": 10840 + }, + { + "epoch": 0.665520734215292, + "grad_norm": 0.9418258316040742, + "learning_rate": 5.315430984605974e-06, + "loss": 0.7578, + "step": 10841 + }, + { + "epoch": 0.6655821234537586, + "grad_norm": 0.8995293924092245, + "learning_rate": 5.313674397329398e-06, + "loss": 0.7849, + "step": 10842 + }, + { + "epoch": 0.6656435126922251, + "grad_norm": 1.0093531500094657, + "learning_rate": 5.311917995328344e-06, + "loss": 0.778, + "step": 10843 + }, + { + "epoch": 0.6657049019306915, + "grad_norm": 0.9197869719000511, + "learning_rate": 5.310161778672242e-06, + "loss": 0.7522, + "step": 10844 + }, + { + "epoch": 0.6657662911691581, + "grad_norm": 0.9755919984813485, + "learning_rate": 5.308405747430534e-06, + "loss": 0.7918, + "step": 10845 + }, + { + "epoch": 0.6658276804076245, + "grad_norm": 0.8217012545288656, + "learning_rate": 5.306649901672631e-06, + "loss": 0.7497, + "step": 10846 + }, + { + "epoch": 0.6658890696460911, + "grad_norm": 0.8483047972999587, + "learning_rate": 5.304894241467964e-06, + "loss": 0.8089, + "step": 10847 + }, + { + "epoch": 0.6659504588845575, + "grad_norm": 1.0261471835024494, + "learning_rate": 5.303138766885938e-06, + "loss": 0.8156, + "step": 10848 + }, + { + "epoch": 0.666011848123024, + "grad_norm": 0.8885250284772002, + "learning_rate": 5.3013834779959564e-06, + "loss": 0.7916, + "step": 10849 + }, + { + "epoch": 0.6660732373614905, + "grad_norm": 0.8623603621603338, + "learning_rate": 5.299628374867416e-06, + "loss": 0.7529, + "step": 10850 + }, + { + "epoch": 0.666134626599957, + "grad_norm": 0.915985827334519, + "learning_rate": 5.297873457569706e-06, + "loss": 0.7646, + "step": 10851 + }, + { + "epoch": 0.6661960158384235, + "grad_norm": 0.6211619924508972, + "learning_rate": 5.296118726172208e-06, + "loss": 0.6559, + "step": 10852 + }, + { + "epoch": 0.66625740507689, + "grad_norm": 1.0261792943374035, + "learning_rate": 5.294364180744289e-06, + "loss": 0.8013, + "step": 10853 + }, + { + "epoch": 0.6663187943153566, + "grad_norm": 0.8516986670475593, + "learning_rate": 5.292609821355326e-06, + "loss": 0.8002, + "step": 10854 + }, + { + "epoch": 0.666380183553823, + "grad_norm": 0.9353108861248695, + "learning_rate": 5.2908556480746775e-06, + "loss": 0.7939, + "step": 10855 + }, + { + "epoch": 0.6664415727922895, + "grad_norm": 0.963945529588522, + "learning_rate": 5.289101660971685e-06, + "loss": 0.8213, + "step": 10856 + }, + { + "epoch": 0.666502962030756, + "grad_norm": 0.8988993780891442, + "learning_rate": 5.287347860115701e-06, + "loss": 0.7444, + "step": 10857 + }, + { + "epoch": 0.6665643512692225, + "grad_norm": 0.9778892145028006, + "learning_rate": 5.285594245576062e-06, + "loss": 0.8343, + "step": 10858 + }, + { + "epoch": 0.666625740507689, + "grad_norm": 0.9100436213128812, + "learning_rate": 5.283840817422102e-06, + "loss": 0.7613, + "step": 10859 + }, + { + "epoch": 0.6666871297461555, + "grad_norm": 0.8393381437320659, + "learning_rate": 5.282087575723129e-06, + "loss": 0.7751, + "step": 10860 + }, + { + "epoch": 0.666748518984622, + "grad_norm": 0.8986504890482697, + "learning_rate": 5.280334520548472e-06, + "loss": 0.7849, + "step": 10861 + }, + { + "epoch": 0.6668099082230885, + "grad_norm": 0.8576884342894879, + "learning_rate": 5.278581651967434e-06, + "loss": 0.7918, + "step": 10862 + }, + { + "epoch": 0.6668712974615549, + "grad_norm": 0.8630677708577379, + "learning_rate": 5.276828970049315e-06, + "loss": 0.8109, + "step": 10863 + }, + { + "epoch": 0.6669326867000215, + "grad_norm": 0.8710263443555427, + "learning_rate": 5.275076474863408e-06, + "loss": 0.7561, + "step": 10864 + }, + { + "epoch": 0.666994075938488, + "grad_norm": 0.9679685893811464, + "learning_rate": 5.2733241664789994e-06, + "loss": 0.8055, + "step": 10865 + }, + { + "epoch": 0.6670554651769545, + "grad_norm": 0.789820300401914, + "learning_rate": 5.2715720449653654e-06, + "loss": 0.7256, + "step": 10866 + }, + { + "epoch": 0.667116854415421, + "grad_norm": 0.915959558164443, + "learning_rate": 5.269820110391774e-06, + "loss": 0.7853, + "step": 10867 + }, + { + "epoch": 0.6671782436538874, + "grad_norm": 0.998122643376716, + "learning_rate": 5.268068362827498e-06, + "loss": 0.7858, + "step": 10868 + }, + { + "epoch": 0.667239632892354, + "grad_norm": 0.8769927243594111, + "learning_rate": 5.26631680234179e-06, + "loss": 0.7868, + "step": 10869 + }, + { + "epoch": 0.6673010221308204, + "grad_norm": 0.7919755454239291, + "learning_rate": 5.26456542900389e-06, + "loss": 0.7927, + "step": 10870 + }, + { + "epoch": 0.667362411369287, + "grad_norm": 0.9398622371235408, + "learning_rate": 5.2628142428830475e-06, + "loss": 0.7454, + "step": 10871 + }, + { + "epoch": 0.6674238006077534, + "grad_norm": 0.937627762536235, + "learning_rate": 5.261063244048495e-06, + "loss": 0.7792, + "step": 10872 + }, + { + "epoch": 0.66748518984622, + "grad_norm": 0.8358949461008299, + "learning_rate": 5.259312432569458e-06, + "loss": 0.7902, + "step": 10873 + }, + { + "epoch": 0.6675465790846865, + "grad_norm": 0.8787310194311384, + "learning_rate": 5.257561808515156e-06, + "loss": 0.8092, + "step": 10874 + }, + { + "epoch": 0.667607968323153, + "grad_norm": 0.9329719208266964, + "learning_rate": 5.2558113719548e-06, + "loss": 0.7749, + "step": 10875 + }, + { + "epoch": 0.6676693575616195, + "grad_norm": 0.8767057450484727, + "learning_rate": 5.254061122957593e-06, + "loss": 0.782, + "step": 10876 + }, + { + "epoch": 0.6677307468000859, + "grad_norm": 0.9792202947108438, + "learning_rate": 5.252311061592734e-06, + "loss": 0.7707, + "step": 10877 + }, + { + "epoch": 0.6677921360385525, + "grad_norm": 0.9482453610796212, + "learning_rate": 5.250561187929407e-06, + "loss": 0.7889, + "step": 10878 + }, + { + "epoch": 0.6678535252770189, + "grad_norm": 0.8194425664070217, + "learning_rate": 5.248811502036806e-06, + "loss": 0.8052, + "step": 10879 + }, + { + "epoch": 0.6679149145154855, + "grad_norm": 1.0161330087478202, + "learning_rate": 5.2470620039840935e-06, + "loss": 0.7656, + "step": 10880 + }, + { + "epoch": 0.6679763037539519, + "grad_norm": 0.8787214707675236, + "learning_rate": 5.245312693840436e-06, + "loss": 0.7745, + "step": 10881 + }, + { + "epoch": 0.6680376929924184, + "grad_norm": 0.8898678654236584, + "learning_rate": 5.243563571675002e-06, + "loss": 0.7795, + "step": 10882 + }, + { + "epoch": 0.6680990822308849, + "grad_norm": 0.8902920548957188, + "learning_rate": 5.241814637556939e-06, + "loss": 0.7358, + "step": 10883 + }, + { + "epoch": 0.6681604714693514, + "grad_norm": 0.9510232438182908, + "learning_rate": 5.240065891555397e-06, + "loss": 0.7687, + "step": 10884 + }, + { + "epoch": 0.668221860707818, + "grad_norm": 0.8835314194502374, + "learning_rate": 5.238317333739499e-06, + "loss": 0.7944, + "step": 10885 + }, + { + "epoch": 0.6682832499462844, + "grad_norm": 1.022532910429455, + "learning_rate": 5.236568964178388e-06, + "loss": 0.8618, + "step": 10886 + }, + { + "epoch": 0.668344639184751, + "grad_norm": 0.90994683059384, + "learning_rate": 5.234820782941184e-06, + "loss": 0.8162, + "step": 10887 + }, + { + "epoch": 0.6684060284232174, + "grad_norm": 0.9084735601844192, + "learning_rate": 5.233072790096998e-06, + "loss": 0.7477, + "step": 10888 + }, + { + "epoch": 0.6684674176616839, + "grad_norm": 0.9197269853923925, + "learning_rate": 5.231324985714942e-06, + "loss": 0.8167, + "step": 10889 + }, + { + "epoch": 0.6685288069001504, + "grad_norm": 0.8536063520453903, + "learning_rate": 5.229577369864113e-06, + "loss": 0.7604, + "step": 10890 + }, + { + "epoch": 0.6685901961386169, + "grad_norm": 0.9088621484433819, + "learning_rate": 5.227829942613605e-06, + "loss": 0.7972, + "step": 10891 + }, + { + "epoch": 0.6686515853770834, + "grad_norm": 0.879373406121019, + "learning_rate": 5.226082704032498e-06, + "loss": 0.7905, + "step": 10892 + }, + { + "epoch": 0.6687129746155499, + "grad_norm": 0.9858759693902344, + "learning_rate": 5.2243356541898794e-06, + "loss": 0.7589, + "step": 10893 + }, + { + "epoch": 0.6687743638540163, + "grad_norm": 0.9635197274160883, + "learning_rate": 5.2225887931548165e-06, + "loss": 0.7725, + "step": 10894 + }, + { + "epoch": 0.6688357530924829, + "grad_norm": 0.8945704786150481, + "learning_rate": 5.220842120996365e-06, + "loss": 0.7787, + "step": 10895 + }, + { + "epoch": 0.6688971423309494, + "grad_norm": 0.9531707273090895, + "learning_rate": 5.2190956377835875e-06, + "loss": 0.7711, + "step": 10896 + }, + { + "epoch": 0.6689585315694159, + "grad_norm": 0.8615388203412253, + "learning_rate": 5.217349343585529e-06, + "loss": 0.7956, + "step": 10897 + }, + { + "epoch": 0.6690199208078824, + "grad_norm": 0.9683231620309849, + "learning_rate": 5.215603238471232e-06, + "loss": 0.7498, + "step": 10898 + }, + { + "epoch": 0.6690813100463489, + "grad_norm": 0.9330599420345728, + "learning_rate": 5.213857322509727e-06, + "loss": 0.8005, + "step": 10899 + }, + { + "epoch": 0.6691426992848154, + "grad_norm": 0.8423403098891861, + "learning_rate": 5.21211159577004e-06, + "loss": 0.7985, + "step": 10900 + }, + { + "epoch": 0.6692040885232818, + "grad_norm": 0.967359755537688, + "learning_rate": 5.210366058321188e-06, + "loss": 0.7661, + "step": 10901 + }, + { + "epoch": 0.6692654777617484, + "grad_norm": 0.9980279546040658, + "learning_rate": 5.208620710232184e-06, + "loss": 0.773, + "step": 10902 + }, + { + "epoch": 0.6693268670002148, + "grad_norm": 1.0060284826376054, + "learning_rate": 5.206875551572025e-06, + "loss": 0.7592, + "step": 10903 + }, + { + "epoch": 0.6693882562386814, + "grad_norm": 0.9014484875928641, + "learning_rate": 5.205130582409719e-06, + "loss": 0.7648, + "step": 10904 + }, + { + "epoch": 0.6694496454771478, + "grad_norm": 0.9520380213636487, + "learning_rate": 5.20338580281424e-06, + "loss": 0.8375, + "step": 10905 + }, + { + "epoch": 0.6695110347156144, + "grad_norm": 0.635970211331725, + "learning_rate": 5.2016412128545735e-06, + "loss": 0.7179, + "step": 10906 + }, + { + "epoch": 0.6695724239540809, + "grad_norm": 0.8960146609938436, + "learning_rate": 5.199896812599695e-06, + "loss": 0.7901, + "step": 10907 + }, + { + "epoch": 0.6696338131925473, + "grad_norm": 0.8149853176853842, + "learning_rate": 5.198152602118569e-06, + "loss": 0.7243, + "step": 10908 + }, + { + "epoch": 0.6696952024310139, + "grad_norm": 0.9734025537225528, + "learning_rate": 5.196408581480152e-06, + "loss": 0.7544, + "step": 10909 + }, + { + "epoch": 0.6697565916694803, + "grad_norm": 1.0275668148391783, + "learning_rate": 5.194664750753397e-06, + "loss": 0.8128, + "step": 10910 + }, + { + "epoch": 0.6698179809079469, + "grad_norm": 0.9443896350278592, + "learning_rate": 5.1929211100072426e-06, + "loss": 0.7872, + "step": 10911 + }, + { + "epoch": 0.6698793701464133, + "grad_norm": 0.8333238040563538, + "learning_rate": 5.191177659310629e-06, + "loss": 0.8015, + "step": 10912 + }, + { + "epoch": 0.6699407593848798, + "grad_norm": 0.9213846058844094, + "learning_rate": 5.1894343987324805e-06, + "loss": 0.7747, + "step": 10913 + }, + { + "epoch": 0.6700021486233463, + "grad_norm": 0.8903112193512284, + "learning_rate": 5.1876913283417196e-06, + "loss": 0.7442, + "step": 10914 + }, + { + "epoch": 0.6700635378618128, + "grad_norm": 0.9906493972892276, + "learning_rate": 5.185948448207259e-06, + "loss": 0.8379, + "step": 10915 + }, + { + "epoch": 0.6701249271002793, + "grad_norm": 0.9186223213226583, + "learning_rate": 5.184205758398002e-06, + "loss": 0.7675, + "step": 10916 + }, + { + "epoch": 0.6701863163387458, + "grad_norm": 1.0769379704286715, + "learning_rate": 5.1824632589828465e-06, + "loss": 0.7377, + "step": 10917 + }, + { + "epoch": 0.6702477055772124, + "grad_norm": 0.9360425116338181, + "learning_rate": 5.1807209500306865e-06, + "loss": 0.7801, + "step": 10918 + }, + { + "epoch": 0.6703090948156788, + "grad_norm": 0.9627525068126491, + "learning_rate": 5.178978831610407e-06, + "loss": 0.818, + "step": 10919 + }, + { + "epoch": 0.6703704840541453, + "grad_norm": 0.9612017541420752, + "learning_rate": 5.177236903790871e-06, + "loss": 0.7775, + "step": 10920 + }, + { + "epoch": 0.6704318732926118, + "grad_norm": 0.8340520076764655, + "learning_rate": 5.175495166640958e-06, + "loss": 0.7993, + "step": 10921 + }, + { + "epoch": 0.6704932625310783, + "grad_norm": 0.9690968239514505, + "learning_rate": 5.173753620229525e-06, + "loss": 0.7997, + "step": 10922 + }, + { + "epoch": 0.6705546517695448, + "grad_norm": 0.929771824757203, + "learning_rate": 5.172012264625423e-06, + "loss": 0.8154, + "step": 10923 + }, + { + "epoch": 0.6706160410080113, + "grad_norm": 0.9402980937253357, + "learning_rate": 5.170271099897499e-06, + "loss": 0.8354, + "step": 10924 + }, + { + "epoch": 0.6706774302464777, + "grad_norm": 0.9011087372413584, + "learning_rate": 5.168530126114589e-06, + "loss": 0.743, + "step": 10925 + }, + { + "epoch": 0.6707388194849443, + "grad_norm": 0.9205775441385493, + "learning_rate": 5.1667893433455244e-06, + "loss": 0.8581, + "step": 10926 + }, + { + "epoch": 0.6708002087234108, + "grad_norm": 0.9133240213298635, + "learning_rate": 5.1650487516591255e-06, + "loss": 0.7745, + "step": 10927 + }, + { + "epoch": 0.6708615979618773, + "grad_norm": 0.9342347573611557, + "learning_rate": 5.16330835112421e-06, + "loss": 0.7633, + "step": 10928 + }, + { + "epoch": 0.6709229872003438, + "grad_norm": 0.9762640468836549, + "learning_rate": 5.161568141809583e-06, + "loss": 0.7966, + "step": 10929 + }, + { + "epoch": 0.6709843764388103, + "grad_norm": 0.926096419644421, + "learning_rate": 5.159828123784046e-06, + "loss": 0.8315, + "step": 10930 + }, + { + "epoch": 0.6710457656772768, + "grad_norm": 0.8303878968164448, + "learning_rate": 5.158088297116385e-06, + "loss": 0.7616, + "step": 10931 + }, + { + "epoch": 0.6711071549157432, + "grad_norm": 0.902544433686503, + "learning_rate": 5.1563486618753945e-06, + "loss": 0.7721, + "step": 10932 + }, + { + "epoch": 0.6711685441542098, + "grad_norm": 0.8887175807740619, + "learning_rate": 5.154609218129851e-06, + "loss": 0.7334, + "step": 10933 + }, + { + "epoch": 0.6712299333926762, + "grad_norm": 0.9185471575312596, + "learning_rate": 5.152869965948513e-06, + "loss": 0.7507, + "step": 10934 + }, + { + "epoch": 0.6712913226311428, + "grad_norm": 0.9248917597544516, + "learning_rate": 5.151130905400152e-06, + "loss": 0.7903, + "step": 10935 + }, + { + "epoch": 0.6713527118696092, + "grad_norm": 0.5803215764342348, + "learning_rate": 5.149392036553521e-06, + "loss": 0.6122, + "step": 10936 + }, + { + "epoch": 0.6714141011080758, + "grad_norm": 0.9554409253887624, + "learning_rate": 5.147653359477365e-06, + "loss": 0.8037, + "step": 10937 + }, + { + "epoch": 0.6714754903465423, + "grad_norm": 1.2527504616704956, + "learning_rate": 5.145914874240424e-06, + "loss": 0.9276, + "step": 10938 + }, + { + "epoch": 0.6715368795850087, + "grad_norm": 0.9326374132251671, + "learning_rate": 5.144176580911431e-06, + "loss": 0.7799, + "step": 10939 + }, + { + "epoch": 0.6715982688234753, + "grad_norm": 0.8506464228760031, + "learning_rate": 5.1424384795591066e-06, + "loss": 0.7618, + "step": 10940 + }, + { + "epoch": 0.6716596580619417, + "grad_norm": 0.9903914451386683, + "learning_rate": 5.140700570252169e-06, + "loss": 0.7671, + "step": 10941 + }, + { + "epoch": 0.6717210473004083, + "grad_norm": 0.9952312182971593, + "learning_rate": 5.138962853059324e-06, + "loss": 0.7678, + "step": 10942 + }, + { + "epoch": 0.6717824365388747, + "grad_norm": 0.8651228678028805, + "learning_rate": 5.137225328049285e-06, + "loss": 0.7704, + "step": 10943 + }, + { + "epoch": 0.6718438257773413, + "grad_norm": 0.9320242403845215, + "learning_rate": 5.135487995290731e-06, + "loss": 0.7528, + "step": 10944 + }, + { + "epoch": 0.6719052150158077, + "grad_norm": 0.9225201750141359, + "learning_rate": 5.13375085485235e-06, + "loss": 0.785, + "step": 10945 + }, + { + "epoch": 0.6719666042542742, + "grad_norm": 0.9650733966040899, + "learning_rate": 5.132013906802829e-06, + "loss": 0.7907, + "step": 10946 + }, + { + "epoch": 0.6720279934927407, + "grad_norm": 0.8888241388767041, + "learning_rate": 5.130277151210834e-06, + "loss": 0.8066, + "step": 10947 + }, + { + "epoch": 0.6720893827312072, + "grad_norm": 0.9011132678882096, + "learning_rate": 5.128540588145032e-06, + "loss": 0.7817, + "step": 10948 + }, + { + "epoch": 0.6721507719696738, + "grad_norm": 0.9062473507356544, + "learning_rate": 5.126804217674068e-06, + "loss": 0.7799, + "step": 10949 + }, + { + "epoch": 0.6722121612081402, + "grad_norm": 0.9132263825542554, + "learning_rate": 5.125068039866601e-06, + "loss": 0.7813, + "step": 10950 + }, + { + "epoch": 0.6722735504466067, + "grad_norm": 0.8481646496373648, + "learning_rate": 5.123332054791265e-06, + "loss": 0.7641, + "step": 10951 + }, + { + "epoch": 0.6723349396850732, + "grad_norm": 1.0045761092093544, + "learning_rate": 5.121596262516697e-06, + "loss": 0.8215, + "step": 10952 + }, + { + "epoch": 0.6723963289235397, + "grad_norm": 0.9256879412068248, + "learning_rate": 5.11986066311152e-06, + "loss": 0.7543, + "step": 10953 + }, + { + "epoch": 0.6724577181620062, + "grad_norm": 0.9225430845098942, + "learning_rate": 5.118125256644353e-06, + "loss": 0.7646, + "step": 10954 + }, + { + "epoch": 0.6725191074004727, + "grad_norm": 1.0122603636631229, + "learning_rate": 5.116390043183803e-06, + "loss": 0.7395, + "step": 10955 + }, + { + "epoch": 0.6725804966389392, + "grad_norm": 0.9287232362653979, + "learning_rate": 5.114655022798469e-06, + "loss": 0.7471, + "step": 10956 + }, + { + "epoch": 0.6726418858774057, + "grad_norm": 1.039332870465878, + "learning_rate": 5.112920195556957e-06, + "loss": 0.7726, + "step": 10957 + }, + { + "epoch": 0.6727032751158721, + "grad_norm": 1.0081782153090508, + "learning_rate": 5.1111855615278505e-06, + "loss": 0.849, + "step": 10958 + }, + { + "epoch": 0.6727646643543387, + "grad_norm": 0.8897378264533301, + "learning_rate": 5.109451120779718e-06, + "loss": 0.7356, + "step": 10959 + }, + { + "epoch": 0.6728260535928052, + "grad_norm": 0.8356426490857134, + "learning_rate": 5.107716873381144e-06, + "loss": 0.8076, + "step": 10960 + }, + { + "epoch": 0.6728874428312717, + "grad_norm": 0.9527748520870957, + "learning_rate": 5.105982819400687e-06, + "loss": 0.7598, + "step": 10961 + }, + { + "epoch": 0.6729488320697382, + "grad_norm": 0.8493631231584893, + "learning_rate": 5.104248958906903e-06, + "loss": 0.749, + "step": 10962 + }, + { + "epoch": 0.6730102213082046, + "grad_norm": 1.0150378513811407, + "learning_rate": 5.102515291968344e-06, + "loss": 0.784, + "step": 10963 + }, + { + "epoch": 0.6730716105466712, + "grad_norm": 0.9849887916814111, + "learning_rate": 5.100781818653549e-06, + "loss": 0.7914, + "step": 10964 + }, + { + "epoch": 0.6731329997851376, + "grad_norm": 0.9919518419011581, + "learning_rate": 5.09904853903105e-06, + "loss": 0.7418, + "step": 10965 + }, + { + "epoch": 0.6731943890236042, + "grad_norm": 0.9694709842755703, + "learning_rate": 5.097315453169376e-06, + "loss": 0.7629, + "step": 10966 + }, + { + "epoch": 0.6732557782620706, + "grad_norm": 0.9247730162740468, + "learning_rate": 5.095582561137038e-06, + "loss": 0.757, + "step": 10967 + }, + { + "epoch": 0.6733171675005372, + "grad_norm": 0.8880222916442618, + "learning_rate": 5.093849863002561e-06, + "loss": 0.7641, + "step": 10968 + }, + { + "epoch": 0.6733785567390036, + "grad_norm": 0.9351048330880297, + "learning_rate": 5.092117358834434e-06, + "loss": 0.7727, + "step": 10969 + }, + { + "epoch": 0.6734399459774701, + "grad_norm": 0.961382588476756, + "learning_rate": 5.090385048701154e-06, + "loss": 0.7792, + "step": 10970 + }, + { + "epoch": 0.6735013352159367, + "grad_norm": 1.0334773636903642, + "learning_rate": 5.088652932671216e-06, + "loss": 0.7637, + "step": 10971 + }, + { + "epoch": 0.6735627244544031, + "grad_norm": 0.9842020617009203, + "learning_rate": 5.086921010813094e-06, + "loss": 0.8018, + "step": 10972 + }, + { + "epoch": 0.6736241136928697, + "grad_norm": 0.9336953983990515, + "learning_rate": 5.085189283195262e-06, + "loss": 0.7863, + "step": 10973 + }, + { + "epoch": 0.6736855029313361, + "grad_norm": 0.9349464272654677, + "learning_rate": 5.083457749886183e-06, + "loss": 0.7366, + "step": 10974 + }, + { + "epoch": 0.6737468921698027, + "grad_norm": 0.983742072309058, + "learning_rate": 5.081726410954316e-06, + "loss": 0.7817, + "step": 10975 + }, + { + "epoch": 0.6738082814082691, + "grad_norm": 0.9410480760487144, + "learning_rate": 5.0799952664681086e-06, + "loss": 0.7751, + "step": 10976 + }, + { + "epoch": 0.6738696706467356, + "grad_norm": 0.953089294005169, + "learning_rate": 5.078264316496002e-06, + "loss": 0.7906, + "step": 10977 + }, + { + "epoch": 0.6739310598852021, + "grad_norm": 0.9384891399340118, + "learning_rate": 5.076533561106429e-06, + "loss": 0.8202, + "step": 10978 + }, + { + "epoch": 0.6739924491236686, + "grad_norm": 1.0133480712340452, + "learning_rate": 5.074803000367818e-06, + "loss": 0.84, + "step": 10979 + }, + { + "epoch": 0.6740538383621352, + "grad_norm": 0.9725813790998127, + "learning_rate": 5.073072634348588e-06, + "loss": 0.7757, + "step": 10980 + }, + { + "epoch": 0.6741152276006016, + "grad_norm": 0.9280667548107706, + "learning_rate": 5.071342463117142e-06, + "loss": 0.7717, + "step": 10981 + }, + { + "epoch": 0.6741766168390682, + "grad_norm": 0.9449428055997761, + "learning_rate": 5.069612486741893e-06, + "loss": 0.7181, + "step": 10982 + }, + { + "epoch": 0.6742380060775346, + "grad_norm": 0.8962286865438873, + "learning_rate": 5.067882705291236e-06, + "loss": 0.7193, + "step": 10983 + }, + { + "epoch": 0.6742993953160011, + "grad_norm": 0.9403884810171379, + "learning_rate": 5.066153118833546e-06, + "loss": 0.7576, + "step": 10984 + }, + { + "epoch": 0.6743607845544676, + "grad_norm": 0.7980794105437838, + "learning_rate": 5.064423727437215e-06, + "loss": 0.777, + "step": 10985 + }, + { + "epoch": 0.6744221737929341, + "grad_norm": 0.9914345937942517, + "learning_rate": 5.062694531170612e-06, + "loss": 0.8171, + "step": 10986 + }, + { + "epoch": 0.6744835630314006, + "grad_norm": 0.9879065544525215, + "learning_rate": 5.060965530102101e-06, + "loss": 0.7486, + "step": 10987 + }, + { + "epoch": 0.6745449522698671, + "grad_norm": 0.990290031006514, + "learning_rate": 5.059236724300038e-06, + "loss": 0.797, + "step": 10988 + }, + { + "epoch": 0.6746063415083335, + "grad_norm": 0.8261821625760224, + "learning_rate": 5.057508113832772e-06, + "loss": 0.7727, + "step": 10989 + }, + { + "epoch": 0.6746677307468001, + "grad_norm": 0.8993667567717748, + "learning_rate": 5.055779698768646e-06, + "loss": 0.7642, + "step": 10990 + }, + { + "epoch": 0.6747291199852666, + "grad_norm": 0.880914997186403, + "learning_rate": 5.054051479175991e-06, + "loss": 0.7617, + "step": 10991 + }, + { + "epoch": 0.6747905092237331, + "grad_norm": 1.006058817059422, + "learning_rate": 5.052323455123134e-06, + "loss": 0.8077, + "step": 10992 + }, + { + "epoch": 0.6748518984621996, + "grad_norm": 0.9385370411845266, + "learning_rate": 5.050595626678392e-06, + "loss": 0.7328, + "step": 10993 + }, + { + "epoch": 0.674913287700666, + "grad_norm": 0.8768925381450384, + "learning_rate": 5.048867993910077e-06, + "loss": 0.7713, + "step": 10994 + }, + { + "epoch": 0.6749746769391326, + "grad_norm": 0.9168388727873389, + "learning_rate": 5.047140556886487e-06, + "loss": 0.7979, + "step": 10995 + }, + { + "epoch": 0.675036066177599, + "grad_norm": 0.8312697510712882, + "learning_rate": 5.045413315675925e-06, + "loss": 0.7849, + "step": 10996 + }, + { + "epoch": 0.6750974554160656, + "grad_norm": 0.9504787258194282, + "learning_rate": 5.043686270346676e-06, + "loss": 0.7764, + "step": 10997 + }, + { + "epoch": 0.675158844654532, + "grad_norm": 0.946520734046938, + "learning_rate": 5.04195942096701e-06, + "loss": 0.8245, + "step": 10998 + }, + { + "epoch": 0.6752202338929986, + "grad_norm": 1.037224859852384, + "learning_rate": 5.040232767605209e-06, + "loss": 0.8234, + "step": 10999 + }, + { + "epoch": 0.675281623131465, + "grad_norm": 1.1017292439702673, + "learning_rate": 5.038506310329534e-06, + "loss": 0.7571, + "step": 11000 + }, + { + "epoch": 0.6753430123699316, + "grad_norm": 0.800130425425111, + "learning_rate": 5.036780049208239e-06, + "loss": 0.779, + "step": 11001 + }, + { + "epoch": 0.6754044016083981, + "grad_norm": 0.8549926988845048, + "learning_rate": 5.0350539843095755e-06, + "loss": 0.7652, + "step": 11002 + }, + { + "epoch": 0.6754657908468645, + "grad_norm": 0.5988203370322506, + "learning_rate": 5.033328115701782e-06, + "loss": 0.6426, + "step": 11003 + }, + { + "epoch": 0.6755271800853311, + "grad_norm": 0.9239618574688654, + "learning_rate": 5.031602443453092e-06, + "loss": 0.7489, + "step": 11004 + }, + { + "epoch": 0.6755885693237975, + "grad_norm": 0.9568703692006882, + "learning_rate": 5.029876967631731e-06, + "loss": 0.756, + "step": 11005 + }, + { + "epoch": 0.6756499585622641, + "grad_norm": 1.0095102206120123, + "learning_rate": 5.028151688305909e-06, + "loss": 0.7854, + "step": 11006 + }, + { + "epoch": 0.6757113478007305, + "grad_norm": 0.9668134417537234, + "learning_rate": 5.0264266055438524e-06, + "loss": 0.7962, + "step": 11007 + }, + { + "epoch": 0.675772737039197, + "grad_norm": 0.579046162127261, + "learning_rate": 5.024701719413747e-06, + "loss": 0.6324, + "step": 11008 + }, + { + "epoch": 0.6758341262776635, + "grad_norm": 0.8965429324912239, + "learning_rate": 5.0229770299837886e-06, + "loss": 0.7405, + "step": 11009 + }, + { + "epoch": 0.67589551551613, + "grad_norm": 1.0344339621629637, + "learning_rate": 5.021252537322172e-06, + "loss": 0.7513, + "step": 11010 + }, + { + "epoch": 0.6759569047545965, + "grad_norm": 0.8929325493996463, + "learning_rate": 5.019528241497071e-06, + "loss": 0.7655, + "step": 11011 + }, + { + "epoch": 0.676018293993063, + "grad_norm": 0.9171545307376573, + "learning_rate": 5.017804142576656e-06, + "loss": 0.7762, + "step": 11012 + }, + { + "epoch": 0.6760796832315296, + "grad_norm": 0.8678927760269483, + "learning_rate": 5.0160802406290884e-06, + "loss": 0.7502, + "step": 11013 + }, + { + "epoch": 0.676141072469996, + "grad_norm": 0.564771485788253, + "learning_rate": 5.014356535722527e-06, + "loss": 0.6712, + "step": 11014 + }, + { + "epoch": 0.6762024617084625, + "grad_norm": 0.834768616247699, + "learning_rate": 5.0126330279251155e-06, + "loss": 0.7503, + "step": 11015 + }, + { + "epoch": 0.676263850946929, + "grad_norm": 0.594448625300534, + "learning_rate": 5.010909717304995e-06, + "loss": 0.6863, + "step": 11016 + }, + { + "epoch": 0.6763252401853955, + "grad_norm": 0.8652847072849087, + "learning_rate": 5.009186603930296e-06, + "loss": 0.7542, + "step": 11017 + }, + { + "epoch": 0.676386629423862, + "grad_norm": 0.9156959000695131, + "learning_rate": 5.007463687869145e-06, + "loss": 0.7948, + "step": 11018 + }, + { + "epoch": 0.6764480186623285, + "grad_norm": 0.9176699684797572, + "learning_rate": 5.005740969189655e-06, + "loss": 0.7486, + "step": 11019 + }, + { + "epoch": 0.676509407900795, + "grad_norm": 1.021357847777156, + "learning_rate": 5.004018447959933e-06, + "loss": 0.8195, + "step": 11020 + }, + { + "epoch": 0.6765707971392615, + "grad_norm": 0.940688849187245, + "learning_rate": 5.002296124248085e-06, + "loss": 0.7655, + "step": 11021 + }, + { + "epoch": 0.6766321863777279, + "grad_norm": 0.900514474964778, + "learning_rate": 5.000573998122205e-06, + "loss": 0.8354, + "step": 11022 + }, + { + "epoch": 0.6766935756161945, + "grad_norm": 0.9185057527781924, + "learning_rate": 4.9988520696503665e-06, + "loss": 0.7873, + "step": 11023 + }, + { + "epoch": 0.676754964854661, + "grad_norm": 0.8623118087514271, + "learning_rate": 4.997130338900657e-06, + "loss": 0.7696, + "step": 11024 + }, + { + "epoch": 0.6768163540931275, + "grad_norm": 0.9017469647356449, + "learning_rate": 4.995408805941142e-06, + "loss": 0.7859, + "step": 11025 + }, + { + "epoch": 0.676877743331594, + "grad_norm": 1.0509585467162448, + "learning_rate": 4.993687470839884e-06, + "loss": 0.7815, + "step": 11026 + }, + { + "epoch": 0.6769391325700604, + "grad_norm": 0.899116481462835, + "learning_rate": 4.991966333664935e-06, + "loss": 0.7303, + "step": 11027 + }, + { + "epoch": 0.677000521808527, + "grad_norm": 0.9465918692654725, + "learning_rate": 4.990245394484343e-06, + "loss": 0.7713, + "step": 11028 + }, + { + "epoch": 0.6770619110469934, + "grad_norm": 0.9649488353763321, + "learning_rate": 4.988524653366144e-06, + "loss": 0.7703, + "step": 11029 + }, + { + "epoch": 0.67712330028546, + "grad_norm": 0.884465953734545, + "learning_rate": 4.986804110378368e-06, + "loss": 0.7724, + "step": 11030 + }, + { + "epoch": 0.6771846895239264, + "grad_norm": 0.8844349298298866, + "learning_rate": 4.9850837655890346e-06, + "loss": 0.7702, + "step": 11031 + }, + { + "epoch": 0.677246078762393, + "grad_norm": 1.0090107651044493, + "learning_rate": 4.983363619066171e-06, + "loss": 0.8172, + "step": 11032 + }, + { + "epoch": 0.6773074680008595, + "grad_norm": 0.9072125176419805, + "learning_rate": 4.9816436708777685e-06, + "loss": 0.7778, + "step": 11033 + }, + { + "epoch": 0.6773688572393259, + "grad_norm": 0.9523526698745889, + "learning_rate": 4.979923921091828e-06, + "loss": 0.7859, + "step": 11034 + }, + { + "epoch": 0.6774302464777925, + "grad_norm": 0.8685859810931933, + "learning_rate": 4.978204369776348e-06, + "loss": 0.7821, + "step": 11035 + }, + { + "epoch": 0.6774916357162589, + "grad_norm": 0.8319171948153334, + "learning_rate": 4.976485016999309e-06, + "loss": 0.7668, + "step": 11036 + }, + { + "epoch": 0.6775530249547255, + "grad_norm": 0.9334277829658211, + "learning_rate": 4.974765862828683e-06, + "loss": 0.7698, + "step": 11037 + }, + { + "epoch": 0.6776144141931919, + "grad_norm": 0.9084748847622921, + "learning_rate": 4.973046907332441e-06, + "loss": 0.8136, + "step": 11038 + }, + { + "epoch": 0.6776758034316585, + "grad_norm": 0.9086189179398584, + "learning_rate": 4.9713281505785404e-06, + "loss": 0.763, + "step": 11039 + }, + { + "epoch": 0.6777371926701249, + "grad_norm": 0.8597322715511649, + "learning_rate": 4.969609592634933e-06, + "loss": 0.7013, + "step": 11040 + }, + { + "epoch": 0.6777985819085914, + "grad_norm": 0.8910582711542071, + "learning_rate": 4.967891233569563e-06, + "loss": 0.7838, + "step": 11041 + }, + { + "epoch": 0.6778599711470579, + "grad_norm": 0.921223333350274, + "learning_rate": 4.966173073450366e-06, + "loss": 0.752, + "step": 11042 + }, + { + "epoch": 0.6779213603855244, + "grad_norm": 0.8559120599989073, + "learning_rate": 4.96445511234527e-06, + "loss": 0.7522, + "step": 11043 + }, + { + "epoch": 0.677982749623991, + "grad_norm": 0.8810202580827742, + "learning_rate": 4.962737350322195e-06, + "loss": 0.8167, + "step": 11044 + }, + { + "epoch": 0.6780441388624574, + "grad_norm": 0.8491524744797622, + "learning_rate": 4.961019787449051e-06, + "loss": 0.779, + "step": 11045 + }, + { + "epoch": 0.678105528100924, + "grad_norm": 0.9210717841022845, + "learning_rate": 4.959302423793748e-06, + "loss": 0.7965, + "step": 11046 + }, + { + "epoch": 0.6781669173393904, + "grad_norm": 1.0200370986139007, + "learning_rate": 4.957585259424184e-06, + "loss": 0.7669, + "step": 11047 + }, + { + "epoch": 0.6782283065778569, + "grad_norm": 0.79850136305581, + "learning_rate": 4.955868294408236e-06, + "loss": 0.7637, + "step": 11048 + }, + { + "epoch": 0.6782896958163234, + "grad_norm": 0.8731773385027418, + "learning_rate": 4.954151528813796e-06, + "loss": 0.7774, + "step": 11049 + }, + { + "epoch": 0.6783510850547899, + "grad_norm": 0.9141710699200799, + "learning_rate": 4.952434962708732e-06, + "loss": 0.7788, + "step": 11050 + }, + { + "epoch": 0.6784124742932564, + "grad_norm": 0.842020067658981, + "learning_rate": 4.950718596160912e-06, + "loss": 0.8064, + "step": 11051 + }, + { + "epoch": 0.6784738635317229, + "grad_norm": 0.8424548515753895, + "learning_rate": 4.94900242923819e-06, + "loss": 0.7291, + "step": 11052 + }, + { + "epoch": 0.6785352527701893, + "grad_norm": 0.8804553260610096, + "learning_rate": 4.947286462008417e-06, + "loss": 0.7684, + "step": 11053 + }, + { + "epoch": 0.6785966420086559, + "grad_norm": 0.9559682653109052, + "learning_rate": 4.945570694539434e-06, + "loss": 0.8037, + "step": 11054 + }, + { + "epoch": 0.6786580312471224, + "grad_norm": 0.8676495034337314, + "learning_rate": 4.943855126899075e-06, + "loss": 0.7205, + "step": 11055 + }, + { + "epoch": 0.6787194204855889, + "grad_norm": 0.9935305511347194, + "learning_rate": 4.942139759155164e-06, + "loss": 0.7858, + "step": 11056 + }, + { + "epoch": 0.6787808097240554, + "grad_norm": 0.8704363748091384, + "learning_rate": 4.940424591375521e-06, + "loss": 0.7874, + "step": 11057 + }, + { + "epoch": 0.6788421989625218, + "grad_norm": 0.9697009186739514, + "learning_rate": 4.938709623627953e-06, + "loss": 0.7953, + "step": 11058 + }, + { + "epoch": 0.6789035882009884, + "grad_norm": 0.8231373711972831, + "learning_rate": 4.93699485598026e-06, + "loss": 0.758, + "step": 11059 + }, + { + "epoch": 0.6789649774394548, + "grad_norm": 0.974843495177568, + "learning_rate": 4.935280288500244e-06, + "loss": 0.8004, + "step": 11060 + }, + { + "epoch": 0.6790263666779214, + "grad_norm": 0.8985869596076477, + "learning_rate": 4.933565921255689e-06, + "loss": 0.7586, + "step": 11061 + }, + { + "epoch": 0.6790877559163878, + "grad_norm": 0.9180131352954667, + "learning_rate": 4.931851754314363e-06, + "loss": 0.7706, + "step": 11062 + }, + { + "epoch": 0.6791491451548544, + "grad_norm": 0.8748893205160061, + "learning_rate": 4.930137787744047e-06, + "loss": 0.7781, + "step": 11063 + }, + { + "epoch": 0.6792105343933208, + "grad_norm": 0.9632563069634352, + "learning_rate": 4.928424021612499e-06, + "loss": 0.7484, + "step": 11064 + }, + { + "epoch": 0.6792719236317873, + "grad_norm": 0.8774601013316822, + "learning_rate": 4.926710455987475e-06, + "loss": 0.77, + "step": 11065 + }, + { + "epoch": 0.6793333128702539, + "grad_norm": 0.8634741952970546, + "learning_rate": 4.924997090936721e-06, + "loss": 0.7748, + "step": 11066 + }, + { + "epoch": 0.6793947021087203, + "grad_norm": 1.036453013399155, + "learning_rate": 4.9232839265279746e-06, + "loss": 0.8359, + "step": 11067 + }, + { + "epoch": 0.6794560913471869, + "grad_norm": 0.9047932299802536, + "learning_rate": 4.9215709628289665e-06, + "loss": 0.7647, + "step": 11068 + }, + { + "epoch": 0.6795174805856533, + "grad_norm": 0.867364971800013, + "learning_rate": 4.91985819990742e-06, + "loss": 0.788, + "step": 11069 + }, + { + "epoch": 0.6795788698241199, + "grad_norm": 0.9092925874797555, + "learning_rate": 4.918145637831046e-06, + "loss": 0.7478, + "step": 11070 + }, + { + "epoch": 0.6796402590625863, + "grad_norm": 0.9357393327312952, + "learning_rate": 4.916433276667561e-06, + "loss": 0.741, + "step": 11071 + }, + { + "epoch": 0.6797016483010528, + "grad_norm": 0.910816764307111, + "learning_rate": 4.914721116484654e-06, + "loss": 0.7853, + "step": 11072 + }, + { + "epoch": 0.6797630375395193, + "grad_norm": 1.0023733413859637, + "learning_rate": 4.913009157350016e-06, + "loss": 0.7871, + "step": 11073 + }, + { + "epoch": 0.6798244267779858, + "grad_norm": 1.0458411182635068, + "learning_rate": 4.911297399331336e-06, + "loss": 0.8492, + "step": 11074 + }, + { + "epoch": 0.6798858160164524, + "grad_norm": 0.86342792639813, + "learning_rate": 4.909585842496287e-06, + "loss": 0.7485, + "step": 11075 + }, + { + "epoch": 0.6799472052549188, + "grad_norm": 0.9522024889882399, + "learning_rate": 4.907874486912535e-06, + "loss": 0.7566, + "step": 11076 + }, + { + "epoch": 0.6800085944933854, + "grad_norm": 0.908468847497418, + "learning_rate": 4.906163332647739e-06, + "loss": 0.7415, + "step": 11077 + }, + { + "epoch": 0.6800699837318518, + "grad_norm": 0.7846245758715304, + "learning_rate": 4.90445237976955e-06, + "loss": 0.8023, + "step": 11078 + }, + { + "epoch": 0.6801313729703183, + "grad_norm": 0.8954747317652183, + "learning_rate": 4.902741628345612e-06, + "loss": 0.7418, + "step": 11079 + }, + { + "epoch": 0.6801927622087848, + "grad_norm": 0.9205561758893672, + "learning_rate": 4.901031078443559e-06, + "loss": 0.8038, + "step": 11080 + }, + { + "epoch": 0.6802541514472513, + "grad_norm": 0.8478407603479192, + "learning_rate": 4.8993207301310185e-06, + "loss": 0.718, + "step": 11081 + }, + { + "epoch": 0.6803155406857178, + "grad_norm": 0.8377982703295324, + "learning_rate": 4.897610583475609e-06, + "loss": 0.7335, + "step": 11082 + }, + { + "epoch": 0.6803769299241843, + "grad_norm": 0.9610379608804697, + "learning_rate": 4.8959006385449446e-06, + "loss": 0.7677, + "step": 11083 + }, + { + "epoch": 0.6804383191626507, + "grad_norm": 0.888126010249932, + "learning_rate": 4.894190895406622e-06, + "loss": 0.7989, + "step": 11084 + }, + { + "epoch": 0.6804997084011173, + "grad_norm": 0.9064382889918543, + "learning_rate": 4.892481354128244e-06, + "loss": 0.748, + "step": 11085 + }, + { + "epoch": 0.6805610976395838, + "grad_norm": 0.9607332647864925, + "learning_rate": 4.890772014777399e-06, + "loss": 0.7794, + "step": 11086 + }, + { + "epoch": 0.6806224868780503, + "grad_norm": 0.8371721435280444, + "learning_rate": 4.889062877421657e-06, + "loss": 0.8059, + "step": 11087 + }, + { + "epoch": 0.6806838761165168, + "grad_norm": 1.0504008359957544, + "learning_rate": 4.8873539421285965e-06, + "loss": 0.7993, + "step": 11088 + }, + { + "epoch": 0.6807452653549833, + "grad_norm": 0.9780907873909365, + "learning_rate": 4.885645208965779e-06, + "loss": 0.7581, + "step": 11089 + }, + { + "epoch": 0.6808066545934498, + "grad_norm": 0.8604940903888729, + "learning_rate": 4.88393667800076e-06, + "loss": 0.7609, + "step": 11090 + }, + { + "epoch": 0.6808680438319162, + "grad_norm": 0.9741184791216366, + "learning_rate": 4.882228349301087e-06, + "loss": 0.8252, + "step": 11091 + }, + { + "epoch": 0.6809294330703828, + "grad_norm": 0.9530881597034104, + "learning_rate": 4.8805202229342985e-06, + "loss": 0.7562, + "step": 11092 + }, + { + "epoch": 0.6809908223088492, + "grad_norm": 0.932939035145314, + "learning_rate": 4.8788122989679275e-06, + "loss": 0.7787, + "step": 11093 + }, + { + "epoch": 0.6810522115473158, + "grad_norm": 0.9282536141668752, + "learning_rate": 4.877104577469496e-06, + "loss": 0.8065, + "step": 11094 + }, + { + "epoch": 0.6811136007857822, + "grad_norm": 0.9709807574272008, + "learning_rate": 4.875397058506516e-06, + "loss": 0.7639, + "step": 11095 + }, + { + "epoch": 0.6811749900242487, + "grad_norm": 0.9973830514605556, + "learning_rate": 4.873689742146506e-06, + "loss": 0.7637, + "step": 11096 + }, + { + "epoch": 0.6812363792627153, + "grad_norm": 0.8771021733037032, + "learning_rate": 4.871982628456954e-06, + "loss": 0.7519, + "step": 11097 + }, + { + "epoch": 0.6812977685011817, + "grad_norm": 0.9706856277818012, + "learning_rate": 4.870275717505351e-06, + "loss": 0.7604, + "step": 11098 + }, + { + "epoch": 0.6813591577396483, + "grad_norm": 0.9195038914879587, + "learning_rate": 4.868569009359189e-06, + "loss": 0.766, + "step": 11099 + }, + { + "epoch": 0.6814205469781147, + "grad_norm": 1.0376628862920965, + "learning_rate": 4.8668625040859386e-06, + "loss": 0.7869, + "step": 11100 + }, + { + "epoch": 0.6814819362165813, + "grad_norm": 1.0494414161930716, + "learning_rate": 4.8651562017530685e-06, + "loss": 0.7431, + "step": 11101 + }, + { + "epoch": 0.6815433254550477, + "grad_norm": 1.0787396564506853, + "learning_rate": 4.863450102428036e-06, + "loss": 0.7876, + "step": 11102 + }, + { + "epoch": 0.6816047146935142, + "grad_norm": 0.9905061599248207, + "learning_rate": 4.861744206178293e-06, + "loss": 0.7607, + "step": 11103 + }, + { + "epoch": 0.6816661039319807, + "grad_norm": 0.826257000316852, + "learning_rate": 4.860038513071282e-06, + "loss": 0.7584, + "step": 11104 + }, + { + "epoch": 0.6817274931704472, + "grad_norm": 0.9851234134459984, + "learning_rate": 4.858333023174436e-06, + "loss": 0.8311, + "step": 11105 + }, + { + "epoch": 0.6817888824089137, + "grad_norm": 0.9528345756034332, + "learning_rate": 4.856627736555194e-06, + "loss": 0.8579, + "step": 11106 + }, + { + "epoch": 0.6818502716473802, + "grad_norm": 0.8368450233805347, + "learning_rate": 4.8549226532809615e-06, + "loss": 0.7579, + "step": 11107 + }, + { + "epoch": 0.6819116608858468, + "grad_norm": 0.957599953665364, + "learning_rate": 4.853217773419153e-06, + "loss": 0.7303, + "step": 11108 + }, + { + "epoch": 0.6819730501243132, + "grad_norm": 0.9765656886642106, + "learning_rate": 4.851513097037171e-06, + "loss": 0.786, + "step": 11109 + }, + { + "epoch": 0.6820344393627797, + "grad_norm": 1.0477524118607482, + "learning_rate": 4.849808624202414e-06, + "loss": 0.813, + "step": 11110 + }, + { + "epoch": 0.6820958286012462, + "grad_norm": 0.9809314374078052, + "learning_rate": 4.848104354982273e-06, + "loss": 0.8391, + "step": 11111 + }, + { + "epoch": 0.6821572178397127, + "grad_norm": 1.0018072158516498, + "learning_rate": 4.846400289444113e-06, + "loss": 0.8128, + "step": 11112 + }, + { + "epoch": 0.6822186070781792, + "grad_norm": 1.0091766488130267, + "learning_rate": 4.844696427655317e-06, + "loss": 0.8021, + "step": 11113 + }, + { + "epoch": 0.6822799963166457, + "grad_norm": 0.9380630494062797, + "learning_rate": 4.8429927696832434e-06, + "loss": 0.7795, + "step": 11114 + }, + { + "epoch": 0.6823413855551121, + "grad_norm": 0.9667845125615934, + "learning_rate": 4.8412893155952465e-06, + "loss": 0.7894, + "step": 11115 + }, + { + "epoch": 0.6824027747935787, + "grad_norm": 0.8214822559895976, + "learning_rate": 4.839586065458674e-06, + "loss": 0.7299, + "step": 11116 + }, + { + "epoch": 0.6824641640320451, + "grad_norm": 0.991232134105129, + "learning_rate": 4.837883019340866e-06, + "loss": 0.79, + "step": 11117 + }, + { + "epoch": 0.6825255532705117, + "grad_norm": 0.9190076640093952, + "learning_rate": 4.836180177309149e-06, + "loss": 0.7913, + "step": 11118 + }, + { + "epoch": 0.6825869425089782, + "grad_norm": 0.9210828148539244, + "learning_rate": 4.834477539430848e-06, + "loss": 0.7802, + "step": 11119 + }, + { + "epoch": 0.6826483317474447, + "grad_norm": 0.8514690431839933, + "learning_rate": 4.8327751057732745e-06, + "loss": 0.7822, + "step": 11120 + }, + { + "epoch": 0.6827097209859112, + "grad_norm": 0.932774013152856, + "learning_rate": 4.831072876403744e-06, + "loss": 0.7187, + "step": 11121 + }, + { + "epoch": 0.6827711102243776, + "grad_norm": 0.9365388922984483, + "learning_rate": 4.829370851389545e-06, + "loss": 0.7537, + "step": 11122 + }, + { + "epoch": 0.6828324994628442, + "grad_norm": 0.840612334668671, + "learning_rate": 4.827669030797966e-06, + "loss": 0.7403, + "step": 11123 + }, + { + "epoch": 0.6828938887013106, + "grad_norm": 0.9856869756865562, + "learning_rate": 4.825967414696297e-06, + "loss": 0.7517, + "step": 11124 + }, + { + "epoch": 0.6829552779397772, + "grad_norm": 0.8772927796013267, + "learning_rate": 4.824266003151814e-06, + "loss": 0.7882, + "step": 11125 + }, + { + "epoch": 0.6830166671782436, + "grad_norm": 0.9698832319061258, + "learning_rate": 4.822564796231769e-06, + "loss": 0.8121, + "step": 11126 + }, + { + "epoch": 0.6830780564167102, + "grad_norm": 0.91051435177168, + "learning_rate": 4.8208637940034335e-06, + "loss": 0.7622, + "step": 11127 + }, + { + "epoch": 0.6831394456551767, + "grad_norm": 0.9150654034827875, + "learning_rate": 4.8191629965340504e-06, + "loss": 0.7375, + "step": 11128 + }, + { + "epoch": 0.6832008348936431, + "grad_norm": 0.8999729319274811, + "learning_rate": 4.8174624038908645e-06, + "loss": 0.8099, + "step": 11129 + }, + { + "epoch": 0.6832622241321097, + "grad_norm": 0.9915209380013444, + "learning_rate": 4.815762016141106e-06, + "loss": 0.8064, + "step": 11130 + }, + { + "epoch": 0.6833236133705761, + "grad_norm": 0.8651323886351243, + "learning_rate": 4.814061833352005e-06, + "loss": 0.7358, + "step": 11131 + }, + { + "epoch": 0.6833850026090427, + "grad_norm": 0.8517715273633554, + "learning_rate": 4.812361855590775e-06, + "loss": 0.7377, + "step": 11132 + }, + { + "epoch": 0.6834463918475091, + "grad_norm": 0.9187647050111036, + "learning_rate": 4.810662082924626e-06, + "loss": 0.7745, + "step": 11133 + }, + { + "epoch": 0.6835077810859757, + "grad_norm": 0.8953801330927424, + "learning_rate": 4.808962515420756e-06, + "loss": 0.7069, + "step": 11134 + }, + { + "epoch": 0.6835691703244421, + "grad_norm": 0.9395768626028996, + "learning_rate": 4.807263153146368e-06, + "loss": 0.8395, + "step": 11135 + }, + { + "epoch": 0.6836305595629086, + "grad_norm": 0.8761214232715323, + "learning_rate": 4.805563996168637e-06, + "loss": 0.7645, + "step": 11136 + }, + { + "epoch": 0.6836919488013751, + "grad_norm": 0.8982419780494707, + "learning_rate": 4.803865044554739e-06, + "loss": 0.7599, + "step": 11137 + }, + { + "epoch": 0.6837533380398416, + "grad_norm": 0.8976601805417872, + "learning_rate": 4.802166298371852e-06, + "loss": 0.771, + "step": 11138 + }, + { + "epoch": 0.6838147272783082, + "grad_norm": 0.9436329157275817, + "learning_rate": 4.800467757687131e-06, + "loss": 0.7591, + "step": 11139 + }, + { + "epoch": 0.6838761165167746, + "grad_norm": 0.9659644647709357, + "learning_rate": 4.798769422567727e-06, + "loss": 0.7753, + "step": 11140 + }, + { + "epoch": 0.6839375057552411, + "grad_norm": 0.913918901947475, + "learning_rate": 4.797071293080786e-06, + "loss": 0.7612, + "step": 11141 + }, + { + "epoch": 0.6839988949937076, + "grad_norm": 0.8555632225798598, + "learning_rate": 4.7953733692934445e-06, + "loss": 0.7432, + "step": 11142 + }, + { + "epoch": 0.6840602842321741, + "grad_norm": 0.9711162841173875, + "learning_rate": 4.7936756512728296e-06, + "loss": 0.7884, + "step": 11143 + }, + { + "epoch": 0.6841216734706406, + "grad_norm": 0.9602807184109187, + "learning_rate": 4.791978139086059e-06, + "loss": 0.7784, + "step": 11144 + }, + { + "epoch": 0.6841830627091071, + "grad_norm": 0.9320724467215561, + "learning_rate": 4.7902808328002535e-06, + "loss": 0.7758, + "step": 11145 + }, + { + "epoch": 0.6842444519475736, + "grad_norm": 1.0076638980607853, + "learning_rate": 4.7885837324825064e-06, + "loss": 0.8097, + "step": 11146 + }, + { + "epoch": 0.6843058411860401, + "grad_norm": 0.9490754931375375, + "learning_rate": 4.786886838199918e-06, + "loss": 0.7509, + "step": 11147 + }, + { + "epoch": 0.6843672304245065, + "grad_norm": 0.8200983537821976, + "learning_rate": 4.785190150019571e-06, + "loss": 0.7704, + "step": 11148 + }, + { + "epoch": 0.6844286196629731, + "grad_norm": 0.8827142041444865, + "learning_rate": 4.783493668008551e-06, + "loss": 0.7543, + "step": 11149 + }, + { + "epoch": 0.6844900089014396, + "grad_norm": 1.0340623679468568, + "learning_rate": 4.781797392233929e-06, + "loss": 0.8043, + "step": 11150 + }, + { + "epoch": 0.6845513981399061, + "grad_norm": 0.853049924345892, + "learning_rate": 4.780101322762759e-06, + "loss": 0.7589, + "step": 11151 + }, + { + "epoch": 0.6846127873783726, + "grad_norm": 0.9345899994976024, + "learning_rate": 4.778405459662105e-06, + "loss": 0.7856, + "step": 11152 + }, + { + "epoch": 0.684674176616839, + "grad_norm": 0.8962266812023781, + "learning_rate": 4.77670980299901e-06, + "loss": 0.7528, + "step": 11153 + }, + { + "epoch": 0.6847355658553056, + "grad_norm": 0.966127454642899, + "learning_rate": 4.775014352840512e-06, + "loss": 0.7568, + "step": 11154 + }, + { + "epoch": 0.684796955093772, + "grad_norm": 1.0312134089611464, + "learning_rate": 4.7733191092536435e-06, + "loss": 0.8106, + "step": 11155 + }, + { + "epoch": 0.6848583443322386, + "grad_norm": 0.9019108497173228, + "learning_rate": 4.771624072305423e-06, + "loss": 0.7738, + "step": 11156 + }, + { + "epoch": 0.684919733570705, + "grad_norm": 0.9615519887367384, + "learning_rate": 4.7699292420628675e-06, + "loss": 0.7687, + "step": 11157 + }, + { + "epoch": 0.6849811228091716, + "grad_norm": 0.9495769299291448, + "learning_rate": 4.768234618592981e-06, + "loss": 0.7636, + "step": 11158 + }, + { + "epoch": 0.685042512047638, + "grad_norm": 0.94055980845642, + "learning_rate": 4.7665402019627585e-06, + "loss": 0.7355, + "step": 11159 + }, + { + "epoch": 0.6851039012861045, + "grad_norm": 0.9429703421423542, + "learning_rate": 4.764845992239198e-06, + "loss": 0.7821, + "step": 11160 + }, + { + "epoch": 0.6851652905245711, + "grad_norm": 0.9294239850246475, + "learning_rate": 4.763151989489273e-06, + "loss": 0.7608, + "step": 11161 + }, + { + "epoch": 0.6852266797630375, + "grad_norm": 1.0018492243390786, + "learning_rate": 4.761458193779954e-06, + "loss": 0.7814, + "step": 11162 + }, + { + "epoch": 0.6852880690015041, + "grad_norm": 1.0712781757687495, + "learning_rate": 4.759764605178214e-06, + "loss": 0.8016, + "step": 11163 + }, + { + "epoch": 0.6853494582399705, + "grad_norm": 0.9264897946469525, + "learning_rate": 4.758071223751006e-06, + "loss": 0.7689, + "step": 11164 + }, + { + "epoch": 0.6854108474784371, + "grad_norm": 0.8721116201392729, + "learning_rate": 4.756378049565279e-06, + "loss": 0.7567, + "step": 11165 + }, + { + "epoch": 0.6854722367169035, + "grad_norm": 0.9041088254509932, + "learning_rate": 4.754685082687972e-06, + "loss": 0.8681, + "step": 11166 + }, + { + "epoch": 0.68553362595537, + "grad_norm": 0.9807039444851381, + "learning_rate": 4.752992323186017e-06, + "loss": 0.7684, + "step": 11167 + }, + { + "epoch": 0.6855950151938365, + "grad_norm": 0.9516903345761556, + "learning_rate": 4.75129977112634e-06, + "loss": 0.7458, + "step": 11168 + }, + { + "epoch": 0.685656404432303, + "grad_norm": 0.8608249519180945, + "learning_rate": 4.749607426575849e-06, + "loss": 0.7716, + "step": 11169 + }, + { + "epoch": 0.6857177936707695, + "grad_norm": 0.9337775993943809, + "learning_rate": 4.747915289601467e-06, + "loss": 0.7489, + "step": 11170 + }, + { + "epoch": 0.685779182909236, + "grad_norm": 0.6063863845606426, + "learning_rate": 4.7462233602700794e-06, + "loss": 0.6742, + "step": 11171 + }, + { + "epoch": 0.6858405721477026, + "grad_norm": 0.9169792538059592, + "learning_rate": 4.7445316386485814e-06, + "loss": 0.7636, + "step": 11172 + }, + { + "epoch": 0.685901961386169, + "grad_norm": 0.893375609569779, + "learning_rate": 4.742840124803852e-06, + "loss": 0.7726, + "step": 11173 + }, + { + "epoch": 0.6859633506246355, + "grad_norm": 0.8937522491579615, + "learning_rate": 4.741148818802773e-06, + "loss": 0.7527, + "step": 11174 + }, + { + "epoch": 0.686024739863102, + "grad_norm": 0.8943049703516248, + "learning_rate": 4.7394577207122125e-06, + "loss": 0.773, + "step": 11175 + }, + { + "epoch": 0.6860861291015685, + "grad_norm": 0.9259946631727655, + "learning_rate": 4.737766830599016e-06, + "loss": 0.7894, + "step": 11176 + }, + { + "epoch": 0.686147518340035, + "grad_norm": 0.9126735765856752, + "learning_rate": 4.736076148530044e-06, + "loss": 0.7348, + "step": 11177 + }, + { + "epoch": 0.6862089075785015, + "grad_norm": 0.8800183330666986, + "learning_rate": 4.734385674572136e-06, + "loss": 0.766, + "step": 11178 + }, + { + "epoch": 0.6862702968169679, + "grad_norm": 0.9316657037622685, + "learning_rate": 4.732695408792125e-06, + "loss": 0.8269, + "step": 11179 + }, + { + "epoch": 0.6863316860554345, + "grad_norm": 1.045575399811736, + "learning_rate": 4.731005351256835e-06, + "loss": 0.7807, + "step": 11180 + }, + { + "epoch": 0.686393075293901, + "grad_norm": 0.8228019788335549, + "learning_rate": 4.7293155020330846e-06, + "loss": 0.7414, + "step": 11181 + }, + { + "epoch": 0.6864544645323675, + "grad_norm": 0.9200606061290809, + "learning_rate": 4.727625861187682e-06, + "loss": 0.7719, + "step": 11182 + }, + { + "epoch": 0.686515853770834, + "grad_norm": 0.964791253898858, + "learning_rate": 4.725936428787424e-06, + "loss": 0.7903, + "step": 11183 + }, + { + "epoch": 0.6865772430093005, + "grad_norm": 0.9771925495636087, + "learning_rate": 4.72424720489911e-06, + "loss": 0.7718, + "step": 11184 + }, + { + "epoch": 0.686638632247767, + "grad_norm": 0.9207471312732691, + "learning_rate": 4.722558189589526e-06, + "loss": 0.7718, + "step": 11185 + }, + { + "epoch": 0.6867000214862334, + "grad_norm": 0.8727219357365569, + "learning_rate": 4.720869382925437e-06, + "loss": 0.7575, + "step": 11186 + }, + { + "epoch": 0.6867614107247, + "grad_norm": 0.9687864197489903, + "learning_rate": 4.719180784973613e-06, + "loss": 0.7689, + "step": 11187 + }, + { + "epoch": 0.6868227999631664, + "grad_norm": 0.9360711679848477, + "learning_rate": 4.71749239580082e-06, + "loss": 0.8039, + "step": 11188 + }, + { + "epoch": 0.686884189201633, + "grad_norm": 0.9458034799172933, + "learning_rate": 4.7158042154738094e-06, + "loss": 0.7742, + "step": 11189 + }, + { + "epoch": 0.6869455784400994, + "grad_norm": 0.8634766805103341, + "learning_rate": 4.714116244059312e-06, + "loss": 0.7466, + "step": 11190 + }, + { + "epoch": 0.687006967678566, + "grad_norm": 0.9722389309911351, + "learning_rate": 4.712428481624074e-06, + "loss": 0.8006, + "step": 11191 + }, + { + "epoch": 0.6870683569170325, + "grad_norm": 0.9060889372768822, + "learning_rate": 4.7107409282348194e-06, + "loss": 0.7995, + "step": 11192 + }, + { + "epoch": 0.6871297461554989, + "grad_norm": 0.8670965646737907, + "learning_rate": 4.709053583958263e-06, + "loss": 0.7904, + "step": 11193 + }, + { + "epoch": 0.6871911353939655, + "grad_norm": 0.9289342056505753, + "learning_rate": 4.7073664488611185e-06, + "loss": 0.7794, + "step": 11194 + }, + { + "epoch": 0.6872525246324319, + "grad_norm": 1.008978975133801, + "learning_rate": 4.705679523010084e-06, + "loss": 0.8055, + "step": 11195 + }, + { + "epoch": 0.6873139138708985, + "grad_norm": 1.0405036000229257, + "learning_rate": 4.703992806471853e-06, + "loss": 0.796, + "step": 11196 + }, + { + "epoch": 0.6873753031093649, + "grad_norm": 0.9356379011460211, + "learning_rate": 4.702306299313113e-06, + "loss": 0.7376, + "step": 11197 + }, + { + "epoch": 0.6874366923478314, + "grad_norm": 0.8680021665495881, + "learning_rate": 4.700620001600534e-06, + "loss": 0.7797, + "step": 11198 + }, + { + "epoch": 0.6874980815862979, + "grad_norm": 0.8889945998413682, + "learning_rate": 4.698933913400798e-06, + "loss": 0.7624, + "step": 11199 + }, + { + "epoch": 0.6875594708247644, + "grad_norm": 0.8909078302785487, + "learning_rate": 4.697248034780553e-06, + "loss": 0.8021, + "step": 11200 + }, + { + "epoch": 0.6876208600632309, + "grad_norm": 0.9387713731158651, + "learning_rate": 4.69556236580645e-06, + "loss": 0.7716, + "step": 11201 + }, + { + "epoch": 0.6876822493016974, + "grad_norm": 0.8538516217786516, + "learning_rate": 4.693876906545141e-06, + "loss": 0.7956, + "step": 11202 + }, + { + "epoch": 0.687743638540164, + "grad_norm": 0.9095078240205975, + "learning_rate": 4.692191657063257e-06, + "loss": 0.7409, + "step": 11203 + }, + { + "epoch": 0.6878050277786304, + "grad_norm": 0.9598985599885037, + "learning_rate": 4.690506617427424e-06, + "loss": 0.7684, + "step": 11204 + }, + { + "epoch": 0.6878664170170969, + "grad_norm": 0.9384246728837491, + "learning_rate": 4.6888217877042616e-06, + "loss": 0.7798, + "step": 11205 + }, + { + "epoch": 0.6879278062555634, + "grad_norm": 0.9455480818572735, + "learning_rate": 4.687137167960381e-06, + "loss": 0.7945, + "step": 11206 + }, + { + "epoch": 0.6879891954940299, + "grad_norm": 0.8951268149054411, + "learning_rate": 4.685452758262382e-06, + "loss": 0.7903, + "step": 11207 + }, + { + "epoch": 0.6880505847324964, + "grad_norm": 0.959798474027011, + "learning_rate": 4.683768558676858e-06, + "loss": 0.8427, + "step": 11208 + }, + { + "epoch": 0.6881119739709629, + "grad_norm": 0.960098561077682, + "learning_rate": 4.682084569270402e-06, + "loss": 0.7967, + "step": 11209 + }, + { + "epoch": 0.6881733632094293, + "grad_norm": 0.9672887986695503, + "learning_rate": 4.680400790109581e-06, + "loss": 0.8093, + "step": 11210 + }, + { + "epoch": 0.6882347524478959, + "grad_norm": 0.8441618405566184, + "learning_rate": 4.67871722126097e-06, + "loss": 0.7308, + "step": 11211 + }, + { + "epoch": 0.6882961416863623, + "grad_norm": 0.949257297809415, + "learning_rate": 4.677033862791122e-06, + "loss": 0.7955, + "step": 11212 + }, + { + "epoch": 0.6883575309248289, + "grad_norm": 0.9366284437046327, + "learning_rate": 4.675350714766599e-06, + "loss": 0.7454, + "step": 11213 + }, + { + "epoch": 0.6884189201632954, + "grad_norm": 0.8685775154616622, + "learning_rate": 4.673667777253944e-06, + "loss": 0.7286, + "step": 11214 + }, + { + "epoch": 0.6884803094017619, + "grad_norm": 0.8602366398179127, + "learning_rate": 4.671985050319681e-06, + "loss": 0.719, + "step": 11215 + }, + { + "epoch": 0.6885416986402284, + "grad_norm": 1.0617813454821214, + "learning_rate": 4.670302534030351e-06, + "loss": 0.8142, + "step": 11216 + }, + { + "epoch": 0.6886030878786948, + "grad_norm": 0.845628427609757, + "learning_rate": 4.668620228452465e-06, + "loss": 0.7864, + "step": 11217 + }, + { + "epoch": 0.6886644771171614, + "grad_norm": 0.9377263545652615, + "learning_rate": 4.666938133652537e-06, + "loss": 0.7898, + "step": 11218 + }, + { + "epoch": 0.6887258663556278, + "grad_norm": 0.9902447953882029, + "learning_rate": 4.665256249697067e-06, + "loss": 0.7892, + "step": 11219 + }, + { + "epoch": 0.6887872555940944, + "grad_norm": 0.8542775016601012, + "learning_rate": 4.663574576652549e-06, + "loss": 0.8016, + "step": 11220 + }, + { + "epoch": 0.6888486448325608, + "grad_norm": 0.8439942154342133, + "learning_rate": 4.66189311458547e-06, + "loss": 0.7585, + "step": 11221 + }, + { + "epoch": 0.6889100340710274, + "grad_norm": 0.9249575504803065, + "learning_rate": 4.6602118635623064e-06, + "loss": 0.7859, + "step": 11222 + }, + { + "epoch": 0.6889714233094938, + "grad_norm": 1.0076854213460567, + "learning_rate": 4.658530823649523e-06, + "loss": 0.7903, + "step": 11223 + }, + { + "epoch": 0.6890328125479603, + "grad_norm": 0.8734727142271846, + "learning_rate": 4.656849994913593e-06, + "loss": 0.7384, + "step": 11224 + }, + { + "epoch": 0.6890942017864269, + "grad_norm": 0.9668000482537982, + "learning_rate": 4.6551693774209535e-06, + "loss": 0.8694, + "step": 11225 + }, + { + "epoch": 0.6891555910248933, + "grad_norm": 0.9147179872543404, + "learning_rate": 4.653488971238054e-06, + "loss": 0.7285, + "step": 11226 + }, + { + "epoch": 0.6892169802633599, + "grad_norm": 0.9250186631617656, + "learning_rate": 4.651808776431333e-06, + "loss": 0.8039, + "step": 11227 + }, + { + "epoch": 0.6892783695018263, + "grad_norm": 0.8877925533110081, + "learning_rate": 4.650128793067215e-06, + "loss": 0.7489, + "step": 11228 + }, + { + "epoch": 0.6893397587402929, + "grad_norm": 0.9098672554436463, + "learning_rate": 4.648449021212118e-06, + "loss": 0.7573, + "step": 11229 + }, + { + "epoch": 0.6894011479787593, + "grad_norm": 1.0375139805259455, + "learning_rate": 4.646769460932454e-06, + "loss": 0.8004, + "step": 11230 + }, + { + "epoch": 0.6894625372172258, + "grad_norm": 0.5660920457025901, + "learning_rate": 4.6450901122946255e-06, + "loss": 0.6573, + "step": 11231 + }, + { + "epoch": 0.6895239264556923, + "grad_norm": 0.9878667518393663, + "learning_rate": 4.643410975365024e-06, + "loss": 0.8075, + "step": 11232 + }, + { + "epoch": 0.6895853156941588, + "grad_norm": 0.9991949277731254, + "learning_rate": 4.641732050210032e-06, + "loss": 0.7337, + "step": 11233 + }, + { + "epoch": 0.6896467049326254, + "grad_norm": 0.8921350579071052, + "learning_rate": 4.640053336896038e-06, + "loss": 0.7315, + "step": 11234 + }, + { + "epoch": 0.6897080941710918, + "grad_norm": 1.0047273053103005, + "learning_rate": 4.638374835489398e-06, + "loss": 0.7434, + "step": 11235 + }, + { + "epoch": 0.6897694834095583, + "grad_norm": 0.8766397933072498, + "learning_rate": 4.636696546056478e-06, + "loss": 0.8033, + "step": 11236 + }, + { + "epoch": 0.6898308726480248, + "grad_norm": 0.7894528832174916, + "learning_rate": 4.635018468663623e-06, + "loss": 0.766, + "step": 11237 + }, + { + "epoch": 0.6898922618864913, + "grad_norm": 0.9806529288803655, + "learning_rate": 4.6333406033771865e-06, + "loss": 0.7576, + "step": 11238 + }, + { + "epoch": 0.6899536511249578, + "grad_norm": 1.006253403150475, + "learning_rate": 4.631662950263502e-06, + "loss": 0.7701, + "step": 11239 + }, + { + "epoch": 0.6900150403634243, + "grad_norm": 0.9016149644743405, + "learning_rate": 4.629985509388887e-06, + "loss": 0.7748, + "step": 11240 + }, + { + "epoch": 0.6900764296018908, + "grad_norm": 0.8937868831356881, + "learning_rate": 4.6283082808196685e-06, + "loss": 0.7297, + "step": 11241 + }, + { + "epoch": 0.6901378188403573, + "grad_norm": 0.8822434058484951, + "learning_rate": 4.626631264622153e-06, + "loss": 0.8034, + "step": 11242 + }, + { + "epoch": 0.6901992080788237, + "grad_norm": 0.9931627296685183, + "learning_rate": 4.624954460862644e-06, + "loss": 0.7759, + "step": 11243 + }, + { + "epoch": 0.6902605973172903, + "grad_norm": 0.9892968677860043, + "learning_rate": 4.6232778696074306e-06, + "loss": 0.7931, + "step": 11244 + }, + { + "epoch": 0.6903219865557568, + "grad_norm": 0.6798483097671681, + "learning_rate": 4.621601490922803e-06, + "loss": 0.7317, + "step": 11245 + }, + { + "epoch": 0.6903833757942233, + "grad_norm": 0.8775423462547436, + "learning_rate": 4.619925324875031e-06, + "loss": 0.8167, + "step": 11246 + }, + { + "epoch": 0.6904447650326898, + "grad_norm": 0.9005970001558731, + "learning_rate": 4.618249371530383e-06, + "loss": 0.8015, + "step": 11247 + }, + { + "epoch": 0.6905061542711562, + "grad_norm": 0.9962879446970266, + "learning_rate": 4.616573630955125e-06, + "loss": 0.7691, + "step": 11248 + }, + { + "epoch": 0.6905675435096228, + "grad_norm": 0.9401888113803359, + "learning_rate": 4.614898103215507e-06, + "loss": 0.7839, + "step": 11249 + }, + { + "epoch": 0.6906289327480892, + "grad_norm": 0.9700894197387949, + "learning_rate": 4.613222788377766e-06, + "loss": 0.771, + "step": 11250 + }, + { + "epoch": 0.6906903219865558, + "grad_norm": 0.9217242518255117, + "learning_rate": 4.611547686508134e-06, + "loss": 0.7092, + "step": 11251 + }, + { + "epoch": 0.6907517112250222, + "grad_norm": 0.8939149229890269, + "learning_rate": 4.609872797672845e-06, + "loss": 0.8033, + "step": 11252 + }, + { + "epoch": 0.6908131004634888, + "grad_norm": 0.9903313441066781, + "learning_rate": 4.6081981219381166e-06, + "loss": 0.7459, + "step": 11253 + }, + { + "epoch": 0.6908744897019552, + "grad_norm": 0.9545812818764191, + "learning_rate": 4.606523659370147e-06, + "loss": 0.7716, + "step": 11254 + }, + { + "epoch": 0.6909358789404217, + "grad_norm": 0.9812215027548653, + "learning_rate": 4.604849410035146e-06, + "loss": 0.7396, + "step": 11255 + }, + { + "epoch": 0.6909972681788883, + "grad_norm": 0.9183594813648479, + "learning_rate": 4.603175373999305e-06, + "loss": 0.7957, + "step": 11256 + }, + { + "epoch": 0.6910586574173547, + "grad_norm": 0.6107350742366237, + "learning_rate": 4.601501551328804e-06, + "loss": 0.6845, + "step": 11257 + }, + { + "epoch": 0.6911200466558213, + "grad_norm": 0.9508109028129182, + "learning_rate": 4.5998279420898206e-06, + "loss": 0.8098, + "step": 11258 + }, + { + "epoch": 0.6911814358942877, + "grad_norm": 0.9104511021935976, + "learning_rate": 4.59815454634852e-06, + "loss": 0.8264, + "step": 11259 + }, + { + "epoch": 0.6912428251327543, + "grad_norm": 0.874217343213091, + "learning_rate": 4.596481364171062e-06, + "loss": 0.7481, + "step": 11260 + }, + { + "epoch": 0.6913042143712207, + "grad_norm": 0.9763098459798832, + "learning_rate": 4.5948083956235955e-06, + "loss": 0.8073, + "step": 11261 + }, + { + "epoch": 0.6913656036096872, + "grad_norm": 0.9247341393697386, + "learning_rate": 4.593135640772259e-06, + "loss": 0.7662, + "step": 11262 + }, + { + "epoch": 0.6914269928481537, + "grad_norm": 0.9863901212239613, + "learning_rate": 4.591463099683196e-06, + "loss": 0.7727, + "step": 11263 + }, + { + "epoch": 0.6914883820866202, + "grad_norm": 0.9759246459833711, + "learning_rate": 4.589790772422519e-06, + "loss": 0.771, + "step": 11264 + }, + { + "epoch": 0.6915497713250867, + "grad_norm": 1.0485172596661447, + "learning_rate": 4.588118659056346e-06, + "loss": 0.7858, + "step": 11265 + }, + { + "epoch": 0.6916111605635532, + "grad_norm": 0.9444152343727125, + "learning_rate": 4.58644675965079e-06, + "loss": 0.7708, + "step": 11266 + }, + { + "epoch": 0.6916725498020198, + "grad_norm": 0.9556662360039385, + "learning_rate": 4.584775074271946e-06, + "loss": 0.7399, + "step": 11267 + }, + { + "epoch": 0.6917339390404862, + "grad_norm": 1.0097145887096315, + "learning_rate": 4.583103602985909e-06, + "loss": 0.756, + "step": 11268 + }, + { + "epoch": 0.6917953282789527, + "grad_norm": 0.8839623360617702, + "learning_rate": 4.5814323458587565e-06, + "loss": 0.8045, + "step": 11269 + }, + { + "epoch": 0.6918567175174192, + "grad_norm": 0.9458785135076454, + "learning_rate": 4.579761302956564e-06, + "loss": 0.777, + "step": 11270 + }, + { + "epoch": 0.6919181067558857, + "grad_norm": 1.026711746329291, + "learning_rate": 4.5780904743453965e-06, + "loss": 0.7433, + "step": 11271 + }, + { + "epoch": 0.6919794959943522, + "grad_norm": 1.014861231052664, + "learning_rate": 4.576419860091308e-06, + "loss": 0.804, + "step": 11272 + }, + { + "epoch": 0.6920408852328187, + "grad_norm": 0.9508168863886157, + "learning_rate": 4.574749460260356e-06, + "loss": 0.8027, + "step": 11273 + }, + { + "epoch": 0.6921022744712851, + "grad_norm": 0.8839996031166688, + "learning_rate": 4.573079274918571e-06, + "loss": 0.7559, + "step": 11274 + }, + { + "epoch": 0.6921636637097517, + "grad_norm": 0.8616108518736691, + "learning_rate": 4.571409304131987e-06, + "loss": 0.7972, + "step": 11275 + }, + { + "epoch": 0.6922250529482181, + "grad_norm": 0.8945283152410417, + "learning_rate": 4.569739547966625e-06, + "loss": 0.7279, + "step": 11276 + }, + { + "epoch": 0.6922864421866847, + "grad_norm": 0.8466322721455963, + "learning_rate": 4.568070006488504e-06, + "loss": 0.7508, + "step": 11277 + }, + { + "epoch": 0.6923478314251512, + "grad_norm": 0.9369135758650474, + "learning_rate": 4.566400679763633e-06, + "loss": 0.7718, + "step": 11278 + }, + { + "epoch": 0.6924092206636177, + "grad_norm": 0.9727181576059876, + "learning_rate": 4.564731567857995e-06, + "loss": 0.7883, + "step": 11279 + }, + { + "epoch": 0.6924706099020842, + "grad_norm": 0.9197605954028483, + "learning_rate": 4.563062670837593e-06, + "loss": 0.7486, + "step": 11280 + }, + { + "epoch": 0.6925319991405506, + "grad_norm": 0.9543565440569546, + "learning_rate": 4.561393988768401e-06, + "loss": 0.7591, + "step": 11281 + }, + { + "epoch": 0.6925933883790172, + "grad_norm": 0.882492138895281, + "learning_rate": 4.559725521716393e-06, + "loss": 0.7525, + "step": 11282 + }, + { + "epoch": 0.6926547776174836, + "grad_norm": 0.8368650272920081, + "learning_rate": 4.558057269747532e-06, + "loss": 0.7634, + "step": 11283 + }, + { + "epoch": 0.6927161668559502, + "grad_norm": 0.8912617267695189, + "learning_rate": 4.556389232927773e-06, + "loss": 0.8088, + "step": 11284 + }, + { + "epoch": 0.6927775560944166, + "grad_norm": 0.901577701571526, + "learning_rate": 4.5547214113230605e-06, + "loss": 0.7719, + "step": 11285 + }, + { + "epoch": 0.6928389453328831, + "grad_norm": 0.8720296932689542, + "learning_rate": 4.553053804999332e-06, + "loss": 0.7545, + "step": 11286 + }, + { + "epoch": 0.6929003345713497, + "grad_norm": 0.9214294272920255, + "learning_rate": 4.551386414022522e-06, + "loss": 0.7702, + "step": 11287 + }, + { + "epoch": 0.6929617238098161, + "grad_norm": 0.9775203268191262, + "learning_rate": 4.549719238458552e-06, + "loss": 0.7616, + "step": 11288 + }, + { + "epoch": 0.6930231130482827, + "grad_norm": 0.8912673782626591, + "learning_rate": 4.548052278373327e-06, + "loss": 0.7565, + "step": 11289 + }, + { + "epoch": 0.6930845022867491, + "grad_norm": 1.0510066883667826, + "learning_rate": 4.546385533832751e-06, + "loss": 0.7762, + "step": 11290 + }, + { + "epoch": 0.6931458915252157, + "grad_norm": 0.8949671558024413, + "learning_rate": 4.544719004902726e-06, + "loss": 0.8329, + "step": 11291 + }, + { + "epoch": 0.6932072807636821, + "grad_norm": 0.8908215221373749, + "learning_rate": 4.543052691649136e-06, + "loss": 0.7963, + "step": 11292 + }, + { + "epoch": 0.6932686700021486, + "grad_norm": 0.6086957536829469, + "learning_rate": 4.5413865941378585e-06, + "loss": 0.6757, + "step": 11293 + }, + { + "epoch": 0.6933300592406151, + "grad_norm": 0.8958787172825978, + "learning_rate": 4.539720712434764e-06, + "loss": 0.7025, + "step": 11294 + }, + { + "epoch": 0.6933914484790816, + "grad_norm": 0.8882103240646148, + "learning_rate": 4.538055046605714e-06, + "loss": 0.7599, + "step": 11295 + }, + { + "epoch": 0.6934528377175481, + "grad_norm": 0.9090997176151948, + "learning_rate": 4.53638959671656e-06, + "loss": 0.7656, + "step": 11296 + }, + { + "epoch": 0.6935142269560146, + "grad_norm": 0.8828031563231763, + "learning_rate": 4.5347243628331425e-06, + "loss": 0.7401, + "step": 11297 + }, + { + "epoch": 0.6935756161944812, + "grad_norm": 1.0026414822790979, + "learning_rate": 4.533059345021309e-06, + "loss": 0.7687, + "step": 11298 + }, + { + "epoch": 0.6936370054329476, + "grad_norm": 1.0312589625535442, + "learning_rate": 4.531394543346875e-06, + "loss": 0.7968, + "step": 11299 + }, + { + "epoch": 0.6936983946714141, + "grad_norm": 0.9447735739037066, + "learning_rate": 4.529729957875664e-06, + "loss": 0.7359, + "step": 11300 + }, + { + "epoch": 0.6937597839098806, + "grad_norm": 0.9061303402223415, + "learning_rate": 4.528065588673479e-06, + "loss": 0.8528, + "step": 11301 + }, + { + "epoch": 0.6938211731483471, + "grad_norm": 0.9537075300707725, + "learning_rate": 4.526401435806133e-06, + "loss": 0.722, + "step": 11302 + }, + { + "epoch": 0.6938825623868136, + "grad_norm": 0.95675123817704, + "learning_rate": 4.524737499339415e-06, + "loss": 0.7876, + "step": 11303 + }, + { + "epoch": 0.6939439516252801, + "grad_norm": 1.025777554510087, + "learning_rate": 4.523073779339101e-06, + "loss": 0.7546, + "step": 11304 + }, + { + "epoch": 0.6940053408637465, + "grad_norm": 0.8563327065647247, + "learning_rate": 4.5214102758709774e-06, + "loss": 0.7514, + "step": 11305 + }, + { + "epoch": 0.6940667301022131, + "grad_norm": 0.9350676419479592, + "learning_rate": 4.519746989000806e-06, + "loss": 0.785, + "step": 11306 + }, + { + "epoch": 0.6941281193406795, + "grad_norm": 0.7637684773558179, + "learning_rate": 4.518083918794347e-06, + "loss": 0.7419, + "step": 11307 + }, + { + "epoch": 0.6941895085791461, + "grad_norm": 0.9407127630315312, + "learning_rate": 4.516421065317351e-06, + "loss": 0.7634, + "step": 11308 + }, + { + "epoch": 0.6942508978176126, + "grad_norm": 0.9927063191189139, + "learning_rate": 4.5147584286355575e-06, + "loss": 0.7838, + "step": 11309 + }, + { + "epoch": 0.6943122870560791, + "grad_norm": 0.9196228381256751, + "learning_rate": 4.5130960088147e-06, + "loss": 0.7805, + "step": 11310 + }, + { + "epoch": 0.6943736762945456, + "grad_norm": 0.9040684456137358, + "learning_rate": 4.511433805920501e-06, + "loss": 0.7574, + "step": 11311 + }, + { + "epoch": 0.694435065533012, + "grad_norm": 0.8936532838816198, + "learning_rate": 4.509771820018682e-06, + "loss": 0.7856, + "step": 11312 + }, + { + "epoch": 0.6944964547714786, + "grad_norm": 0.944864769105484, + "learning_rate": 4.50811005117495e-06, + "loss": 0.7919, + "step": 11313 + }, + { + "epoch": 0.694557844009945, + "grad_norm": 0.5540551857981912, + "learning_rate": 4.506448499454996e-06, + "loss": 0.6265, + "step": 11314 + }, + { + "epoch": 0.6946192332484116, + "grad_norm": 0.9242754267336385, + "learning_rate": 4.504787164924511e-06, + "loss": 0.8059, + "step": 11315 + }, + { + "epoch": 0.694680622486878, + "grad_norm": 0.9358688868663253, + "learning_rate": 4.503126047649184e-06, + "loss": 0.7671, + "step": 11316 + }, + { + "epoch": 0.6947420117253446, + "grad_norm": 1.0664226190638209, + "learning_rate": 4.501465147694684e-06, + "loss": 0.7735, + "step": 11317 + }, + { + "epoch": 0.694803400963811, + "grad_norm": 0.9056380133500337, + "learning_rate": 4.499804465126675e-06, + "loss": 0.7458, + "step": 11318 + }, + { + "epoch": 0.6948647902022775, + "grad_norm": 0.9473142008004015, + "learning_rate": 4.498144000010811e-06, + "loss": 0.8101, + "step": 11319 + }, + { + "epoch": 0.6949261794407441, + "grad_norm": 1.1066833669348526, + "learning_rate": 4.496483752412743e-06, + "loss": 0.7765, + "step": 11320 + }, + { + "epoch": 0.6949875686792105, + "grad_norm": 1.0543044415123803, + "learning_rate": 4.494823722398105e-06, + "loss": 0.7706, + "step": 11321 + }, + { + "epoch": 0.6950489579176771, + "grad_norm": 0.8402842100616131, + "learning_rate": 4.49316391003253e-06, + "loss": 0.7472, + "step": 11322 + }, + { + "epoch": 0.6951103471561435, + "grad_norm": 0.9332103658663512, + "learning_rate": 4.491504315381638e-06, + "loss": 0.7992, + "step": 11323 + }, + { + "epoch": 0.69517173639461, + "grad_norm": 0.9847481560125708, + "learning_rate": 4.489844938511042e-06, + "loss": 0.7797, + "step": 11324 + }, + { + "epoch": 0.6952331256330765, + "grad_norm": 0.8590913093726779, + "learning_rate": 4.4881857794863424e-06, + "loss": 0.7741, + "step": 11325 + }, + { + "epoch": 0.695294514871543, + "grad_norm": 0.8682985407044972, + "learning_rate": 4.486526838373142e-06, + "loss": 0.7288, + "step": 11326 + }, + { + "epoch": 0.6953559041100095, + "grad_norm": 1.041897566129664, + "learning_rate": 4.4848681152370274e-06, + "loss": 0.8086, + "step": 11327 + }, + { + "epoch": 0.695417293348476, + "grad_norm": 0.9051812278767766, + "learning_rate": 4.48320961014357e-06, + "loss": 0.7703, + "step": 11328 + }, + { + "epoch": 0.6954786825869425, + "grad_norm": 0.9762193569483857, + "learning_rate": 4.4815513231583385e-06, + "loss": 0.7679, + "step": 11329 + }, + { + "epoch": 0.695540071825409, + "grad_norm": 0.9007086530586991, + "learning_rate": 4.479893254346901e-06, + "loss": 0.7856, + "step": 11330 + }, + { + "epoch": 0.6956014610638755, + "grad_norm": 0.8489682133792499, + "learning_rate": 4.478235403774808e-06, + "loss": 0.7515, + "step": 11331 + }, + { + "epoch": 0.695662850302342, + "grad_norm": 0.9936987235141429, + "learning_rate": 4.476577771507601e-06, + "loss": 0.736, + "step": 11332 + }, + { + "epoch": 0.6957242395408085, + "grad_norm": 0.8798806308425755, + "learning_rate": 4.474920357610816e-06, + "loss": 0.7478, + "step": 11333 + }, + { + "epoch": 0.695785628779275, + "grad_norm": 0.8908758730110051, + "learning_rate": 4.47326316214998e-06, + "loss": 0.774, + "step": 11334 + }, + { + "epoch": 0.6958470180177415, + "grad_norm": 0.8458713760932628, + "learning_rate": 4.47160618519061e-06, + "loss": 0.7354, + "step": 11335 + }, + { + "epoch": 0.695908407256208, + "grad_norm": 0.8001729316127263, + "learning_rate": 4.469949426798211e-06, + "loss": 0.7538, + "step": 11336 + }, + { + "epoch": 0.6959697964946745, + "grad_norm": 0.9622458766430334, + "learning_rate": 4.468292887038297e-06, + "loss": 0.7847, + "step": 11337 + }, + { + "epoch": 0.6960311857331409, + "grad_norm": 1.0973833295831783, + "learning_rate": 4.466636565976345e-06, + "loss": 0.771, + "step": 11338 + }, + { + "epoch": 0.6960925749716075, + "grad_norm": 0.8767836119978347, + "learning_rate": 4.464980463677846e-06, + "loss": 0.7482, + "step": 11339 + }, + { + "epoch": 0.696153964210074, + "grad_norm": 0.9356531488632446, + "learning_rate": 4.463324580208268e-06, + "loss": 0.7413, + "step": 11340 + }, + { + "epoch": 0.6962153534485405, + "grad_norm": 0.8088987050026832, + "learning_rate": 4.461668915633085e-06, + "loss": 0.768, + "step": 11341 + }, + { + "epoch": 0.696276742687007, + "grad_norm": 1.0402947944472973, + "learning_rate": 4.460013470017756e-06, + "loss": 0.7684, + "step": 11342 + }, + { + "epoch": 0.6963381319254734, + "grad_norm": 0.931874590230359, + "learning_rate": 4.458358243427715e-06, + "loss": 0.7372, + "step": 11343 + }, + { + "epoch": 0.69639952116394, + "grad_norm": 1.002384260184485, + "learning_rate": 4.456703235928417e-06, + "loss": 0.8072, + "step": 11344 + }, + { + "epoch": 0.6964609104024064, + "grad_norm": 0.8523999559249983, + "learning_rate": 4.455048447585286e-06, + "loss": 0.7903, + "step": 11345 + }, + { + "epoch": 0.696522299640873, + "grad_norm": 0.9302664505928675, + "learning_rate": 4.453393878463748e-06, + "loss": 0.7533, + "step": 11346 + }, + { + "epoch": 0.6965836888793394, + "grad_norm": 0.8757443660718331, + "learning_rate": 4.4517395286292145e-06, + "loss": 0.7299, + "step": 11347 + }, + { + "epoch": 0.696645078117806, + "grad_norm": 1.0590621961897686, + "learning_rate": 4.450085398147091e-06, + "loss": 0.7485, + "step": 11348 + }, + { + "epoch": 0.6967064673562724, + "grad_norm": 1.011507160248187, + "learning_rate": 4.448431487082776e-06, + "loss": 0.8134, + "step": 11349 + }, + { + "epoch": 0.6967678565947389, + "grad_norm": 1.0040479433296612, + "learning_rate": 4.446777795501652e-06, + "loss": 0.7363, + "step": 11350 + }, + { + "epoch": 0.6968292458332055, + "grad_norm": 0.902053250363779, + "learning_rate": 4.445124323469106e-06, + "loss": 0.778, + "step": 11351 + }, + { + "epoch": 0.6968906350716719, + "grad_norm": 0.8161828325048108, + "learning_rate": 4.443471071050509e-06, + "loss": 0.7786, + "step": 11352 + }, + { + "epoch": 0.6969520243101385, + "grad_norm": 1.0036651602204427, + "learning_rate": 4.441818038311215e-06, + "loss": 0.7835, + "step": 11353 + }, + { + "epoch": 0.6970134135486049, + "grad_norm": 0.9341806648629621, + "learning_rate": 4.4401652253165775e-06, + "loss": 0.7469, + "step": 11354 + }, + { + "epoch": 0.6970748027870715, + "grad_norm": 0.8552043737686128, + "learning_rate": 4.438512632131948e-06, + "loss": 0.7402, + "step": 11355 + }, + { + "epoch": 0.6971361920255379, + "grad_norm": 1.0496094484208067, + "learning_rate": 4.43686025882266e-06, + "loss": 0.833, + "step": 11356 + }, + { + "epoch": 0.6971975812640044, + "grad_norm": 1.0282376266109081, + "learning_rate": 4.43520810545404e-06, + "loss": 0.8601, + "step": 11357 + }, + { + "epoch": 0.6972589705024709, + "grad_norm": 1.0293002059249567, + "learning_rate": 4.433556172091404e-06, + "loss": 0.7835, + "step": 11358 + }, + { + "epoch": 0.6973203597409374, + "grad_norm": 0.9163207277545556, + "learning_rate": 4.4319044588000656e-06, + "loss": 0.7497, + "step": 11359 + }, + { + "epoch": 0.6973817489794039, + "grad_norm": 0.961621372470881, + "learning_rate": 4.430252965645325e-06, + "loss": 0.7836, + "step": 11360 + }, + { + "epoch": 0.6974431382178704, + "grad_norm": 0.9606147756982679, + "learning_rate": 4.428601692692469e-06, + "loss": 0.7763, + "step": 11361 + }, + { + "epoch": 0.697504527456337, + "grad_norm": 0.9923253485071457, + "learning_rate": 4.426950640006793e-06, + "loss": 0.7824, + "step": 11362 + }, + { + "epoch": 0.6975659166948034, + "grad_norm": 0.939536437759865, + "learning_rate": 4.425299807653563e-06, + "loss": 0.7665, + "step": 11363 + }, + { + "epoch": 0.6976273059332699, + "grad_norm": 0.8749176900655111, + "learning_rate": 4.423649195698042e-06, + "loss": 0.6947, + "step": 11364 + }, + { + "epoch": 0.6976886951717364, + "grad_norm": 0.9117282358582504, + "learning_rate": 4.421998804205497e-06, + "loss": 0.7594, + "step": 11365 + }, + { + "epoch": 0.6977500844102029, + "grad_norm": 0.8835511746666107, + "learning_rate": 4.420348633241172e-06, + "loss": 0.7862, + "step": 11366 + }, + { + "epoch": 0.6978114736486694, + "grad_norm": 0.9388825728700049, + "learning_rate": 4.418698682870312e-06, + "loss": 0.7779, + "step": 11367 + }, + { + "epoch": 0.6978728628871359, + "grad_norm": 0.9594068773316035, + "learning_rate": 4.417048953158135e-06, + "loss": 0.8052, + "step": 11368 + }, + { + "epoch": 0.6979342521256023, + "grad_norm": 1.0173865994296538, + "learning_rate": 4.415399444169878e-06, + "loss": 0.7631, + "step": 11369 + }, + { + "epoch": 0.6979956413640689, + "grad_norm": 0.8904246425220966, + "learning_rate": 4.413750155970749e-06, + "loss": 0.7304, + "step": 11370 + }, + { + "epoch": 0.6980570306025353, + "grad_norm": 0.9711299829075085, + "learning_rate": 4.412101088625953e-06, + "loss": 0.8036, + "step": 11371 + }, + { + "epoch": 0.6981184198410019, + "grad_norm": 0.5753034483715129, + "learning_rate": 4.410452242200688e-06, + "loss": 0.6789, + "step": 11372 + }, + { + "epoch": 0.6981798090794684, + "grad_norm": 0.9556269031629788, + "learning_rate": 4.408803616760141e-06, + "loss": 0.7664, + "step": 11373 + }, + { + "epoch": 0.6982411983179349, + "grad_norm": 0.7929529701851588, + "learning_rate": 4.407155212369491e-06, + "loss": 0.7782, + "step": 11374 + }, + { + "epoch": 0.6983025875564014, + "grad_norm": 0.8379916933352664, + "learning_rate": 4.4055070290939025e-06, + "loss": 0.7606, + "step": 11375 + }, + { + "epoch": 0.6983639767948678, + "grad_norm": 0.9348807422124873, + "learning_rate": 4.403859066998548e-06, + "loss": 0.7424, + "step": 11376 + }, + { + "epoch": 0.6984253660333344, + "grad_norm": 0.9334346166374999, + "learning_rate": 4.402211326148579e-06, + "loss": 0.8207, + "step": 11377 + }, + { + "epoch": 0.6984867552718008, + "grad_norm": 0.8936992394349477, + "learning_rate": 4.40056380660913e-06, + "loss": 0.7347, + "step": 11378 + }, + { + "epoch": 0.6985481445102674, + "grad_norm": 0.9370935126723537, + "learning_rate": 4.398916508445339e-06, + "loss": 0.7218, + "step": 11379 + }, + { + "epoch": 0.6986095337487338, + "grad_norm": 0.9155425861573769, + "learning_rate": 4.397269431722339e-06, + "loss": 0.7132, + "step": 11380 + }, + { + "epoch": 0.6986709229872003, + "grad_norm": 0.825723559613721, + "learning_rate": 4.395622576505244e-06, + "loss": 0.6903, + "step": 11381 + }, + { + "epoch": 0.6987323122256668, + "grad_norm": 0.9956969146100026, + "learning_rate": 4.393975942859162e-06, + "loss": 0.8129, + "step": 11382 + }, + { + "epoch": 0.6987937014641333, + "grad_norm": 1.0654552506115365, + "learning_rate": 4.392329530849194e-06, + "loss": 0.7872, + "step": 11383 + }, + { + "epoch": 0.6988550907025999, + "grad_norm": 0.9161060580567191, + "learning_rate": 4.390683340540433e-06, + "loss": 0.7589, + "step": 11384 + }, + { + "epoch": 0.6989164799410663, + "grad_norm": 1.001575246410199, + "learning_rate": 4.389037371997958e-06, + "loss": 0.7508, + "step": 11385 + }, + { + "epoch": 0.6989778691795329, + "grad_norm": 0.9944116558966286, + "learning_rate": 4.387391625286848e-06, + "loss": 0.7889, + "step": 11386 + }, + { + "epoch": 0.6990392584179993, + "grad_norm": 0.9831695611873383, + "learning_rate": 4.385746100472163e-06, + "loss": 0.7516, + "step": 11387 + }, + { + "epoch": 0.6991006476564658, + "grad_norm": 0.932991673465778, + "learning_rate": 4.384100797618963e-06, + "loss": 0.7314, + "step": 11388 + }, + { + "epoch": 0.6991620368949323, + "grad_norm": 0.9338055497082955, + "learning_rate": 4.382455716792291e-06, + "loss": 0.7471, + "step": 11389 + }, + { + "epoch": 0.6992234261333988, + "grad_norm": 0.9992464387065376, + "learning_rate": 4.3808108580571915e-06, + "loss": 0.8053, + "step": 11390 + }, + { + "epoch": 0.6992848153718653, + "grad_norm": 1.0178833931223867, + "learning_rate": 4.379166221478697e-06, + "loss": 0.7557, + "step": 11391 + }, + { + "epoch": 0.6993462046103318, + "grad_norm": 1.0615869534998106, + "learning_rate": 4.37752180712182e-06, + "loss": 0.7566, + "step": 11392 + }, + { + "epoch": 0.6994075938487984, + "grad_norm": 0.9382237399480764, + "learning_rate": 4.375877615051575e-06, + "loss": 0.7875, + "step": 11393 + }, + { + "epoch": 0.6994689830872648, + "grad_norm": 0.900604218695959, + "learning_rate": 4.374233645332969e-06, + "loss": 0.7233, + "step": 11394 + }, + { + "epoch": 0.6995303723257313, + "grad_norm": 1.0247633217396976, + "learning_rate": 4.372589898030998e-06, + "loss": 0.7651, + "step": 11395 + }, + { + "epoch": 0.6995917615641978, + "grad_norm": 0.955491292522649, + "learning_rate": 4.370946373210644e-06, + "loss": 0.789, + "step": 11396 + }, + { + "epoch": 0.6996531508026643, + "grad_norm": 0.9360688376976242, + "learning_rate": 4.369303070936886e-06, + "loss": 0.7079, + "step": 11397 + }, + { + "epoch": 0.6997145400411308, + "grad_norm": 1.0070343170504281, + "learning_rate": 4.367659991274694e-06, + "loss": 0.7812, + "step": 11398 + }, + { + "epoch": 0.6997759292795973, + "grad_norm": 1.0024109594076576, + "learning_rate": 4.366017134289027e-06, + "loss": 0.788, + "step": 11399 + }, + { + "epoch": 0.6998373185180637, + "grad_norm": 0.910673611173405, + "learning_rate": 4.36437450004483e-06, + "loss": 0.8104, + "step": 11400 + }, + { + "epoch": 0.6998987077565303, + "grad_norm": 1.0350233433033347, + "learning_rate": 4.362732088607059e-06, + "loss": 0.802, + "step": 11401 + }, + { + "epoch": 0.6999600969949967, + "grad_norm": 0.8383734866459748, + "learning_rate": 4.3610899000406346e-06, + "loss": 0.7342, + "step": 11402 + }, + { + "epoch": 0.7000214862334633, + "grad_norm": 0.9218142998676824, + "learning_rate": 4.359447934410481e-06, + "loss": 0.7564, + "step": 11403 + }, + { + "epoch": 0.7000828754719298, + "grad_norm": 0.979006375018057, + "learning_rate": 4.3578061917815236e-06, + "loss": 0.7497, + "step": 11404 + }, + { + "epoch": 0.7001442647103963, + "grad_norm": 0.9258275688977534, + "learning_rate": 4.356164672218664e-06, + "loss": 0.767, + "step": 11405 + }, + { + "epoch": 0.7002056539488628, + "grad_norm": 0.9458560085803329, + "learning_rate": 4.354523375786802e-06, + "loss": 0.7642, + "step": 11406 + }, + { + "epoch": 0.7002670431873292, + "grad_norm": 0.9817175757322147, + "learning_rate": 4.352882302550819e-06, + "loss": 0.7558, + "step": 11407 + }, + { + "epoch": 0.7003284324257958, + "grad_norm": 0.9318533109614433, + "learning_rate": 4.3512414525756054e-06, + "loss": 0.7447, + "step": 11408 + }, + { + "epoch": 0.7003898216642622, + "grad_norm": 0.993256744427205, + "learning_rate": 4.349600825926028e-06, + "loss": 0.7744, + "step": 11409 + }, + { + "epoch": 0.7004512109027288, + "grad_norm": 0.9153956961565531, + "learning_rate": 4.3479604226669515e-06, + "loss": 0.7532, + "step": 11410 + }, + { + "epoch": 0.7005126001411952, + "grad_norm": 0.980091315879348, + "learning_rate": 4.346320242863228e-06, + "loss": 0.8212, + "step": 11411 + }, + { + "epoch": 0.7005739893796618, + "grad_norm": 1.0449896197931177, + "learning_rate": 4.344680286579703e-06, + "loss": 0.7475, + "step": 11412 + }, + { + "epoch": 0.7006353786181282, + "grad_norm": 0.9834682032693521, + "learning_rate": 4.343040553881214e-06, + "loss": 0.7755, + "step": 11413 + }, + { + "epoch": 0.7006967678565947, + "grad_norm": 0.8780321160372061, + "learning_rate": 4.341401044832583e-06, + "loss": 0.7357, + "step": 11414 + }, + { + "epoch": 0.7007581570950613, + "grad_norm": 0.9525277961579335, + "learning_rate": 4.3397617594986375e-06, + "loss": 0.7818, + "step": 11415 + }, + { + "epoch": 0.7008195463335277, + "grad_norm": 0.913452760758621, + "learning_rate": 4.338122697944185e-06, + "loss": 0.7414, + "step": 11416 + }, + { + "epoch": 0.7008809355719943, + "grad_norm": 0.9837267053467443, + "learning_rate": 4.336483860234022e-06, + "loss": 0.7467, + "step": 11417 + }, + { + "epoch": 0.7009423248104607, + "grad_norm": 0.9101427028557108, + "learning_rate": 4.3348452464329384e-06, + "loss": 0.7838, + "step": 11418 + }, + { + "epoch": 0.7010037140489273, + "grad_norm": 0.975118868875215, + "learning_rate": 4.333206856605725e-06, + "loss": 0.7811, + "step": 11419 + }, + { + "epoch": 0.7010651032873937, + "grad_norm": 0.904456875261362, + "learning_rate": 4.331568690817153e-06, + "loss": 0.7873, + "step": 11420 + }, + { + "epoch": 0.7011264925258602, + "grad_norm": 0.9204969071762178, + "learning_rate": 4.329930749131987e-06, + "loss": 0.7583, + "step": 11421 + }, + { + "epoch": 0.7011878817643267, + "grad_norm": 0.8402955243823221, + "learning_rate": 4.328293031614984e-06, + "loss": 0.7282, + "step": 11422 + }, + { + "epoch": 0.7012492710027932, + "grad_norm": 0.9788199252197608, + "learning_rate": 4.3266555383308924e-06, + "loss": 0.8247, + "step": 11423 + }, + { + "epoch": 0.7013106602412597, + "grad_norm": 0.8788168824648247, + "learning_rate": 4.325018269344451e-06, + "loss": 0.701, + "step": 11424 + }, + { + "epoch": 0.7013720494797262, + "grad_norm": 0.9432182415340217, + "learning_rate": 4.323381224720384e-06, + "loss": 0.7946, + "step": 11425 + }, + { + "epoch": 0.7014334387181927, + "grad_norm": 0.9093322990838538, + "learning_rate": 4.321744404523427e-06, + "loss": 0.747, + "step": 11426 + }, + { + "epoch": 0.7014948279566592, + "grad_norm": 0.9815108029309138, + "learning_rate": 4.3201078088182795e-06, + "loss": 0.7643, + "step": 11427 + }, + { + "epoch": 0.7015562171951257, + "grad_norm": 0.8975636457253133, + "learning_rate": 4.318471437669644e-06, + "loss": 0.7799, + "step": 11428 + }, + { + "epoch": 0.7016176064335922, + "grad_norm": 0.9623023746264527, + "learning_rate": 4.316835291142223e-06, + "loss": 0.771, + "step": 11429 + }, + { + "epoch": 0.7016789956720587, + "grad_norm": 1.0072111586858574, + "learning_rate": 4.315199369300699e-06, + "loss": 0.7487, + "step": 11430 + }, + { + "epoch": 0.7017403849105252, + "grad_norm": 0.949356649636456, + "learning_rate": 4.313563672209753e-06, + "loss": 0.7858, + "step": 11431 + }, + { + "epoch": 0.7018017741489917, + "grad_norm": 0.9635842169021791, + "learning_rate": 4.311928199934039e-06, + "loss": 0.8144, + "step": 11432 + }, + { + "epoch": 0.7018631633874581, + "grad_norm": 0.9875076531822748, + "learning_rate": 4.310292952538231e-06, + "loss": 0.7712, + "step": 11433 + }, + { + "epoch": 0.7019245526259247, + "grad_norm": 0.9277155408054129, + "learning_rate": 4.308657930086971e-06, + "loss": 0.8126, + "step": 11434 + }, + { + "epoch": 0.7019859418643912, + "grad_norm": 0.8222398529057408, + "learning_rate": 4.307023132644904e-06, + "loss": 0.7416, + "step": 11435 + }, + { + "epoch": 0.7020473311028577, + "grad_norm": 0.9542288934067158, + "learning_rate": 4.305388560276661e-06, + "loss": 0.7629, + "step": 11436 + }, + { + "epoch": 0.7021087203413242, + "grad_norm": 1.1000716356529656, + "learning_rate": 4.303754213046865e-06, + "loss": 0.783, + "step": 11437 + }, + { + "epoch": 0.7021701095797906, + "grad_norm": 0.9916550464352026, + "learning_rate": 4.302120091020129e-06, + "loss": 0.7847, + "step": 11438 + }, + { + "epoch": 0.7022314988182572, + "grad_norm": 0.9453559066933902, + "learning_rate": 4.3004861942610575e-06, + "loss": 0.7524, + "step": 11439 + }, + { + "epoch": 0.7022928880567236, + "grad_norm": 0.9693220491523615, + "learning_rate": 4.298852522834254e-06, + "loss": 0.7746, + "step": 11440 + }, + { + "epoch": 0.7023542772951902, + "grad_norm": 0.9496092191670008, + "learning_rate": 4.2972190768043055e-06, + "loss": 0.7633, + "step": 11441 + }, + { + "epoch": 0.7024156665336566, + "grad_norm": 0.9810309090549703, + "learning_rate": 4.29558585623578e-06, + "loss": 0.7656, + "step": 11442 + }, + { + "epoch": 0.7024770557721232, + "grad_norm": 0.9164181798020258, + "learning_rate": 4.293952861193259e-06, + "loss": 0.8, + "step": 11443 + }, + { + "epoch": 0.7025384450105896, + "grad_norm": 0.9679222923928353, + "learning_rate": 4.2923200917413e-06, + "loss": 0.7658, + "step": 11444 + }, + { + "epoch": 0.7025998342490561, + "grad_norm": 0.9662683099431483, + "learning_rate": 4.290687547944453e-06, + "loss": 0.7822, + "step": 11445 + }, + { + "epoch": 0.7026612234875227, + "grad_norm": 0.9422422569925802, + "learning_rate": 4.289055229867264e-06, + "loss": 0.7605, + "step": 11446 + }, + { + "epoch": 0.7027226127259891, + "grad_norm": 0.8026244190286854, + "learning_rate": 4.287423137574266e-06, + "loss": 0.7654, + "step": 11447 + }, + { + "epoch": 0.7027840019644557, + "grad_norm": 0.9018131206491847, + "learning_rate": 4.285791271129984e-06, + "loss": 0.8067, + "step": 11448 + }, + { + "epoch": 0.7028453912029221, + "grad_norm": 0.958166797994078, + "learning_rate": 4.284159630598935e-06, + "loss": 0.7976, + "step": 11449 + }, + { + "epoch": 0.7029067804413887, + "grad_norm": 0.8659484274827056, + "learning_rate": 4.282528216045623e-06, + "loss": 0.7443, + "step": 11450 + }, + { + "epoch": 0.7029681696798551, + "grad_norm": 0.9903337297098812, + "learning_rate": 4.280897027534556e-06, + "loss": 0.7486, + "step": 11451 + }, + { + "epoch": 0.7030295589183216, + "grad_norm": 0.9435566147378367, + "learning_rate": 4.279266065130214e-06, + "loss": 0.7466, + "step": 11452 + }, + { + "epoch": 0.7030909481567881, + "grad_norm": 0.8695428674707497, + "learning_rate": 4.277635328897079e-06, + "loss": 0.6923, + "step": 11453 + }, + { + "epoch": 0.7031523373952546, + "grad_norm": 0.9360038573237031, + "learning_rate": 4.276004818899626e-06, + "loss": 0.7789, + "step": 11454 + }, + { + "epoch": 0.7032137266337211, + "grad_norm": 1.0320781690181322, + "learning_rate": 4.274374535202321e-06, + "loss": 0.7875, + "step": 11455 + }, + { + "epoch": 0.7032751158721876, + "grad_norm": 0.8563002777868336, + "learning_rate": 4.2727444778696115e-06, + "loss": 0.7442, + "step": 11456 + }, + { + "epoch": 0.7033365051106542, + "grad_norm": 0.9046730095626921, + "learning_rate": 4.271114646965939e-06, + "loss": 0.7372, + "step": 11457 + }, + { + "epoch": 0.7033978943491206, + "grad_norm": 0.903378236670203, + "learning_rate": 4.269485042555749e-06, + "loss": 0.8111, + "step": 11458 + }, + { + "epoch": 0.7034592835875871, + "grad_norm": 0.8558803578343508, + "learning_rate": 4.267855664703464e-06, + "loss": 0.7702, + "step": 11459 + }, + { + "epoch": 0.7035206728260536, + "grad_norm": 1.056828677951525, + "learning_rate": 4.266226513473502e-06, + "loss": 0.7873, + "step": 11460 + }, + { + "epoch": 0.7035820620645201, + "grad_norm": 1.0115101179250818, + "learning_rate": 4.2645975889302725e-06, + "loss": 0.7726, + "step": 11461 + }, + { + "epoch": 0.7036434513029866, + "grad_norm": 0.8677630833856926, + "learning_rate": 4.262968891138176e-06, + "loss": 0.7903, + "step": 11462 + }, + { + "epoch": 0.7037048405414531, + "grad_norm": 0.9744127668158806, + "learning_rate": 4.261340420161603e-06, + "loss": 0.7605, + "step": 11463 + }, + { + "epoch": 0.7037662297799195, + "grad_norm": 0.9997676718645981, + "learning_rate": 4.25971217606493e-06, + "loss": 0.7837, + "step": 11464 + }, + { + "epoch": 0.7038276190183861, + "grad_norm": 1.0988640648214107, + "learning_rate": 4.258084158912545e-06, + "loss": 0.7953, + "step": 11465 + }, + { + "epoch": 0.7038890082568525, + "grad_norm": 0.8754626175989321, + "learning_rate": 4.2564563687688e-06, + "loss": 0.7967, + "step": 11466 + }, + { + "epoch": 0.7039503974953191, + "grad_norm": 0.9988713740917164, + "learning_rate": 4.254828805698049e-06, + "loss": 0.7504, + "step": 11467 + }, + { + "epoch": 0.7040117867337856, + "grad_norm": 0.8659186400722161, + "learning_rate": 4.253201469764646e-06, + "loss": 0.7571, + "step": 11468 + }, + { + "epoch": 0.704073175972252, + "grad_norm": 0.9763918315298822, + "learning_rate": 4.251574361032926e-06, + "loss": 0.8151, + "step": 11469 + }, + { + "epoch": 0.7041345652107186, + "grad_norm": 0.9361718667685612, + "learning_rate": 4.249947479567218e-06, + "loss": 0.7182, + "step": 11470 + }, + { + "epoch": 0.704195954449185, + "grad_norm": 0.9512847364451761, + "learning_rate": 4.2483208254318344e-06, + "loss": 0.7801, + "step": 11471 + }, + { + "epoch": 0.7042573436876516, + "grad_norm": 0.9063317022126748, + "learning_rate": 4.246694398691092e-06, + "loss": 0.7585, + "step": 11472 + }, + { + "epoch": 0.704318732926118, + "grad_norm": 0.9450804388951634, + "learning_rate": 4.245068199409292e-06, + "loss": 0.7624, + "step": 11473 + }, + { + "epoch": 0.7043801221645846, + "grad_norm": 0.9061162256586485, + "learning_rate": 4.243442227650727e-06, + "loss": 0.772, + "step": 11474 + }, + { + "epoch": 0.704441511403051, + "grad_norm": 1.0248851768542906, + "learning_rate": 4.241816483479677e-06, + "loss": 0.7497, + "step": 11475 + }, + { + "epoch": 0.7045029006415175, + "grad_norm": 0.9922679498179185, + "learning_rate": 4.2401909669604194e-06, + "loss": 0.7766, + "step": 11476 + }, + { + "epoch": 0.704564289879984, + "grad_norm": 0.9106124953019317, + "learning_rate": 4.238565678157218e-06, + "loss": 0.7522, + "step": 11477 + }, + { + "epoch": 0.7046256791184505, + "grad_norm": 0.8792758526851666, + "learning_rate": 4.236940617134326e-06, + "loss": 0.7598, + "step": 11478 + }, + { + "epoch": 0.7046870683569171, + "grad_norm": 1.1101670729201738, + "learning_rate": 4.235315783955999e-06, + "loss": 0.7621, + "step": 11479 + }, + { + "epoch": 0.7047484575953835, + "grad_norm": 0.9288751734401987, + "learning_rate": 4.233691178686473e-06, + "loss": 0.8311, + "step": 11480 + }, + { + "epoch": 0.7048098468338501, + "grad_norm": 0.9814226632830811, + "learning_rate": 4.232066801389969e-06, + "loss": 0.7204, + "step": 11481 + }, + { + "epoch": 0.7048712360723165, + "grad_norm": 0.966478908475791, + "learning_rate": 4.230442652130716e-06, + "loss": 0.7845, + "step": 11482 + }, + { + "epoch": 0.704932625310783, + "grad_norm": 1.0111043012579477, + "learning_rate": 4.228818730972923e-06, + "loss": 0.7947, + "step": 11483 + }, + { + "epoch": 0.7049940145492495, + "grad_norm": 0.912668185173449, + "learning_rate": 4.2271950379807935e-06, + "loss": 0.7691, + "step": 11484 + }, + { + "epoch": 0.705055403787716, + "grad_norm": 0.870232135128604, + "learning_rate": 4.2255715732185175e-06, + "loss": 0.7636, + "step": 11485 + }, + { + "epoch": 0.7051167930261825, + "grad_norm": 0.8758201094421554, + "learning_rate": 4.223948336750282e-06, + "loss": 0.778, + "step": 11486 + }, + { + "epoch": 0.705178182264649, + "grad_norm": 0.8878849163803155, + "learning_rate": 4.222325328640261e-06, + "loss": 0.7546, + "step": 11487 + }, + { + "epoch": 0.7052395715031156, + "grad_norm": 0.9022545245405426, + "learning_rate": 4.22070254895262e-06, + "loss": 0.7419, + "step": 11488 + }, + { + "epoch": 0.705300960741582, + "grad_norm": 0.9278872006377725, + "learning_rate": 4.219079997751515e-06, + "loss": 0.7801, + "step": 11489 + }, + { + "epoch": 0.7053623499800485, + "grad_norm": 1.0139401435921047, + "learning_rate": 4.2174576751011024e-06, + "loss": 0.7575, + "step": 11490 + }, + { + "epoch": 0.705423739218515, + "grad_norm": 1.051675638769908, + "learning_rate": 4.215835581065512e-06, + "loss": 0.7666, + "step": 11491 + }, + { + "epoch": 0.7054851284569815, + "grad_norm": 0.8805017269503262, + "learning_rate": 4.214213715708873e-06, + "loss": 0.7371, + "step": 11492 + }, + { + "epoch": 0.705546517695448, + "grad_norm": 0.8959053941707056, + "learning_rate": 4.212592079095315e-06, + "loss": 0.7286, + "step": 11493 + }, + { + "epoch": 0.7056079069339145, + "grad_norm": 0.8723817653403522, + "learning_rate": 4.210970671288943e-06, + "loss": 0.7892, + "step": 11494 + }, + { + "epoch": 0.7056692961723809, + "grad_norm": 0.9079299504152465, + "learning_rate": 4.209349492353868e-06, + "loss": 0.7683, + "step": 11495 + }, + { + "epoch": 0.7057306854108475, + "grad_norm": 0.8739643823615366, + "learning_rate": 4.207728542354171e-06, + "loss": 0.7439, + "step": 11496 + }, + { + "epoch": 0.7057920746493139, + "grad_norm": 1.01272764044804, + "learning_rate": 4.206107821353946e-06, + "loss": 0.7777, + "step": 11497 + }, + { + "epoch": 0.7058534638877805, + "grad_norm": 1.0499859045228213, + "learning_rate": 4.204487329417267e-06, + "loss": 0.7864, + "step": 11498 + }, + { + "epoch": 0.705914853126247, + "grad_norm": 0.938549853291334, + "learning_rate": 4.202867066608202e-06, + "loss": 0.733, + "step": 11499 + }, + { + "epoch": 0.7059762423647135, + "grad_norm": 1.018952255793696, + "learning_rate": 4.201247032990806e-06, + "loss": 0.7546, + "step": 11500 + }, + { + "epoch": 0.70603763160318, + "grad_norm": 0.9620273979857875, + "learning_rate": 4.199627228629128e-06, + "loss": 0.7146, + "step": 11501 + }, + { + "epoch": 0.7060990208416464, + "grad_norm": 0.9911869518029554, + "learning_rate": 4.19800765358721e-06, + "loss": 0.7512, + "step": 11502 + }, + { + "epoch": 0.706160410080113, + "grad_norm": 0.9020085615015558, + "learning_rate": 4.196388307929076e-06, + "loss": 0.7698, + "step": 11503 + }, + { + "epoch": 0.7062217993185794, + "grad_norm": 0.9034135098074659, + "learning_rate": 4.194769191718756e-06, + "loss": 0.7516, + "step": 11504 + }, + { + "epoch": 0.706283188557046, + "grad_norm": 0.9943416548378086, + "learning_rate": 4.1931503050202614e-06, + "loss": 0.7539, + "step": 11505 + }, + { + "epoch": 0.7063445777955124, + "grad_norm": 1.0313526774853872, + "learning_rate": 4.191531647897586e-06, + "loss": 0.8364, + "step": 11506 + }, + { + "epoch": 0.706405967033979, + "grad_norm": 0.9253495325757939, + "learning_rate": 4.189913220414734e-06, + "loss": 0.7415, + "step": 11507 + }, + { + "epoch": 0.7064673562724454, + "grad_norm": 0.9179705313058601, + "learning_rate": 4.1882950226356865e-06, + "loss": 0.8042, + "step": 11508 + }, + { + "epoch": 0.7065287455109119, + "grad_norm": 0.9804497190141165, + "learning_rate": 4.186677054624421e-06, + "loss": 0.7514, + "step": 11509 + }, + { + "epoch": 0.7065901347493785, + "grad_norm": 0.8847163209960123, + "learning_rate": 4.185059316444902e-06, + "loss": 0.7152, + "step": 11510 + }, + { + "epoch": 0.7066515239878449, + "grad_norm": 1.051616638147833, + "learning_rate": 4.183441808161088e-06, + "loss": 0.7855, + "step": 11511 + }, + { + "epoch": 0.7067129132263115, + "grad_norm": 0.9643493198298484, + "learning_rate": 4.181824529836931e-06, + "loss": 0.7388, + "step": 11512 + }, + { + "epoch": 0.7067743024647779, + "grad_norm": 0.9675102244102571, + "learning_rate": 4.1802074815363656e-06, + "loss": 0.8021, + "step": 11513 + }, + { + "epoch": 0.7068356917032445, + "grad_norm": 0.9407981639038868, + "learning_rate": 4.178590663323323e-06, + "loss": 0.7249, + "step": 11514 + }, + { + "epoch": 0.7068970809417109, + "grad_norm": 1.0236475613042901, + "learning_rate": 4.176974075261734e-06, + "loss": 0.7953, + "step": 11515 + }, + { + "epoch": 0.7069584701801774, + "grad_norm": 1.053560185062511, + "learning_rate": 4.175357717415499e-06, + "loss": 0.7798, + "step": 11516 + }, + { + "epoch": 0.7070198594186439, + "grad_norm": 0.988255358245965, + "learning_rate": 4.173741589848522e-06, + "loss": 0.8043, + "step": 11517 + }, + { + "epoch": 0.7070812486571104, + "grad_norm": 0.866285326767108, + "learning_rate": 4.1721256926247044e-06, + "loss": 0.7743, + "step": 11518 + }, + { + "epoch": 0.7071426378955769, + "grad_norm": 0.8435220022574721, + "learning_rate": 4.170510025807933e-06, + "loss": 0.7856, + "step": 11519 + }, + { + "epoch": 0.7072040271340434, + "grad_norm": 0.9401211613160589, + "learning_rate": 4.168894589462073e-06, + "loss": 0.8, + "step": 11520 + }, + { + "epoch": 0.70726541637251, + "grad_norm": 0.9562820087966827, + "learning_rate": 4.167279383650995e-06, + "loss": 0.7274, + "step": 11521 + }, + { + "epoch": 0.7073268056109764, + "grad_norm": 0.9936286048147174, + "learning_rate": 4.165664408438561e-06, + "loss": 0.7956, + "step": 11522 + }, + { + "epoch": 0.7073881948494429, + "grad_norm": 0.8221275806321706, + "learning_rate": 4.164049663888618e-06, + "loss": 0.7156, + "step": 11523 + }, + { + "epoch": 0.7074495840879094, + "grad_norm": 1.0872364813018354, + "learning_rate": 4.162435150065004e-06, + "loss": 0.7581, + "step": 11524 + }, + { + "epoch": 0.7075109733263759, + "grad_norm": 0.9376502332921339, + "learning_rate": 4.16082086703155e-06, + "loss": 0.7863, + "step": 11525 + }, + { + "epoch": 0.7075723625648423, + "grad_norm": 1.015168920330118, + "learning_rate": 4.159206814852077e-06, + "loss": 0.7599, + "step": 11526 + }, + { + "epoch": 0.7076337518033089, + "grad_norm": 0.9005574298855836, + "learning_rate": 4.157592993590398e-06, + "loss": 0.7869, + "step": 11527 + }, + { + "epoch": 0.7076951410417753, + "grad_norm": 1.004504159519476, + "learning_rate": 4.155979403310312e-06, + "loss": 0.7864, + "step": 11528 + }, + { + "epoch": 0.7077565302802419, + "grad_norm": 0.946852957438874, + "learning_rate": 4.154366044075623e-06, + "loss": 0.7651, + "step": 11529 + }, + { + "epoch": 0.7078179195187083, + "grad_norm": 0.9564625467384034, + "learning_rate": 4.152752915950105e-06, + "loss": 0.768, + "step": 11530 + }, + { + "epoch": 0.7078793087571749, + "grad_norm": 1.037476135555618, + "learning_rate": 4.151140018997534e-06, + "loss": 0.7625, + "step": 11531 + }, + { + "epoch": 0.7079406979956414, + "grad_norm": 1.0069337024454539, + "learning_rate": 4.149527353281684e-06, + "loss": 0.815, + "step": 11532 + }, + { + "epoch": 0.7080020872341078, + "grad_norm": 0.9483678004189774, + "learning_rate": 4.147914918866308e-06, + "loss": 0.7375, + "step": 11533 + }, + { + "epoch": 0.7080634764725744, + "grad_norm": 0.9794686196186895, + "learning_rate": 4.1463027158151585e-06, + "loss": 0.7639, + "step": 11534 + }, + { + "epoch": 0.7081248657110408, + "grad_norm": 0.9374341652121142, + "learning_rate": 4.144690744191961e-06, + "loss": 0.7663, + "step": 11535 + }, + { + "epoch": 0.7081862549495074, + "grad_norm": 0.9912460448034478, + "learning_rate": 4.143079004060461e-06, + "loss": 0.7613, + "step": 11536 + }, + { + "epoch": 0.7082476441879738, + "grad_norm": 0.9159123567277054, + "learning_rate": 4.141467495484371e-06, + "loss": 0.7521, + "step": 11537 + }, + { + "epoch": 0.7083090334264404, + "grad_norm": 1.044839112493545, + "learning_rate": 4.139856218527406e-06, + "loss": 0.8136, + "step": 11538 + }, + { + "epoch": 0.7083704226649068, + "grad_norm": 0.850834099792928, + "learning_rate": 4.138245173253267e-06, + "loss": 0.8055, + "step": 11539 + }, + { + "epoch": 0.7084318119033733, + "grad_norm": 0.9775136806863388, + "learning_rate": 4.1366343597256465e-06, + "loss": 0.7466, + "step": 11540 + }, + { + "epoch": 0.7084932011418399, + "grad_norm": 0.8439406341366799, + "learning_rate": 4.135023778008229e-06, + "loss": 0.7805, + "step": 11541 + }, + { + "epoch": 0.7085545903803063, + "grad_norm": 0.9479544421873534, + "learning_rate": 4.133413428164688e-06, + "loss": 0.7264, + "step": 11542 + }, + { + "epoch": 0.7086159796187729, + "grad_norm": 0.9581026267374946, + "learning_rate": 4.131803310258692e-06, + "loss": 0.7864, + "step": 11543 + }, + { + "epoch": 0.7086773688572393, + "grad_norm": 0.7970697731028047, + "learning_rate": 4.130193424353901e-06, + "loss": 0.7144, + "step": 11544 + }, + { + "epoch": 0.7087387580957059, + "grad_norm": 0.9899356987178651, + "learning_rate": 4.128583770513951e-06, + "loss": 0.7626, + "step": 11545 + }, + { + "epoch": 0.7088001473341723, + "grad_norm": 0.8184435431489842, + "learning_rate": 4.12697434880249e-06, + "loss": 0.7504, + "step": 11546 + }, + { + "epoch": 0.7088615365726388, + "grad_norm": 0.9046884172643921, + "learning_rate": 4.125365159283144e-06, + "loss": 0.7657, + "step": 11547 + }, + { + "epoch": 0.7089229258111053, + "grad_norm": 0.8844262485923746, + "learning_rate": 4.123756202019535e-06, + "loss": 0.7661, + "step": 11548 + }, + { + "epoch": 0.7089843150495718, + "grad_norm": 0.973713936944147, + "learning_rate": 4.12214747707527e-06, + "loss": 0.7738, + "step": 11549 + }, + { + "epoch": 0.7090457042880383, + "grad_norm": 0.9188325081479628, + "learning_rate": 4.120538984513952e-06, + "loss": 0.7657, + "step": 11550 + }, + { + "epoch": 0.7091070935265048, + "grad_norm": 0.9456963030087302, + "learning_rate": 4.118930724399174e-06, + "loss": 0.7647, + "step": 11551 + }, + { + "epoch": 0.7091684827649714, + "grad_norm": 0.9829241629505341, + "learning_rate": 4.117322696794519e-06, + "loss": 0.7919, + "step": 11552 + }, + { + "epoch": 0.7092298720034378, + "grad_norm": 0.8674086797459107, + "learning_rate": 4.115714901763557e-06, + "loss": 0.7531, + "step": 11553 + }, + { + "epoch": 0.7092912612419043, + "grad_norm": 0.8888938102218492, + "learning_rate": 4.114107339369863e-06, + "loss": 0.7254, + "step": 11554 + }, + { + "epoch": 0.7093526504803708, + "grad_norm": 0.9904425185943967, + "learning_rate": 4.112500009676982e-06, + "loss": 0.8437, + "step": 11555 + }, + { + "epoch": 0.7094140397188373, + "grad_norm": 0.9649547790259051, + "learning_rate": 4.110892912748461e-06, + "loss": 0.7859, + "step": 11556 + }, + { + "epoch": 0.7094754289573038, + "grad_norm": 0.9169873931524647, + "learning_rate": 4.109286048647844e-06, + "loss": 0.7278, + "step": 11557 + }, + { + "epoch": 0.7095368181957703, + "grad_norm": 0.8372834748889689, + "learning_rate": 4.1076794174386545e-06, + "loss": 0.7399, + "step": 11558 + }, + { + "epoch": 0.7095982074342367, + "grad_norm": 0.8718195370677679, + "learning_rate": 4.106073019184415e-06, + "loss": 0.7235, + "step": 11559 + }, + { + "epoch": 0.7096595966727033, + "grad_norm": 0.9578316237243077, + "learning_rate": 4.104466853948626e-06, + "loss": 0.7731, + "step": 11560 + }, + { + "epoch": 0.7097209859111697, + "grad_norm": 0.9803586591971898, + "learning_rate": 4.102860921794798e-06, + "loss": 0.8041, + "step": 11561 + }, + { + "epoch": 0.7097823751496363, + "grad_norm": 1.022968103310319, + "learning_rate": 4.101255222786418e-06, + "loss": 0.82, + "step": 11562 + }, + { + "epoch": 0.7098437643881028, + "grad_norm": 0.9013000684020859, + "learning_rate": 4.099649756986966e-06, + "loss": 0.7101, + "step": 11563 + }, + { + "epoch": 0.7099051536265693, + "grad_norm": 0.9841147469639786, + "learning_rate": 4.0980445244599174e-06, + "loss": 0.7993, + "step": 11564 + }, + { + "epoch": 0.7099665428650358, + "grad_norm": 0.9634434397879289, + "learning_rate": 4.096439525268735e-06, + "loss": 0.792, + "step": 11565 + }, + { + "epoch": 0.7100279321035022, + "grad_norm": 0.9323827164497621, + "learning_rate": 4.0948347594768725e-06, + "loss": 0.7977, + "step": 11566 + }, + { + "epoch": 0.7100893213419688, + "grad_norm": 0.85249279449012, + "learning_rate": 4.0932302271477705e-06, + "loss": 0.7683, + "step": 11567 + }, + { + "epoch": 0.7101507105804352, + "grad_norm": 0.8911549880395292, + "learning_rate": 4.091625928344874e-06, + "loss": 0.742, + "step": 11568 + }, + { + "epoch": 0.7102120998189018, + "grad_norm": 0.9571263786827542, + "learning_rate": 4.090021863131608e-06, + "loss": 0.7372, + "step": 11569 + }, + { + "epoch": 0.7102734890573682, + "grad_norm": 0.9244636708502803, + "learning_rate": 4.088418031571378e-06, + "loss": 0.7154, + "step": 11570 + }, + { + "epoch": 0.7103348782958347, + "grad_norm": 1.0127306651053325, + "learning_rate": 4.086814433727606e-06, + "loss": 0.7948, + "step": 11571 + }, + { + "epoch": 0.7103962675343012, + "grad_norm": 0.8906908989807537, + "learning_rate": 4.085211069663685e-06, + "loss": 0.795, + "step": 11572 + }, + { + "epoch": 0.7104576567727677, + "grad_norm": 0.8601577208474949, + "learning_rate": 4.083607939443004e-06, + "loss": 0.7657, + "step": 11573 + }, + { + "epoch": 0.7105190460112343, + "grad_norm": 0.9231584155884464, + "learning_rate": 4.0820050431289445e-06, + "loss": 0.7377, + "step": 11574 + }, + { + "epoch": 0.7105804352497007, + "grad_norm": 0.9725640221995244, + "learning_rate": 4.080402380784878e-06, + "loss": 0.8179, + "step": 11575 + }, + { + "epoch": 0.7106418244881673, + "grad_norm": 0.9337341895771009, + "learning_rate": 4.078799952474165e-06, + "loss": 0.7708, + "step": 11576 + }, + { + "epoch": 0.7107032137266337, + "grad_norm": 0.9414664533041877, + "learning_rate": 4.07719775826016e-06, + "loss": 0.7636, + "step": 11577 + }, + { + "epoch": 0.7107646029651002, + "grad_norm": 0.8436319985196572, + "learning_rate": 4.0755957982062e-06, + "loss": 0.7227, + "step": 11578 + }, + { + "epoch": 0.7108259922035667, + "grad_norm": 0.9579007528300981, + "learning_rate": 4.073994072375631e-06, + "loss": 0.7281, + "step": 11579 + }, + { + "epoch": 0.7108873814420332, + "grad_norm": 0.9958526662532383, + "learning_rate": 4.0723925808317685e-06, + "loss": 0.7459, + "step": 11580 + }, + { + "epoch": 0.7109487706804997, + "grad_norm": 0.9835982768334209, + "learning_rate": 4.070791323637926e-06, + "loss": 0.7467, + "step": 11581 + }, + { + "epoch": 0.7110101599189662, + "grad_norm": 0.769078120714667, + "learning_rate": 4.0691903008574175e-06, + "loss": 0.7336, + "step": 11582 + }, + { + "epoch": 0.7110715491574326, + "grad_norm": 0.9084601002777213, + "learning_rate": 4.06758951255354e-06, + "loss": 0.7868, + "step": 11583 + }, + { + "epoch": 0.7111329383958992, + "grad_norm": 1.0495191386613065, + "learning_rate": 4.065988958789572e-06, + "loss": 0.7737, + "step": 11584 + }, + { + "epoch": 0.7111943276343657, + "grad_norm": 0.8135995274350049, + "learning_rate": 4.0643886396288e-06, + "loss": 0.8099, + "step": 11585 + }, + { + "epoch": 0.7112557168728322, + "grad_norm": 0.9299280569582025, + "learning_rate": 4.0627885551344914e-06, + "loss": 0.7439, + "step": 11586 + }, + { + "epoch": 0.7113171061112987, + "grad_norm": 0.9508639533539767, + "learning_rate": 4.061188705369906e-06, + "loss": 0.749, + "step": 11587 + }, + { + "epoch": 0.7113784953497652, + "grad_norm": 1.0009469189706686, + "learning_rate": 4.059589090398294e-06, + "loss": 0.7886, + "step": 11588 + }, + { + "epoch": 0.7114398845882317, + "grad_norm": 0.9679831940514964, + "learning_rate": 4.057989710282897e-06, + "loss": 0.7186, + "step": 11589 + }, + { + "epoch": 0.7115012738266981, + "grad_norm": 0.9171042651293814, + "learning_rate": 4.0563905650869465e-06, + "loss": 0.729, + "step": 11590 + }, + { + "epoch": 0.7115626630651647, + "grad_norm": 0.9001476087029545, + "learning_rate": 4.0547916548736655e-06, + "loss": 0.7395, + "step": 11591 + }, + { + "epoch": 0.7116240523036311, + "grad_norm": 0.960393189631561, + "learning_rate": 4.053192979706264e-06, + "loss": 0.7481, + "step": 11592 + }, + { + "epoch": 0.7116854415420977, + "grad_norm": 0.9900579503862532, + "learning_rate": 4.051594539647956e-06, + "loss": 0.7895, + "step": 11593 + }, + { + "epoch": 0.7117468307805642, + "grad_norm": 0.9208348690158626, + "learning_rate": 4.049996334761929e-06, + "loss": 0.7712, + "step": 11594 + }, + { + "epoch": 0.7118082200190307, + "grad_norm": 1.0353412521380978, + "learning_rate": 4.048398365111364e-06, + "loss": 0.7965, + "step": 11595 + }, + { + "epoch": 0.7118696092574972, + "grad_norm": 1.0970547415391143, + "learning_rate": 4.046800630759448e-06, + "loss": 0.7561, + "step": 11596 + }, + { + "epoch": 0.7119309984959636, + "grad_norm": 1.0149699163318877, + "learning_rate": 4.045203131769342e-06, + "loss": 0.7996, + "step": 11597 + }, + { + "epoch": 0.7119923877344302, + "grad_norm": 0.9869360818322197, + "learning_rate": 4.043605868204208e-06, + "loss": 0.7344, + "step": 11598 + }, + { + "epoch": 0.7120537769728966, + "grad_norm": 1.0135113001290947, + "learning_rate": 4.042008840127185e-06, + "loss": 0.7301, + "step": 11599 + }, + { + "epoch": 0.7121151662113632, + "grad_norm": 0.9495732179020198, + "learning_rate": 4.040412047601421e-06, + "loss": 0.7738, + "step": 11600 + }, + { + "epoch": 0.7121765554498296, + "grad_norm": 1.019053839432877, + "learning_rate": 4.038815490690043e-06, + "loss": 0.7317, + "step": 11601 + }, + { + "epoch": 0.7122379446882962, + "grad_norm": 0.5744972554134612, + "learning_rate": 4.037219169456171e-06, + "loss": 0.6286, + "step": 11602 + }, + { + "epoch": 0.7122993339267626, + "grad_norm": 1.0481481682501632, + "learning_rate": 4.035623083962917e-06, + "loss": 0.7745, + "step": 11603 + }, + { + "epoch": 0.7123607231652291, + "grad_norm": 0.9762241716067794, + "learning_rate": 4.0340272342733834e-06, + "loss": 0.7832, + "step": 11604 + }, + { + "epoch": 0.7124221124036957, + "grad_norm": 1.0038891678389632, + "learning_rate": 4.03243162045066e-06, + "loss": 0.7776, + "step": 11605 + }, + { + "epoch": 0.7124835016421621, + "grad_norm": 0.9450511717573443, + "learning_rate": 4.0308362425578275e-06, + "loss": 0.7956, + "step": 11606 + }, + { + "epoch": 0.7125448908806287, + "grad_norm": 0.9078554416272822, + "learning_rate": 4.029241100657968e-06, + "loss": 0.8052, + "step": 11607 + }, + { + "epoch": 0.7126062801190951, + "grad_norm": 0.9492679291110135, + "learning_rate": 4.027646194814145e-06, + "loss": 0.7671, + "step": 11608 + }, + { + "epoch": 0.7126676693575617, + "grad_norm": 0.9610893407292093, + "learning_rate": 4.026051525089403e-06, + "loss": 0.7949, + "step": 11609 + }, + { + "epoch": 0.7127290585960281, + "grad_norm": 0.8907198111661664, + "learning_rate": 4.024457091546799e-06, + "loss": 0.7341, + "step": 11610 + }, + { + "epoch": 0.7127904478344946, + "grad_norm": 0.8854340227662375, + "learning_rate": 4.022862894249365e-06, + "loss": 0.7534, + "step": 11611 + }, + { + "epoch": 0.7128518370729611, + "grad_norm": 0.9021986275021863, + "learning_rate": 4.0212689332601295e-06, + "loss": 0.7942, + "step": 11612 + }, + { + "epoch": 0.7129132263114276, + "grad_norm": 1.0689534297720578, + "learning_rate": 4.01967520864211e-06, + "loss": 0.8687, + "step": 11613 + }, + { + "epoch": 0.712974615549894, + "grad_norm": 0.8769956989657548, + "learning_rate": 4.018081720458314e-06, + "loss": 0.7208, + "step": 11614 + }, + { + "epoch": 0.7130360047883606, + "grad_norm": 0.9972215489899906, + "learning_rate": 4.016488468771741e-06, + "loss": 0.7818, + "step": 11615 + }, + { + "epoch": 0.7130973940268271, + "grad_norm": 0.928672853185292, + "learning_rate": 4.014895453645381e-06, + "loss": 0.7599, + "step": 11616 + }, + { + "epoch": 0.7131587832652936, + "grad_norm": 0.9298261096873587, + "learning_rate": 4.01330267514221e-06, + "loss": 0.75, + "step": 11617 + }, + { + "epoch": 0.7132201725037601, + "grad_norm": 0.8757132090266699, + "learning_rate": 4.011710133325212e-06, + "loss": 0.7439, + "step": 11618 + }, + { + "epoch": 0.7132815617422266, + "grad_norm": 1.0330501521514757, + "learning_rate": 4.010117828257335e-06, + "loss": 0.7802, + "step": 11619 + }, + { + "epoch": 0.7133429509806931, + "grad_norm": 1.0595353662615277, + "learning_rate": 4.008525760001534e-06, + "loss": 0.7536, + "step": 11620 + }, + { + "epoch": 0.7134043402191595, + "grad_norm": 0.8606145865049062, + "learning_rate": 4.0069339286207565e-06, + "loss": 0.7268, + "step": 11621 + }, + { + "epoch": 0.7134657294576261, + "grad_norm": 0.9900668495538618, + "learning_rate": 4.005342334177935e-06, + "loss": 0.7698, + "step": 11622 + }, + { + "epoch": 0.7135271186960925, + "grad_norm": 1.0237465145495737, + "learning_rate": 4.003750976735993e-06, + "loss": 0.7705, + "step": 11623 + }, + { + "epoch": 0.7135885079345591, + "grad_norm": 1.0128163001944854, + "learning_rate": 4.002159856357845e-06, + "loss": 0.7809, + "step": 11624 + }, + { + "epoch": 0.7136498971730255, + "grad_norm": 0.9654763760130298, + "learning_rate": 4.000568973106396e-06, + "loss": 0.7572, + "step": 11625 + }, + { + "epoch": 0.7137112864114921, + "grad_norm": 1.0095309147971088, + "learning_rate": 3.998978327044543e-06, + "loss": 0.7571, + "step": 11626 + }, + { + "epoch": 0.7137726756499586, + "grad_norm": 1.1374735684995434, + "learning_rate": 3.9973879182351716e-06, + "loss": 0.803, + "step": 11627 + }, + { + "epoch": 0.713834064888425, + "grad_norm": 0.9563600443757964, + "learning_rate": 3.9957977467411615e-06, + "loss": 0.7239, + "step": 11628 + }, + { + "epoch": 0.7138954541268916, + "grad_norm": 1.0095513065698298, + "learning_rate": 3.994207812625378e-06, + "loss": 0.764, + "step": 11629 + }, + { + "epoch": 0.713956843365358, + "grad_norm": 0.9342431849910103, + "learning_rate": 3.992618115950681e-06, + "loss": 0.7736, + "step": 11630 + }, + { + "epoch": 0.7140182326038246, + "grad_norm": 1.0152784531484096, + "learning_rate": 3.991028656779918e-06, + "loss": 0.7729, + "step": 11631 + }, + { + "epoch": 0.714079621842291, + "grad_norm": 1.0796149572098976, + "learning_rate": 3.989439435175932e-06, + "loss": 0.7447, + "step": 11632 + }, + { + "epoch": 0.7141410110807576, + "grad_norm": 0.9682963551806907, + "learning_rate": 3.987850451201556e-06, + "loss": 0.7364, + "step": 11633 + }, + { + "epoch": 0.714202400319224, + "grad_norm": 0.9861878369155722, + "learning_rate": 3.986261704919599e-06, + "loss": 0.7393, + "step": 11634 + }, + { + "epoch": 0.7142637895576905, + "grad_norm": 1.0233484023876203, + "learning_rate": 3.984673196392885e-06, + "loss": 0.7819, + "step": 11635 + }, + { + "epoch": 0.714325178796157, + "grad_norm": 0.9123436897270735, + "learning_rate": 3.9830849256842115e-06, + "loss": 0.7852, + "step": 11636 + }, + { + "epoch": 0.7143865680346235, + "grad_norm": 0.8488750919290947, + "learning_rate": 3.9814968928563716e-06, + "loss": 0.7504, + "step": 11637 + }, + { + "epoch": 0.7144479572730901, + "grad_norm": 0.870935669137104, + "learning_rate": 3.979909097972149e-06, + "loss": 0.7387, + "step": 11638 + }, + { + "epoch": 0.7145093465115565, + "grad_norm": 0.8871248144620372, + "learning_rate": 3.978321541094318e-06, + "loss": 0.7441, + "step": 11639 + }, + { + "epoch": 0.7145707357500231, + "grad_norm": 0.9624605059319528, + "learning_rate": 3.976734222285641e-06, + "loss": 0.7661, + "step": 11640 + }, + { + "epoch": 0.7146321249884895, + "grad_norm": 1.0165960451971217, + "learning_rate": 3.975147141608876e-06, + "loss": 0.8308, + "step": 11641 + }, + { + "epoch": 0.714693514226956, + "grad_norm": 0.9442386817192425, + "learning_rate": 3.973560299126764e-06, + "loss": 0.7056, + "step": 11642 + }, + { + "epoch": 0.7147549034654225, + "grad_norm": 0.8965923000540844, + "learning_rate": 3.971973694902052e-06, + "loss": 0.7515, + "step": 11643 + }, + { + "epoch": 0.714816292703889, + "grad_norm": 1.0002628633699684, + "learning_rate": 3.9703873289974574e-06, + "loss": 0.8007, + "step": 11644 + }, + { + "epoch": 0.7148776819423555, + "grad_norm": 0.900157054001001, + "learning_rate": 3.968801201475695e-06, + "loss": 0.7619, + "step": 11645 + }, + { + "epoch": 0.714939071180822, + "grad_norm": 0.5519876090637148, + "learning_rate": 3.967215312399483e-06, + "loss": 0.7042, + "step": 11646 + }, + { + "epoch": 0.7150004604192886, + "grad_norm": 1.1088436570655518, + "learning_rate": 3.965629661831515e-06, + "loss": 0.771, + "step": 11647 + }, + { + "epoch": 0.715061849657755, + "grad_norm": 0.9790760016237451, + "learning_rate": 3.96404424983448e-06, + "loss": 0.7688, + "step": 11648 + }, + { + "epoch": 0.7151232388962215, + "grad_norm": 0.9823121043133233, + "learning_rate": 3.962459076471059e-06, + "loss": 0.7458, + "step": 11649 + }, + { + "epoch": 0.715184628134688, + "grad_norm": 1.003757906688625, + "learning_rate": 3.960874141803922e-06, + "loss": 0.7994, + "step": 11650 + }, + { + "epoch": 0.7152460173731545, + "grad_norm": 0.9854548853310359, + "learning_rate": 3.959289445895729e-06, + "loss": 0.7206, + "step": 11651 + }, + { + "epoch": 0.715307406611621, + "grad_norm": 1.0036863799439013, + "learning_rate": 3.957704988809133e-06, + "loss": 0.8027, + "step": 11652 + }, + { + "epoch": 0.7153687958500875, + "grad_norm": 0.9660098713338195, + "learning_rate": 3.956120770606775e-06, + "loss": 0.7805, + "step": 11653 + }, + { + "epoch": 0.7154301850885539, + "grad_norm": 0.9939006696970665, + "learning_rate": 3.954536791351287e-06, + "loss": 0.7531, + "step": 11654 + }, + { + "epoch": 0.7154915743270205, + "grad_norm": 1.050518972361024, + "learning_rate": 3.952953051105294e-06, + "loss": 0.812, + "step": 11655 + }, + { + "epoch": 0.7155529635654869, + "grad_norm": 0.9467034744413444, + "learning_rate": 3.9513695499314054e-06, + "loss": 0.7509, + "step": 11656 + }, + { + "epoch": 0.7156143528039535, + "grad_norm": 0.9208191389838425, + "learning_rate": 3.949786287892235e-06, + "loss": 0.7625, + "step": 11657 + }, + { + "epoch": 0.71567574204242, + "grad_norm": 0.9720085959952028, + "learning_rate": 3.948203265050369e-06, + "loss": 0.8045, + "step": 11658 + }, + { + "epoch": 0.7157371312808865, + "grad_norm": 1.1058661184879754, + "learning_rate": 3.94662048146839e-06, + "loss": 0.7136, + "step": 11659 + }, + { + "epoch": 0.715798520519353, + "grad_norm": 0.9985375101648094, + "learning_rate": 3.9450379372088845e-06, + "loss": 0.7818, + "step": 11660 + }, + { + "epoch": 0.7158599097578194, + "grad_norm": 0.9044615218323112, + "learning_rate": 3.943455632334412e-06, + "loss": 0.75, + "step": 11661 + }, + { + "epoch": 0.715921298996286, + "grad_norm": 0.9120358712309056, + "learning_rate": 3.941873566907533e-06, + "loss": 0.731, + "step": 11662 + }, + { + "epoch": 0.7159826882347524, + "grad_norm": 0.840623751035033, + "learning_rate": 3.94029174099079e-06, + "loss": 0.7091, + "step": 11663 + }, + { + "epoch": 0.716044077473219, + "grad_norm": 0.944565638061223, + "learning_rate": 3.938710154646727e-06, + "loss": 0.7324, + "step": 11664 + }, + { + "epoch": 0.7161054667116854, + "grad_norm": 0.9487946789102425, + "learning_rate": 3.937128807937869e-06, + "loss": 0.7864, + "step": 11665 + }, + { + "epoch": 0.716166855950152, + "grad_norm": 1.0312457332315859, + "learning_rate": 3.935547700926735e-06, + "loss": 0.821, + "step": 11666 + }, + { + "epoch": 0.7162282451886184, + "grad_norm": 0.9929717680543076, + "learning_rate": 3.933966833675835e-06, + "loss": 0.7062, + "step": 11667 + }, + { + "epoch": 0.7162896344270849, + "grad_norm": 1.0884294247374893, + "learning_rate": 3.932386206247671e-06, + "loss": 0.7704, + "step": 11668 + }, + { + "epoch": 0.7163510236655515, + "grad_norm": 0.9447200853249277, + "learning_rate": 3.930805818704731e-06, + "loss": 0.7117, + "step": 11669 + }, + { + "epoch": 0.7164124129040179, + "grad_norm": 1.026405960997817, + "learning_rate": 3.9292256711094935e-06, + "loss": 0.8063, + "step": 11670 + }, + { + "epoch": 0.7164738021424845, + "grad_norm": 1.1045625001200041, + "learning_rate": 3.927645763524438e-06, + "loss": 0.7752, + "step": 11671 + }, + { + "epoch": 0.7165351913809509, + "grad_norm": 0.9211747195869965, + "learning_rate": 3.926066096012026e-06, + "loss": 0.7982, + "step": 11672 + }, + { + "epoch": 0.7165965806194174, + "grad_norm": 1.0422600692074706, + "learning_rate": 3.9244866686347e-06, + "loss": 0.7902, + "step": 11673 + }, + { + "epoch": 0.7166579698578839, + "grad_norm": 1.0291568132144575, + "learning_rate": 3.922907481454915e-06, + "loss": 0.7793, + "step": 11674 + }, + { + "epoch": 0.7167193590963504, + "grad_norm": 1.0413131184456308, + "learning_rate": 3.921328534535098e-06, + "loss": 0.7973, + "step": 11675 + }, + { + "epoch": 0.7167807483348169, + "grad_norm": 1.2111172008181876, + "learning_rate": 3.919749827937677e-06, + "loss": 0.7976, + "step": 11676 + }, + { + "epoch": 0.7168421375732834, + "grad_norm": 0.9625867848321042, + "learning_rate": 3.9181713617250625e-06, + "loss": 0.7964, + "step": 11677 + }, + { + "epoch": 0.7169035268117498, + "grad_norm": 0.8666829390232863, + "learning_rate": 3.916593135959663e-06, + "loss": 0.7172, + "step": 11678 + }, + { + "epoch": 0.7169649160502164, + "grad_norm": 1.1541429212831829, + "learning_rate": 3.915015150703873e-06, + "loss": 0.7136, + "step": 11679 + }, + { + "epoch": 0.7170263052886829, + "grad_norm": 1.053911233904662, + "learning_rate": 3.91343740602008e-06, + "loss": 0.7804, + "step": 11680 + }, + { + "epoch": 0.7170876945271494, + "grad_norm": 1.0246934792199367, + "learning_rate": 3.911859901970654e-06, + "loss": 0.7439, + "step": 11681 + }, + { + "epoch": 0.7171490837656159, + "grad_norm": 1.0279495532938892, + "learning_rate": 3.910282638617976e-06, + "loss": 0.7886, + "step": 11682 + }, + { + "epoch": 0.7172104730040824, + "grad_norm": 1.0119374011207534, + "learning_rate": 3.9087056160243916e-06, + "loss": 0.77, + "step": 11683 + }, + { + "epoch": 0.7172718622425489, + "grad_norm": 1.0202331702186285, + "learning_rate": 3.907128834252249e-06, + "loss": 0.8325, + "step": 11684 + }, + { + "epoch": 0.7173332514810153, + "grad_norm": 0.9055141466173404, + "learning_rate": 3.905552293363895e-06, + "loss": 0.7524, + "step": 11685 + }, + { + "epoch": 0.7173946407194819, + "grad_norm": 0.9536391201854049, + "learning_rate": 3.903975993421654e-06, + "loss": 0.7612, + "step": 11686 + }, + { + "epoch": 0.7174560299579483, + "grad_norm": 0.9608341631350458, + "learning_rate": 3.902399934487845e-06, + "loss": 0.7516, + "step": 11687 + }, + { + "epoch": 0.7175174191964149, + "grad_norm": 1.0502535583353483, + "learning_rate": 3.90082411662478e-06, + "loss": 0.8299, + "step": 11688 + }, + { + "epoch": 0.7175788084348813, + "grad_norm": 0.9491110875289335, + "learning_rate": 3.899248539894756e-06, + "loss": 0.7372, + "step": 11689 + }, + { + "epoch": 0.7176401976733479, + "grad_norm": 0.9828827074167255, + "learning_rate": 3.897673204360068e-06, + "loss": 0.746, + "step": 11690 + }, + { + "epoch": 0.7177015869118144, + "grad_norm": 0.884732085266588, + "learning_rate": 3.8960981100829965e-06, + "loss": 0.7067, + "step": 11691 + }, + { + "epoch": 0.7177629761502808, + "grad_norm": 0.80242634398982, + "learning_rate": 3.894523257125812e-06, + "loss": 0.7027, + "step": 11692 + }, + { + "epoch": 0.7178243653887474, + "grad_norm": 0.881303867675408, + "learning_rate": 3.892948645550778e-06, + "loss": 0.7459, + "step": 11693 + }, + { + "epoch": 0.7178857546272138, + "grad_norm": 0.8578968470489, + "learning_rate": 3.891374275420146e-06, + "loss": 0.7912, + "step": 11694 + }, + { + "epoch": 0.7179471438656804, + "grad_norm": 0.9167332426946531, + "learning_rate": 3.889800146796157e-06, + "loss": 0.7777, + "step": 11695 + }, + { + "epoch": 0.7180085331041468, + "grad_norm": 1.0633626582138946, + "learning_rate": 3.888226259741051e-06, + "loss": 0.7768, + "step": 11696 + }, + { + "epoch": 0.7180699223426134, + "grad_norm": 0.9547070182608439, + "learning_rate": 3.886652614317053e-06, + "loss": 0.7755, + "step": 11697 + }, + { + "epoch": 0.7181313115810798, + "grad_norm": 1.0442779687962016, + "learning_rate": 3.885079210586366e-06, + "loss": 0.803, + "step": 11698 + }, + { + "epoch": 0.7181927008195463, + "grad_norm": 0.8529898351448368, + "learning_rate": 3.883506048611206e-06, + "loss": 0.7453, + "step": 11699 + }, + { + "epoch": 0.7182540900580129, + "grad_norm": 0.9767299723792856, + "learning_rate": 3.8819331284537665e-06, + "loss": 0.7641, + "step": 11700 + }, + { + "epoch": 0.7183154792964793, + "grad_norm": 0.972268581426549, + "learning_rate": 3.880360450176232e-06, + "loss": 0.7905, + "step": 11701 + }, + { + "epoch": 0.7183768685349459, + "grad_norm": 0.8861666872147048, + "learning_rate": 3.878788013840779e-06, + "loss": 0.7755, + "step": 11702 + }, + { + "epoch": 0.7184382577734123, + "grad_norm": 0.9807342797138892, + "learning_rate": 3.877215819509573e-06, + "loss": 0.758, + "step": 11703 + }, + { + "epoch": 0.7184996470118789, + "grad_norm": 0.8951593526036157, + "learning_rate": 3.875643867244774e-06, + "loss": 0.7492, + "step": 11704 + }, + { + "epoch": 0.7185610362503453, + "grad_norm": 1.0383451141112319, + "learning_rate": 3.874072157108527e-06, + "loss": 0.7619, + "step": 11705 + }, + { + "epoch": 0.7186224254888118, + "grad_norm": 1.038015761832125, + "learning_rate": 3.872500689162969e-06, + "loss": 0.8468, + "step": 11706 + }, + { + "epoch": 0.7186838147272783, + "grad_norm": 0.9009682811381654, + "learning_rate": 3.8709294634702374e-06, + "loss": 0.7334, + "step": 11707 + }, + { + "epoch": 0.7187452039657448, + "grad_norm": 0.9062784441730705, + "learning_rate": 3.869358480092441e-06, + "loss": 0.7949, + "step": 11708 + }, + { + "epoch": 0.7188065932042113, + "grad_norm": 1.0364828492437734, + "learning_rate": 3.867787739091691e-06, + "loss": 0.7836, + "step": 11709 + }, + { + "epoch": 0.7188679824426778, + "grad_norm": 0.9763201971578503, + "learning_rate": 3.86621724053009e-06, + "loss": 0.6913, + "step": 11710 + }, + { + "epoch": 0.7189293716811443, + "grad_norm": 0.9464559804837679, + "learning_rate": 3.8646469844697285e-06, + "loss": 0.7939, + "step": 11711 + }, + { + "epoch": 0.7189907609196108, + "grad_norm": 0.9675810238366245, + "learning_rate": 3.8630769709726865e-06, + "loss": 0.7588, + "step": 11712 + }, + { + "epoch": 0.7190521501580773, + "grad_norm": 1.0522193359619303, + "learning_rate": 3.861507200101033e-06, + "loss": 0.7899, + "step": 11713 + }, + { + "epoch": 0.7191135393965438, + "grad_norm": 0.5523563557055376, + "learning_rate": 3.859937671916833e-06, + "loss": 0.6342, + "step": 11714 + }, + { + "epoch": 0.7191749286350103, + "grad_norm": 0.9926398973121644, + "learning_rate": 3.858368386482134e-06, + "loss": 0.7621, + "step": 11715 + }, + { + "epoch": 0.7192363178734767, + "grad_norm": 0.9676814560718433, + "learning_rate": 3.856799343858981e-06, + "loss": 0.731, + "step": 11716 + }, + { + "epoch": 0.7192977071119433, + "grad_norm": 0.9761655608606157, + "learning_rate": 3.855230544109408e-06, + "loss": 0.7554, + "step": 11717 + }, + { + "epoch": 0.7193590963504097, + "grad_norm": 1.0055030165314014, + "learning_rate": 3.853661987295433e-06, + "loss": 0.7882, + "step": 11718 + }, + { + "epoch": 0.7194204855888763, + "grad_norm": 1.0283299936378472, + "learning_rate": 3.852093673479075e-06, + "loss": 0.7684, + "step": 11719 + }, + { + "epoch": 0.7194818748273427, + "grad_norm": 1.0082819197218666, + "learning_rate": 3.85052560272233e-06, + "loss": 0.7374, + "step": 11720 + }, + { + "epoch": 0.7195432640658093, + "grad_norm": 0.8794160231241368, + "learning_rate": 3.848957775087207e-06, + "loss": 0.7617, + "step": 11721 + }, + { + "epoch": 0.7196046533042758, + "grad_norm": 0.9952533505796044, + "learning_rate": 3.847390190635676e-06, + "loss": 0.7435, + "step": 11722 + }, + { + "epoch": 0.7196660425427422, + "grad_norm": 0.8823709977907577, + "learning_rate": 3.845822849429713e-06, + "loss": 0.7728, + "step": 11723 + }, + { + "epoch": 0.7197274317812088, + "grad_norm": 1.026480392310782, + "learning_rate": 3.844255751531293e-06, + "loss": 0.7302, + "step": 11724 + }, + { + "epoch": 0.7197888210196752, + "grad_norm": 0.6290697124799054, + "learning_rate": 3.842688897002366e-06, + "loss": 0.7121, + "step": 11725 + }, + { + "epoch": 0.7198502102581418, + "grad_norm": 0.9610186817426757, + "learning_rate": 3.841122285904877e-06, + "loss": 0.7483, + "step": 11726 + }, + { + "epoch": 0.7199115994966082, + "grad_norm": 0.9835074410515112, + "learning_rate": 3.839555918300766e-06, + "loss": 0.7534, + "step": 11727 + }, + { + "epoch": 0.7199729887350748, + "grad_norm": 0.9368789255786706, + "learning_rate": 3.837989794251956e-06, + "loss": 0.7894, + "step": 11728 + }, + { + "epoch": 0.7200343779735412, + "grad_norm": 0.9669979956032112, + "learning_rate": 3.8364239138203676e-06, + "loss": 0.7352, + "step": 11729 + }, + { + "epoch": 0.7200957672120077, + "grad_norm": 1.0199464258769448, + "learning_rate": 3.834858277067906e-06, + "loss": 0.7524, + "step": 11730 + }, + { + "epoch": 0.7201571564504742, + "grad_norm": 0.9609645381354666, + "learning_rate": 3.833292884056471e-06, + "loss": 0.7728, + "step": 11731 + }, + { + "epoch": 0.7202185456889407, + "grad_norm": 0.9790968586440016, + "learning_rate": 3.831727734847951e-06, + "loss": 0.754, + "step": 11732 + }, + { + "epoch": 0.7202799349274073, + "grad_norm": 0.989325211809125, + "learning_rate": 3.8301628295042225e-06, + "loss": 0.7946, + "step": 11733 + }, + { + "epoch": 0.7203413241658737, + "grad_norm": 1.0317958716371096, + "learning_rate": 3.828598168087153e-06, + "loss": 0.7467, + "step": 11734 + }, + { + "epoch": 0.7204027134043403, + "grad_norm": 1.0366734537526885, + "learning_rate": 3.827033750658608e-06, + "loss": 0.8416, + "step": 11735 + }, + { + "epoch": 0.7204641026428067, + "grad_norm": 0.8789941327506456, + "learning_rate": 3.8254695772804375e-06, + "loss": 0.7334, + "step": 11736 + }, + { + "epoch": 0.7205254918812732, + "grad_norm": 0.9567190554884236, + "learning_rate": 3.823905648014472e-06, + "loss": 0.7568, + "step": 11737 + }, + { + "epoch": 0.7205868811197397, + "grad_norm": 0.9955007495789704, + "learning_rate": 3.822341962922551e-06, + "loss": 0.7504, + "step": 11738 + }, + { + "epoch": 0.7206482703582062, + "grad_norm": 1.0417756462133523, + "learning_rate": 3.8207785220664935e-06, + "loss": 0.807, + "step": 11739 + }, + { + "epoch": 0.7207096595966727, + "grad_norm": 1.0762556641052534, + "learning_rate": 3.81921532550811e-06, + "loss": 0.7158, + "step": 11740 + }, + { + "epoch": 0.7207710488351392, + "grad_norm": 0.9474341842243469, + "learning_rate": 3.817652373309201e-06, + "loss": 0.7257, + "step": 11741 + }, + { + "epoch": 0.7208324380736058, + "grad_norm": 0.9852579012480354, + "learning_rate": 3.81608966553156e-06, + "loss": 0.7519, + "step": 11742 + }, + { + "epoch": 0.7208938273120722, + "grad_norm": 0.9342358279907903, + "learning_rate": 3.814527202236967e-06, + "loss": 0.7873, + "step": 11743 + }, + { + "epoch": 0.7209552165505387, + "grad_norm": 0.9744092259080387, + "learning_rate": 3.812964983487197e-06, + "loss": 0.7608, + "step": 11744 + }, + { + "epoch": 0.7210166057890052, + "grad_norm": 1.0229971823004942, + "learning_rate": 3.811403009344008e-06, + "loss": 0.7426, + "step": 11745 + }, + { + "epoch": 0.7210779950274717, + "grad_norm": 0.926844785251802, + "learning_rate": 3.809841279869164e-06, + "loss": 0.7326, + "step": 11746 + }, + { + "epoch": 0.7211393842659382, + "grad_norm": 0.8314129654253561, + "learning_rate": 3.8082797951243988e-06, + "loss": 0.7497, + "step": 11747 + }, + { + "epoch": 0.7212007735044047, + "grad_norm": 1.0536375230023807, + "learning_rate": 3.8067185551714445e-06, + "loss": 0.7784, + "step": 11748 + }, + { + "epoch": 0.7212621627428711, + "grad_norm": 0.9321133464626725, + "learning_rate": 3.8051575600720336e-06, + "loss": 0.7662, + "step": 11749 + }, + { + "epoch": 0.7213235519813377, + "grad_norm": 0.9690921826138779, + "learning_rate": 3.8035968098878774e-06, + "loss": 0.81, + "step": 11750 + }, + { + "epoch": 0.7213849412198041, + "grad_norm": 1.0813548289962138, + "learning_rate": 3.8020363046806784e-06, + "loss": 0.8406, + "step": 11751 + }, + { + "epoch": 0.7214463304582707, + "grad_norm": 0.9381387560372634, + "learning_rate": 3.8004760445121345e-06, + "loss": 0.7546, + "step": 11752 + }, + { + "epoch": 0.7215077196967372, + "grad_norm": 0.8420104347110404, + "learning_rate": 3.7989160294439297e-06, + "loss": 0.7704, + "step": 11753 + }, + { + "epoch": 0.7215691089352037, + "grad_norm": 0.9864137455405415, + "learning_rate": 3.797356259537739e-06, + "loss": 0.7737, + "step": 11754 + }, + { + "epoch": 0.7216304981736702, + "grad_norm": 0.9268868717871814, + "learning_rate": 3.795796734855227e-06, + "loss": 0.7425, + "step": 11755 + }, + { + "epoch": 0.7216918874121366, + "grad_norm": 1.0110921452777253, + "learning_rate": 3.79423745545806e-06, + "loss": 0.7464, + "step": 11756 + }, + { + "epoch": 0.7217532766506032, + "grad_norm": 1.0327427304372259, + "learning_rate": 3.7926784214078727e-06, + "loss": 0.8034, + "step": 11757 + }, + { + "epoch": 0.7218146658890696, + "grad_norm": 0.891031519369849, + "learning_rate": 3.7911196327663057e-06, + "loss": 0.7381, + "step": 11758 + }, + { + "epoch": 0.7218760551275362, + "grad_norm": 0.8936866604142943, + "learning_rate": 3.789561089594985e-06, + "loss": 0.7715, + "step": 11759 + }, + { + "epoch": 0.7219374443660026, + "grad_norm": 0.8418473747247606, + "learning_rate": 3.788002791955533e-06, + "loss": 0.7737, + "step": 11760 + }, + { + "epoch": 0.7219988336044691, + "grad_norm": 0.8865848970310151, + "learning_rate": 3.7864447399095584e-06, + "loss": 0.7941, + "step": 11761 + }, + { + "epoch": 0.7220602228429356, + "grad_norm": 0.9298519325424213, + "learning_rate": 3.7848869335186488e-06, + "loss": 0.7594, + "step": 11762 + }, + { + "epoch": 0.7221216120814021, + "grad_norm": 0.8997957247078348, + "learning_rate": 3.783329372844403e-06, + "loss": 0.7982, + "step": 11763 + }, + { + "epoch": 0.7221830013198687, + "grad_norm": 0.9221865374396819, + "learning_rate": 3.7817720579483962e-06, + "loss": 0.7667, + "step": 11764 + }, + { + "epoch": 0.7222443905583351, + "grad_norm": 0.8623719416898975, + "learning_rate": 3.7802149888921967e-06, + "loss": 0.7739, + "step": 11765 + }, + { + "epoch": 0.7223057797968017, + "grad_norm": 0.975531917575592, + "learning_rate": 3.7786581657373656e-06, + "loss": 0.7572, + "step": 11766 + }, + { + "epoch": 0.7223671690352681, + "grad_norm": 1.0157098264816014, + "learning_rate": 3.777101588545451e-06, + "loss": 0.7784, + "step": 11767 + }, + { + "epoch": 0.7224285582737346, + "grad_norm": 0.9760750696697281, + "learning_rate": 3.7755452573779925e-06, + "loss": 0.7789, + "step": 11768 + }, + { + "epoch": 0.7224899475122011, + "grad_norm": 1.019536923339429, + "learning_rate": 3.7739891722965207e-06, + "loss": 0.745, + "step": 11769 + }, + { + "epoch": 0.7225513367506676, + "grad_norm": 0.962596333960017, + "learning_rate": 3.7724333333625527e-06, + "loss": 0.7578, + "step": 11770 + }, + { + "epoch": 0.7226127259891341, + "grad_norm": 0.8770995513580356, + "learning_rate": 3.7708777406376095e-06, + "loss": 0.7727, + "step": 11771 + }, + { + "epoch": 0.7226741152276006, + "grad_norm": 0.5890193663517462, + "learning_rate": 3.7693223941831812e-06, + "loss": 0.6462, + "step": 11772 + }, + { + "epoch": 0.722735504466067, + "grad_norm": 1.0049313561807516, + "learning_rate": 3.767767294060759e-06, + "loss": 0.8101, + "step": 11773 + }, + { + "epoch": 0.7227968937045336, + "grad_norm": 1.018964986678417, + "learning_rate": 3.7662124403318314e-06, + "loss": 0.7591, + "step": 11774 + }, + { + "epoch": 0.7228582829430001, + "grad_norm": 0.9253567239894106, + "learning_rate": 3.7646578330578676e-06, + "loss": 0.7433, + "step": 11775 + }, + { + "epoch": 0.7229196721814666, + "grad_norm": 0.9462720890008163, + "learning_rate": 3.7631034723003277e-06, + "loss": 0.7684, + "step": 11776 + }, + { + "epoch": 0.7229810614199331, + "grad_norm": 1.0458376620962806, + "learning_rate": 3.7615493581206654e-06, + "loss": 0.7722, + "step": 11777 + }, + { + "epoch": 0.7230424506583996, + "grad_norm": 0.8419987672009303, + "learning_rate": 3.7599954905803217e-06, + "loss": 0.7253, + "step": 11778 + }, + { + "epoch": 0.7231038398968661, + "grad_norm": 0.9711193191814022, + "learning_rate": 3.758441869740731e-06, + "loss": 0.7912, + "step": 11779 + }, + { + "epoch": 0.7231652291353325, + "grad_norm": 1.023075542190629, + "learning_rate": 3.7568884956633143e-06, + "loss": 0.7654, + "step": 11780 + }, + { + "epoch": 0.7232266183737991, + "grad_norm": 1.0267545373178066, + "learning_rate": 3.7553353684094873e-06, + "loss": 0.7732, + "step": 11781 + }, + { + "epoch": 0.7232880076122655, + "grad_norm": 0.9934262309468855, + "learning_rate": 3.7537824880406516e-06, + "loss": 0.743, + "step": 11782 + }, + { + "epoch": 0.7233493968507321, + "grad_norm": 0.9703919700368718, + "learning_rate": 3.7522298546182014e-06, + "loss": 0.7623, + "step": 11783 + }, + { + "epoch": 0.7234107860891985, + "grad_norm": 0.9906244894440881, + "learning_rate": 3.750677468203516e-06, + "loss": 0.7449, + "step": 11784 + }, + { + "epoch": 0.7234721753276651, + "grad_norm": 0.8762052043385256, + "learning_rate": 3.749125328857981e-06, + "loss": 0.7617, + "step": 11785 + }, + { + "epoch": 0.7235335645661316, + "grad_norm": 0.9470443101971477, + "learning_rate": 3.747573436642952e-06, + "loss": 0.7739, + "step": 11786 + }, + { + "epoch": 0.723594953804598, + "grad_norm": 0.9241060452081913, + "learning_rate": 3.7460217916197805e-06, + "loss": 0.782, + "step": 11787 + }, + { + "epoch": 0.7236563430430646, + "grad_norm": 1.0165421744510321, + "learning_rate": 3.7444703938498196e-06, + "loss": 0.7711, + "step": 11788 + }, + { + "epoch": 0.723717732281531, + "grad_norm": 0.9395431050397589, + "learning_rate": 3.7429192433944016e-06, + "loss": 0.7471, + "step": 11789 + }, + { + "epoch": 0.7237791215199976, + "grad_norm": 0.9183080501910212, + "learning_rate": 3.7413683403148504e-06, + "loss": 0.7033, + "step": 11790 + }, + { + "epoch": 0.723840510758464, + "grad_norm": 0.9444926941723124, + "learning_rate": 3.739817684672483e-06, + "loss": 0.79, + "step": 11791 + }, + { + "epoch": 0.7239018999969306, + "grad_norm": 0.9625250777536074, + "learning_rate": 3.7382672765286033e-06, + "loss": 0.7648, + "step": 11792 + }, + { + "epoch": 0.723963289235397, + "grad_norm": 0.9012879592465112, + "learning_rate": 3.736717115944509e-06, + "loss": 0.751, + "step": 11793 + }, + { + "epoch": 0.7240246784738635, + "grad_norm": 1.0311180531462356, + "learning_rate": 3.7351672029814855e-06, + "loss": 0.7304, + "step": 11794 + }, + { + "epoch": 0.7240860677123301, + "grad_norm": 0.9864198081626453, + "learning_rate": 3.7336175377008098e-06, + "loss": 0.7477, + "step": 11795 + }, + { + "epoch": 0.7241474569507965, + "grad_norm": 1.0298167723550513, + "learning_rate": 3.7320681201637465e-06, + "loss": 0.78, + "step": 11796 + }, + { + "epoch": 0.7242088461892631, + "grad_norm": 1.0435641842269308, + "learning_rate": 3.730518950431554e-06, + "loss": 0.7988, + "step": 11797 + }, + { + "epoch": 0.7242702354277295, + "grad_norm": 0.9713320024454377, + "learning_rate": 3.728970028565476e-06, + "loss": 0.7378, + "step": 11798 + }, + { + "epoch": 0.724331624666196, + "grad_norm": 0.8842069495035495, + "learning_rate": 3.7274213546267555e-06, + "loss": 0.7743, + "step": 11799 + }, + { + "epoch": 0.7243930139046625, + "grad_norm": 0.9473800344601243, + "learning_rate": 3.7258729286766216e-06, + "loss": 0.7535, + "step": 11800 + }, + { + "epoch": 0.724454403143129, + "grad_norm": 1.0026216942587924, + "learning_rate": 3.7243247507762793e-06, + "loss": 0.7832, + "step": 11801 + }, + { + "epoch": 0.7245157923815955, + "grad_norm": 0.9922508046896931, + "learning_rate": 3.7227768209869475e-06, + "loss": 0.7685, + "step": 11802 + }, + { + "epoch": 0.724577181620062, + "grad_norm": 0.9427952191114111, + "learning_rate": 3.7212291393698218e-06, + "loss": 0.7427, + "step": 11803 + }, + { + "epoch": 0.7246385708585285, + "grad_norm": 0.928249185986593, + "learning_rate": 3.719681705986088e-06, + "loss": 0.8046, + "step": 11804 + }, + { + "epoch": 0.724699960096995, + "grad_norm": 1.005273323207804, + "learning_rate": 3.7181345208969277e-06, + "loss": 0.7522, + "step": 11805 + }, + { + "epoch": 0.7247613493354615, + "grad_norm": 0.9032089283531138, + "learning_rate": 3.7165875841635057e-06, + "loss": 0.7649, + "step": 11806 + }, + { + "epoch": 0.724822738573928, + "grad_norm": 0.9961716451942376, + "learning_rate": 3.715040895846984e-06, + "loss": 0.7248, + "step": 11807 + }, + { + "epoch": 0.7248841278123945, + "grad_norm": 0.963312825366534, + "learning_rate": 3.7134944560085096e-06, + "loss": 0.8017, + "step": 11808 + }, + { + "epoch": 0.724945517050861, + "grad_norm": 0.9714525268200241, + "learning_rate": 3.7119482647092187e-06, + "loss": 0.7831, + "step": 11809 + }, + { + "epoch": 0.7250069062893275, + "grad_norm": 0.9464000402286296, + "learning_rate": 3.71040232201025e-06, + "loss": 0.7774, + "step": 11810 + }, + { + "epoch": 0.725068295527794, + "grad_norm": 1.0437185852898427, + "learning_rate": 3.7088566279727132e-06, + "loss": 0.7448, + "step": 11811 + }, + { + "epoch": 0.7251296847662605, + "grad_norm": 0.5822179032097822, + "learning_rate": 3.707311182657718e-06, + "loss": 0.6819, + "step": 11812 + }, + { + "epoch": 0.7251910740047269, + "grad_norm": 1.023347770384098, + "learning_rate": 3.7057659861263716e-06, + "loss": 0.7728, + "step": 11813 + }, + { + "epoch": 0.7252524632431935, + "grad_norm": 1.0773681520650902, + "learning_rate": 3.704221038439759e-06, + "loss": 0.7514, + "step": 11814 + }, + { + "epoch": 0.7253138524816599, + "grad_norm": 0.927507695329655, + "learning_rate": 3.7026763396589615e-06, + "loss": 0.7822, + "step": 11815 + }, + { + "epoch": 0.7253752417201265, + "grad_norm": 0.860285502730694, + "learning_rate": 3.7011318898450475e-06, + "loss": 0.7401, + "step": 11816 + }, + { + "epoch": 0.725436630958593, + "grad_norm": 1.0195125165853294, + "learning_rate": 3.69958768905908e-06, + "loss": 0.7375, + "step": 11817 + }, + { + "epoch": 0.7254980201970594, + "grad_norm": 0.809862560263072, + "learning_rate": 3.698043737362108e-06, + "loss": 0.7447, + "step": 11818 + }, + { + "epoch": 0.725559409435526, + "grad_norm": 0.9022095005059753, + "learning_rate": 3.696500034815168e-06, + "loss": 0.72, + "step": 11819 + }, + { + "epoch": 0.7256207986739924, + "grad_norm": 1.015461312371125, + "learning_rate": 3.694956581479302e-06, + "loss": 0.7931, + "step": 11820 + }, + { + "epoch": 0.725682187912459, + "grad_norm": 0.9470134658037885, + "learning_rate": 3.693413377415521e-06, + "loss": 0.7524, + "step": 11821 + }, + { + "epoch": 0.7257435771509254, + "grad_norm": 0.8654978355243375, + "learning_rate": 3.69187042268484e-06, + "loss": 0.8186, + "step": 11822 + }, + { + "epoch": 0.725804966389392, + "grad_norm": 0.913320324600433, + "learning_rate": 3.6903277173482556e-06, + "loss": 0.7642, + "step": 11823 + }, + { + "epoch": 0.7258663556278584, + "grad_norm": 0.9055692574908933, + "learning_rate": 3.688785261466765e-06, + "loss": 0.7209, + "step": 11824 + }, + { + "epoch": 0.7259277448663249, + "grad_norm": 0.9067545939727365, + "learning_rate": 3.6872430551013526e-06, + "loss": 0.716, + "step": 11825 + }, + { + "epoch": 0.7259891341047914, + "grad_norm": 0.950816505168275, + "learning_rate": 3.6857010983129783e-06, + "loss": 0.7375, + "step": 11826 + }, + { + "epoch": 0.7260505233432579, + "grad_norm": 1.0037424367292713, + "learning_rate": 3.684159391162614e-06, + "loss": 0.7041, + "step": 11827 + }, + { + "epoch": 0.7261119125817245, + "grad_norm": 0.9618432678888122, + "learning_rate": 3.682617933711209e-06, + "loss": 0.7558, + "step": 11828 + }, + { + "epoch": 0.7261733018201909, + "grad_norm": 0.9703867271786677, + "learning_rate": 3.6810767260197044e-06, + "loss": 0.7699, + "step": 11829 + }, + { + "epoch": 0.7262346910586575, + "grad_norm": 0.962623935299895, + "learning_rate": 3.679535768149032e-06, + "loss": 0.7922, + "step": 11830 + }, + { + "epoch": 0.7262960802971239, + "grad_norm": 1.0259057738591786, + "learning_rate": 3.6779950601601155e-06, + "loss": 0.7771, + "step": 11831 + }, + { + "epoch": 0.7263574695355904, + "grad_norm": 0.9097356389851831, + "learning_rate": 3.6764546021138668e-06, + "loss": 0.7354, + "step": 11832 + }, + { + "epoch": 0.7264188587740569, + "grad_norm": 0.8792466355235754, + "learning_rate": 3.6749143940711885e-06, + "loss": 0.7754, + "step": 11833 + }, + { + "epoch": 0.7264802480125234, + "grad_norm": 1.0077271245991082, + "learning_rate": 3.67337443609297e-06, + "loss": 0.7431, + "step": 11834 + }, + { + "epoch": 0.7265416372509899, + "grad_norm": 1.0706294315601548, + "learning_rate": 3.6718347282401033e-06, + "loss": 0.7301, + "step": 11835 + }, + { + "epoch": 0.7266030264894564, + "grad_norm": 0.9555278672492433, + "learning_rate": 3.670295270573453e-06, + "loss": 0.8, + "step": 11836 + }, + { + "epoch": 0.7266644157279228, + "grad_norm": 1.0625279615547465, + "learning_rate": 3.66875606315388e-06, + "loss": 0.723, + "step": 11837 + }, + { + "epoch": 0.7267258049663894, + "grad_norm": 1.028903060723931, + "learning_rate": 3.6672171060422447e-06, + "loss": 0.7713, + "step": 11838 + }, + { + "epoch": 0.7267871942048559, + "grad_norm": 1.0209671253057835, + "learning_rate": 3.6656783992993885e-06, + "loss": 0.7731, + "step": 11839 + }, + { + "epoch": 0.7268485834433224, + "grad_norm": 1.023226735926958, + "learning_rate": 3.6641399429861425e-06, + "loss": 0.7578, + "step": 11840 + }, + { + "epoch": 0.7269099726817889, + "grad_norm": 0.8429893284169158, + "learning_rate": 3.6626017371633314e-06, + "loss": 0.7272, + "step": 11841 + }, + { + "epoch": 0.7269713619202554, + "grad_norm": 0.888788200661621, + "learning_rate": 3.6610637818917683e-06, + "loss": 0.7579, + "step": 11842 + }, + { + "epoch": 0.7270327511587219, + "grad_norm": 0.9582588699633469, + "learning_rate": 3.659526077232257e-06, + "loss": 0.7773, + "step": 11843 + }, + { + "epoch": 0.7270941403971883, + "grad_norm": 0.9408918202403704, + "learning_rate": 3.6579886232455873e-06, + "loss": 0.7433, + "step": 11844 + }, + { + "epoch": 0.7271555296356549, + "grad_norm": 0.9985268096746651, + "learning_rate": 3.6564514199925538e-06, + "loss": 0.7492, + "step": 11845 + }, + { + "epoch": 0.7272169188741213, + "grad_norm": 0.9899349263694932, + "learning_rate": 3.654914467533921e-06, + "loss": 0.7727, + "step": 11846 + }, + { + "epoch": 0.7272783081125879, + "grad_norm": 1.007435976910735, + "learning_rate": 3.6533777659304536e-06, + "loss": 0.7697, + "step": 11847 + }, + { + "epoch": 0.7273396973510544, + "grad_norm": 0.9621885853378603, + "learning_rate": 3.6518413152429057e-06, + "loss": 0.7711, + "step": 11848 + }, + { + "epoch": 0.7274010865895209, + "grad_norm": 0.5694062454667892, + "learning_rate": 3.650305115532028e-06, + "loss": 0.663, + "step": 11849 + }, + { + "epoch": 0.7274624758279874, + "grad_norm": 0.9546823239271902, + "learning_rate": 3.648769166858547e-06, + "loss": 0.6702, + "step": 11850 + }, + { + "epoch": 0.7275238650664538, + "grad_norm": 0.8328361159985154, + "learning_rate": 3.6472334692831857e-06, + "loss": 0.7651, + "step": 11851 + }, + { + "epoch": 0.7275852543049204, + "grad_norm": 1.050772612658999, + "learning_rate": 3.6456980228666662e-06, + "loss": 0.7837, + "step": 11852 + }, + { + "epoch": 0.7276466435433868, + "grad_norm": 0.9834187622534826, + "learning_rate": 3.6441628276696894e-06, + "loss": 0.776, + "step": 11853 + }, + { + "epoch": 0.7277080327818534, + "grad_norm": 1.0336360027255396, + "learning_rate": 3.6426278837529484e-06, + "loss": 0.8143, + "step": 11854 + }, + { + "epoch": 0.7277694220203198, + "grad_norm": 0.8400647263767228, + "learning_rate": 3.6410931911771296e-06, + "loss": 0.7464, + "step": 11855 + }, + { + "epoch": 0.7278308112587863, + "grad_norm": 0.9826010394105, + "learning_rate": 3.6395587500029074e-06, + "loss": 0.7764, + "step": 11856 + }, + { + "epoch": 0.7278922004972528, + "grad_norm": 1.000335608933336, + "learning_rate": 3.6380245602909447e-06, + "loss": 0.734, + "step": 11857 + }, + { + "epoch": 0.7279535897357193, + "grad_norm": 0.9653087596135446, + "learning_rate": 3.6364906221018937e-06, + "loss": 0.7831, + "step": 11858 + }, + { + "epoch": 0.7280149789741859, + "grad_norm": 0.952738452400321, + "learning_rate": 3.634956935496411e-06, + "loss": 0.7812, + "step": 11859 + }, + { + "epoch": 0.7280763682126523, + "grad_norm": 0.9687902056374819, + "learning_rate": 3.633423500535118e-06, + "loss": 0.8209, + "step": 11860 + }, + { + "epoch": 0.7281377574511189, + "grad_norm": 1.0277557471338574, + "learning_rate": 3.631890317278647e-06, + "loss": 0.7572, + "step": 11861 + }, + { + "epoch": 0.7281991466895853, + "grad_norm": 0.95803760655351, + "learning_rate": 3.6303573857876063e-06, + "loss": 0.7521, + "step": 11862 + }, + { + "epoch": 0.7282605359280518, + "grad_norm": 0.9053482001749875, + "learning_rate": 3.628824706122609e-06, + "loss": 0.7518, + "step": 11863 + }, + { + "epoch": 0.7283219251665183, + "grad_norm": 0.9340802617287397, + "learning_rate": 3.62729227834425e-06, + "loss": 0.7515, + "step": 11864 + }, + { + "epoch": 0.7283833144049848, + "grad_norm": 0.9471310492945488, + "learning_rate": 3.625760102513103e-06, + "loss": 0.7695, + "step": 11865 + }, + { + "epoch": 0.7284447036434513, + "grad_norm": 1.0121319396127448, + "learning_rate": 3.6242281786897558e-06, + "loss": 0.7688, + "step": 11866 + }, + { + "epoch": 0.7285060928819178, + "grad_norm": 0.8984511782338858, + "learning_rate": 3.6226965069347677e-06, + "loss": 0.7286, + "step": 11867 + }, + { + "epoch": 0.7285674821203842, + "grad_norm": 0.9848364702186877, + "learning_rate": 3.6211650873086955e-06, + "loss": 0.7412, + "step": 11868 + }, + { + "epoch": 0.7286288713588508, + "grad_norm": 0.9741944327028033, + "learning_rate": 3.619633919872083e-06, + "loss": 0.7068, + "step": 11869 + }, + { + "epoch": 0.7286902605973173, + "grad_norm": 1.0131023522108875, + "learning_rate": 3.618103004685467e-06, + "loss": 0.8464, + "step": 11870 + }, + { + "epoch": 0.7287516498357838, + "grad_norm": 0.9150743752873557, + "learning_rate": 3.6165723418093723e-06, + "loss": 0.7836, + "step": 11871 + }, + { + "epoch": 0.7288130390742503, + "grad_norm": 0.9432918930509961, + "learning_rate": 3.615041931304314e-06, + "loss": 0.7758, + "step": 11872 + }, + { + "epoch": 0.7288744283127168, + "grad_norm": 0.8945747039746063, + "learning_rate": 3.6135117732307932e-06, + "loss": 0.7618, + "step": 11873 + }, + { + "epoch": 0.7289358175511833, + "grad_norm": 0.9126641598889678, + "learning_rate": 3.611981867649316e-06, + "loss": 0.7293, + "step": 11874 + }, + { + "epoch": 0.7289972067896497, + "grad_norm": 0.9947681241347637, + "learning_rate": 3.610452214620358e-06, + "loss": 0.7599, + "step": 11875 + }, + { + "epoch": 0.7290585960281163, + "grad_norm": 0.9252827909164858, + "learning_rate": 3.608922814204394e-06, + "loss": 0.7306, + "step": 11876 + }, + { + "epoch": 0.7291199852665827, + "grad_norm": 1.0475474617598421, + "learning_rate": 3.607393666461897e-06, + "loss": 0.7988, + "step": 11877 + }, + { + "epoch": 0.7291813745050493, + "grad_norm": 0.8795084530218978, + "learning_rate": 3.605864771453318e-06, + "loss": 0.7563, + "step": 11878 + }, + { + "epoch": 0.7292427637435157, + "grad_norm": 1.1099759307541734, + "learning_rate": 3.6043361292391035e-06, + "loss": 0.7945, + "step": 11879 + }, + { + "epoch": 0.7293041529819823, + "grad_norm": 0.9473541730711534, + "learning_rate": 3.602807739879688e-06, + "loss": 0.7353, + "step": 11880 + }, + { + "epoch": 0.7293655422204488, + "grad_norm": 0.9349642243218667, + "learning_rate": 3.601279603435497e-06, + "loss": 0.7346, + "step": 11881 + }, + { + "epoch": 0.7294269314589152, + "grad_norm": 0.9367401325018166, + "learning_rate": 3.599751719966945e-06, + "loss": 0.7125, + "step": 11882 + }, + { + "epoch": 0.7294883206973818, + "grad_norm": 0.9507158898172289, + "learning_rate": 3.598224089534437e-06, + "loss": 0.7377, + "step": 11883 + }, + { + "epoch": 0.7295497099358482, + "grad_norm": 1.046864070178892, + "learning_rate": 3.5966967121983753e-06, + "loss": 0.7766, + "step": 11884 + }, + { + "epoch": 0.7296110991743148, + "grad_norm": 0.9350909894395985, + "learning_rate": 3.5951695880191363e-06, + "loss": 0.7907, + "step": 11885 + }, + { + "epoch": 0.7296724884127812, + "grad_norm": 0.9552826812826363, + "learning_rate": 3.5936427170571e-06, + "loss": 0.7536, + "step": 11886 + }, + { + "epoch": 0.7297338776512478, + "grad_norm": 0.927133851314415, + "learning_rate": 3.592116099372626e-06, + "loss": 0.7304, + "step": 11887 + }, + { + "epoch": 0.7297952668897142, + "grad_norm": 0.9502907341117188, + "learning_rate": 3.5905897350260786e-06, + "loss": 0.7651, + "step": 11888 + }, + { + "epoch": 0.7298566561281807, + "grad_norm": 0.8897776925349847, + "learning_rate": 3.589063624077802e-06, + "loss": 0.7333, + "step": 11889 + }, + { + "epoch": 0.7299180453666472, + "grad_norm": 0.9891487822631286, + "learning_rate": 3.5875377665881216e-06, + "loss": 0.7593, + "step": 11890 + }, + { + "epoch": 0.7299794346051137, + "grad_norm": 0.9193299797890994, + "learning_rate": 3.586012162617374e-06, + "loss": 0.7655, + "step": 11891 + }, + { + "epoch": 0.7300408238435803, + "grad_norm": 0.9600033293403221, + "learning_rate": 3.584486812225868e-06, + "loss": 0.7611, + "step": 11892 + }, + { + "epoch": 0.7301022130820467, + "grad_norm": 0.8863374651240541, + "learning_rate": 3.5829617154739128e-06, + "loss": 0.7335, + "step": 11893 + }, + { + "epoch": 0.7301636023205132, + "grad_norm": 0.918069915647388, + "learning_rate": 3.581436872421801e-06, + "loss": 0.733, + "step": 11894 + }, + { + "epoch": 0.7302249915589797, + "grad_norm": 1.005048332539611, + "learning_rate": 3.5799122831298184e-06, + "loss": 0.7591, + "step": 11895 + }, + { + "epoch": 0.7302863807974462, + "grad_norm": 0.9681635850730601, + "learning_rate": 3.5783879476582407e-06, + "loss": 0.7602, + "step": 11896 + }, + { + "epoch": 0.7303477700359127, + "grad_norm": 0.9918041328678547, + "learning_rate": 3.576863866067328e-06, + "loss": 0.7189, + "step": 11897 + }, + { + "epoch": 0.7304091592743792, + "grad_norm": 1.0215247555960816, + "learning_rate": 3.5753400384173442e-06, + "loss": 0.7944, + "step": 11898 + }, + { + "epoch": 0.7304705485128457, + "grad_norm": 0.8787730115474712, + "learning_rate": 3.5738164647685337e-06, + "loss": 0.764, + "step": 11899 + }, + { + "epoch": 0.7305319377513122, + "grad_norm": 1.0049436407532284, + "learning_rate": 3.572293145181125e-06, + "loss": 0.7022, + "step": 11900 + }, + { + "epoch": 0.7305933269897787, + "grad_norm": 1.0337220354131365, + "learning_rate": 3.5707700797153424e-06, + "loss": 0.7189, + "step": 11901 + }, + { + "epoch": 0.7306547162282452, + "grad_norm": 1.0294310166199705, + "learning_rate": 3.5692472684314074e-06, + "loss": 0.7544, + "step": 11902 + }, + { + "epoch": 0.7307161054667117, + "grad_norm": 0.8666261971326248, + "learning_rate": 3.5677247113895218e-06, + "loss": 0.754, + "step": 11903 + }, + { + "epoch": 0.7307774947051782, + "grad_norm": 0.9312616335247678, + "learning_rate": 3.5662024086498815e-06, + "loss": 0.7043, + "step": 11904 + }, + { + "epoch": 0.7308388839436447, + "grad_norm": 0.84401781632044, + "learning_rate": 3.56468036027267e-06, + "loss": 0.7047, + "step": 11905 + }, + { + "epoch": 0.7309002731821111, + "grad_norm": 0.9286865612838416, + "learning_rate": 3.5631585663180624e-06, + "loss": 0.7437, + "step": 11906 + }, + { + "epoch": 0.7309616624205777, + "grad_norm": 0.9685530694022397, + "learning_rate": 3.561637026846223e-06, + "loss": 0.772, + "step": 11907 + }, + { + "epoch": 0.7310230516590441, + "grad_norm": 0.9552832764430793, + "learning_rate": 3.560115741917304e-06, + "loss": 0.7417, + "step": 11908 + }, + { + "epoch": 0.7310844408975107, + "grad_norm": 0.9897143763443459, + "learning_rate": 3.5585947115914586e-06, + "loss": 0.7478, + "step": 11909 + }, + { + "epoch": 0.7311458301359771, + "grad_norm": 0.9313955610799767, + "learning_rate": 3.557073935928812e-06, + "loss": 0.7282, + "step": 11910 + }, + { + "epoch": 0.7312072193744437, + "grad_norm": 1.0463388154142514, + "learning_rate": 3.5555534149894934e-06, + "loss": 0.7315, + "step": 11911 + }, + { + "epoch": 0.7312686086129102, + "grad_norm": 0.987578327279362, + "learning_rate": 3.5540331488336098e-06, + "loss": 0.7632, + "step": 11912 + }, + { + "epoch": 0.7313299978513766, + "grad_norm": 0.9242458656049752, + "learning_rate": 3.5525131375212797e-06, + "loss": 0.7306, + "step": 11913 + }, + { + "epoch": 0.7313913870898432, + "grad_norm": 0.9500709154301329, + "learning_rate": 3.550993381112585e-06, + "loss": 0.7694, + "step": 11914 + }, + { + "epoch": 0.7314527763283096, + "grad_norm": 0.8909271059141072, + "learning_rate": 3.549473879667611e-06, + "loss": 0.7336, + "step": 11915 + }, + { + "epoch": 0.7315141655667762, + "grad_norm": 1.003669765758619, + "learning_rate": 3.5479546332464364e-06, + "loss": 0.7752, + "step": 11916 + }, + { + "epoch": 0.7315755548052426, + "grad_norm": 1.039961571534383, + "learning_rate": 3.546435641909124e-06, + "loss": 0.7421, + "step": 11917 + }, + { + "epoch": 0.7316369440437092, + "grad_norm": 1.0691668493523214, + "learning_rate": 3.5449169057157263e-06, + "loss": 0.8231, + "step": 11918 + }, + { + "epoch": 0.7316983332821756, + "grad_norm": 0.9411343810778271, + "learning_rate": 3.5433984247262876e-06, + "loss": 0.736, + "step": 11919 + }, + { + "epoch": 0.7317597225206421, + "grad_norm": 1.0522469483892376, + "learning_rate": 3.541880199000842e-06, + "loss": 0.7299, + "step": 11920 + }, + { + "epoch": 0.7318211117591086, + "grad_norm": 0.943560220053683, + "learning_rate": 3.540362228599412e-06, + "loss": 0.7776, + "step": 11921 + }, + { + "epoch": 0.7318825009975751, + "grad_norm": 1.1616505056234931, + "learning_rate": 3.5388445135820094e-06, + "loss": 0.7956, + "step": 11922 + }, + { + "epoch": 0.7319438902360417, + "grad_norm": 0.9702737291869247, + "learning_rate": 3.5373270540086458e-06, + "loss": 0.748, + "step": 11923 + }, + { + "epoch": 0.7320052794745081, + "grad_norm": 1.0199190221022645, + "learning_rate": 3.5358098499393046e-06, + "loss": 0.7535, + "step": 11924 + }, + { + "epoch": 0.7320666687129747, + "grad_norm": 0.9493732000523916, + "learning_rate": 3.5342929014339733e-06, + "loss": 0.7055, + "step": 11925 + }, + { + "epoch": 0.7321280579514411, + "grad_norm": 0.9201517451792195, + "learning_rate": 3.5327762085526216e-06, + "loss": 0.7523, + "step": 11926 + }, + { + "epoch": 0.7321894471899076, + "grad_norm": 0.9570058449273945, + "learning_rate": 3.5312597713552188e-06, + "loss": 0.7683, + "step": 11927 + }, + { + "epoch": 0.7322508364283741, + "grad_norm": 1.0217577266276208, + "learning_rate": 3.5297435899017186e-06, + "loss": 0.795, + "step": 11928 + }, + { + "epoch": 0.7323122256668406, + "grad_norm": 0.8665860583574679, + "learning_rate": 3.528227664252052e-06, + "loss": 0.7582, + "step": 11929 + }, + { + "epoch": 0.7323736149053071, + "grad_norm": 0.9700053268760929, + "learning_rate": 3.526711994466163e-06, + "loss": 0.7688, + "step": 11930 + }, + { + "epoch": 0.7324350041437736, + "grad_norm": 0.9351675058364731, + "learning_rate": 3.52519658060397e-06, + "loss": 0.8027, + "step": 11931 + }, + { + "epoch": 0.73249639338224, + "grad_norm": 0.8576518919286595, + "learning_rate": 3.523681422725386e-06, + "loss": 0.7332, + "step": 11932 + }, + { + "epoch": 0.7325577826207066, + "grad_norm": 0.5942066848231066, + "learning_rate": 3.5221665208903134e-06, + "loss": 0.6453, + "step": 11933 + }, + { + "epoch": 0.7326191718591731, + "grad_norm": 0.9041231001460749, + "learning_rate": 3.520651875158644e-06, + "loss": 0.7862, + "step": 11934 + }, + { + "epoch": 0.7326805610976396, + "grad_norm": 0.9088397098706307, + "learning_rate": 3.5191374855902607e-06, + "loss": 0.7293, + "step": 11935 + }, + { + "epoch": 0.7327419503361061, + "grad_norm": 0.9367057962136813, + "learning_rate": 3.5176233522450297e-06, + "loss": 0.7773, + "step": 11936 + }, + { + "epoch": 0.7328033395745726, + "grad_norm": 0.9397692075339643, + "learning_rate": 3.5161094751828217e-06, + "loss": 0.6503, + "step": 11937 + }, + { + "epoch": 0.7328647288130391, + "grad_norm": 0.9825553384646889, + "learning_rate": 3.5145958544634886e-06, + "loss": 0.7857, + "step": 11938 + }, + { + "epoch": 0.7329261180515055, + "grad_norm": 0.8272756397754708, + "learning_rate": 3.513082490146864e-06, + "loss": 0.7322, + "step": 11939 + }, + { + "epoch": 0.7329875072899721, + "grad_norm": 0.9986516366205639, + "learning_rate": 3.51156938229278e-06, + "loss": 0.7709, + "step": 11940 + }, + { + "epoch": 0.7330488965284385, + "grad_norm": 0.8885555332406553, + "learning_rate": 3.5100565309610636e-06, + "loss": 0.7719, + "step": 11941 + }, + { + "epoch": 0.7331102857669051, + "grad_norm": 1.0361105789764076, + "learning_rate": 3.5085439362115224e-06, + "loss": 0.765, + "step": 11942 + }, + { + "epoch": 0.7331716750053715, + "grad_norm": 1.015437628703964, + "learning_rate": 3.5070315981039594e-06, + "loss": 0.8313, + "step": 11943 + }, + { + "epoch": 0.733233064243838, + "grad_norm": 0.9362065634390299, + "learning_rate": 3.505519516698165e-06, + "loss": 0.7444, + "step": 11944 + }, + { + "epoch": 0.7332944534823046, + "grad_norm": 0.8618939945145438, + "learning_rate": 3.504007692053918e-06, + "loss": 0.6907, + "step": 11945 + }, + { + "epoch": 0.733355842720771, + "grad_norm": 1.0003608479907355, + "learning_rate": 3.5024961242309895e-06, + "loss": 0.7304, + "step": 11946 + }, + { + "epoch": 0.7334172319592376, + "grad_norm": 0.8827265367205047, + "learning_rate": 3.5009848132891367e-06, + "loss": 0.7506, + "step": 11947 + }, + { + "epoch": 0.733478621197704, + "grad_norm": 0.9665836127505636, + "learning_rate": 3.499473759288121e-06, + "loss": 0.7773, + "step": 11948 + }, + { + "epoch": 0.7335400104361706, + "grad_norm": 0.9395602671359159, + "learning_rate": 3.497962962287671e-06, + "loss": 0.7864, + "step": 11949 + }, + { + "epoch": 0.733601399674637, + "grad_norm": 0.9313457324183577, + "learning_rate": 3.4964524223475214e-06, + "loss": 0.7682, + "step": 11950 + }, + { + "epoch": 0.7336627889131035, + "grad_norm": 1.0631518299684946, + "learning_rate": 3.4949421395273863e-06, + "loss": 0.7394, + "step": 11951 + }, + { + "epoch": 0.73372417815157, + "grad_norm": 0.918089983643541, + "learning_rate": 3.4934321138869843e-06, + "loss": 0.8005, + "step": 11952 + }, + { + "epoch": 0.7337855673900365, + "grad_norm": 0.9958667327150758, + "learning_rate": 3.491922345486013e-06, + "loss": 0.7376, + "step": 11953 + }, + { + "epoch": 0.7338469566285031, + "grad_norm": 0.8586006434047445, + "learning_rate": 3.4904128343841526e-06, + "loss": 0.7174, + "step": 11954 + }, + { + "epoch": 0.7339083458669695, + "grad_norm": 0.9007517436400224, + "learning_rate": 3.488903580641092e-06, + "loss": 0.7371, + "step": 11955 + }, + { + "epoch": 0.7339697351054361, + "grad_norm": 0.9166191179584499, + "learning_rate": 3.487394584316497e-06, + "loss": 0.7693, + "step": 11956 + }, + { + "epoch": 0.7340311243439025, + "grad_norm": 0.9387002030043436, + "learning_rate": 3.485885845470025e-06, + "loss": 0.7764, + "step": 11957 + }, + { + "epoch": 0.734092513582369, + "grad_norm": 1.0277306256470333, + "learning_rate": 3.4843773641613264e-06, + "loss": 0.736, + "step": 11958 + }, + { + "epoch": 0.7341539028208355, + "grad_norm": 0.9101952000844376, + "learning_rate": 3.482869140450038e-06, + "loss": 0.7259, + "step": 11959 + }, + { + "epoch": 0.734215292059302, + "grad_norm": 1.0900703443349617, + "learning_rate": 3.4813611743957886e-06, + "loss": 0.7787, + "step": 11960 + }, + { + "epoch": 0.7342766812977685, + "grad_norm": 0.9714550957892768, + "learning_rate": 3.479853466058194e-06, + "loss": 0.7797, + "step": 11961 + }, + { + "epoch": 0.734338070536235, + "grad_norm": 0.9518283664982051, + "learning_rate": 3.478346015496866e-06, + "loss": 0.7688, + "step": 11962 + }, + { + "epoch": 0.7343994597747014, + "grad_norm": 1.0618315302412342, + "learning_rate": 3.4768388227714047e-06, + "loss": 0.7519, + "step": 11963 + }, + { + "epoch": 0.734460849013168, + "grad_norm": 0.918837542922033, + "learning_rate": 3.475331887941388e-06, + "loss": 0.7321, + "step": 11964 + }, + { + "epoch": 0.7345222382516345, + "grad_norm": 0.8549733459506529, + "learning_rate": 3.473825211066396e-06, + "loss": 0.7213, + "step": 11965 + }, + { + "epoch": 0.734583627490101, + "grad_norm": 0.9125688625946502, + "learning_rate": 3.4723187922060007e-06, + "loss": 0.7076, + "step": 11966 + }, + { + "epoch": 0.7346450167285675, + "grad_norm": 0.9976060130340089, + "learning_rate": 3.4708126314197566e-06, + "loss": 0.7545, + "step": 11967 + }, + { + "epoch": 0.734706405967034, + "grad_norm": 1.0002955301357719, + "learning_rate": 3.46930672876721e-06, + "loss": 0.7608, + "step": 11968 + }, + { + "epoch": 0.7347677952055005, + "grad_norm": 0.8424132959501638, + "learning_rate": 3.467801084307896e-06, + "loss": 0.7419, + "step": 11969 + }, + { + "epoch": 0.7348291844439669, + "grad_norm": 0.9799330339244623, + "learning_rate": 3.466295698101342e-06, + "loss": 0.7394, + "step": 11970 + }, + { + "epoch": 0.7348905736824335, + "grad_norm": 1.009980279762203, + "learning_rate": 3.4647905702070637e-06, + "loss": 0.8082, + "step": 11971 + }, + { + "epoch": 0.7349519629208999, + "grad_norm": 0.9301539345801447, + "learning_rate": 3.4632857006845646e-06, + "loss": 0.7722, + "step": 11972 + }, + { + "epoch": 0.7350133521593665, + "grad_norm": 0.5862210346075181, + "learning_rate": 3.461781089593348e-06, + "loss": 0.6824, + "step": 11973 + }, + { + "epoch": 0.7350747413978329, + "grad_norm": 0.9192441141943065, + "learning_rate": 3.460276736992891e-06, + "loss": 0.7613, + "step": 11974 + }, + { + "epoch": 0.7351361306362995, + "grad_norm": 0.91254467407807, + "learning_rate": 3.4587726429426684e-06, + "loss": 0.7298, + "step": 11975 + }, + { + "epoch": 0.735197519874766, + "grad_norm": 0.9935125249525885, + "learning_rate": 3.457268807502151e-06, + "loss": 0.7798, + "step": 11976 + }, + { + "epoch": 0.7352589091132324, + "grad_norm": 0.9137832579425469, + "learning_rate": 3.455765230730794e-06, + "loss": 0.7536, + "step": 11977 + }, + { + "epoch": 0.735320298351699, + "grad_norm": 1.0767313553233013, + "learning_rate": 3.454261912688036e-06, + "loss": 0.7267, + "step": 11978 + }, + { + "epoch": 0.7353816875901654, + "grad_norm": 0.9153636576739307, + "learning_rate": 3.452758853433309e-06, + "loss": 0.7661, + "step": 11979 + }, + { + "epoch": 0.735443076828632, + "grad_norm": 0.9313751436687535, + "learning_rate": 3.4512560530260463e-06, + "loss": 0.7983, + "step": 11980 + }, + { + "epoch": 0.7355044660670984, + "grad_norm": 1.107348978993159, + "learning_rate": 3.4497535115256564e-06, + "loss": 0.7743, + "step": 11981 + }, + { + "epoch": 0.735565855305565, + "grad_norm": 0.9362145941042818, + "learning_rate": 3.4482512289915425e-06, + "loss": 0.7972, + "step": 11982 + }, + { + "epoch": 0.7356272445440314, + "grad_norm": 0.89482981482654, + "learning_rate": 3.4467492054830998e-06, + "loss": 0.77, + "step": 11983 + }, + { + "epoch": 0.7356886337824979, + "grad_norm": 0.9550216663715735, + "learning_rate": 3.4452474410597104e-06, + "loss": 0.8027, + "step": 11984 + }, + { + "epoch": 0.7357500230209644, + "grad_norm": 1.0758675744999395, + "learning_rate": 3.443745935780746e-06, + "loss": 0.7754, + "step": 11985 + }, + { + "epoch": 0.7358114122594309, + "grad_norm": 0.9062162912665706, + "learning_rate": 3.442244689705567e-06, + "loss": 0.7916, + "step": 11986 + }, + { + "epoch": 0.7358728014978975, + "grad_norm": 0.9507362776245956, + "learning_rate": 3.4407437028935353e-06, + "loss": 0.7641, + "step": 11987 + }, + { + "epoch": 0.7359341907363639, + "grad_norm": 0.9901663743843928, + "learning_rate": 3.4392429754039837e-06, + "loss": 0.7402, + "step": 11988 + }, + { + "epoch": 0.7359955799748304, + "grad_norm": 0.8621017190485624, + "learning_rate": 3.4377425072962467e-06, + "loss": 0.7273, + "step": 11989 + }, + { + "epoch": 0.7360569692132969, + "grad_norm": 0.8614624891048034, + "learning_rate": 3.4362422986296417e-06, + "loss": 0.7974, + "step": 11990 + }, + { + "epoch": 0.7361183584517634, + "grad_norm": 1.0631002224178485, + "learning_rate": 3.434742349463488e-06, + "loss": 0.7725, + "step": 11991 + }, + { + "epoch": 0.7361797476902299, + "grad_norm": 0.8995372596616159, + "learning_rate": 3.433242659857086e-06, + "loss": 0.8129, + "step": 11992 + }, + { + "epoch": 0.7362411369286964, + "grad_norm": 0.9946528405283688, + "learning_rate": 3.431743229869716e-06, + "loss": 0.774, + "step": 11993 + }, + { + "epoch": 0.7363025261671629, + "grad_norm": 0.9585050065130264, + "learning_rate": 3.4302440595606702e-06, + "loss": 0.7457, + "step": 11994 + }, + { + "epoch": 0.7363639154056294, + "grad_norm": 0.8965675046697966, + "learning_rate": 3.428745148989213e-06, + "loss": 0.7851, + "step": 11995 + }, + { + "epoch": 0.7364253046440958, + "grad_norm": 0.8691975104098, + "learning_rate": 3.427246498214606e-06, + "loss": 0.7377, + "step": 11996 + }, + { + "epoch": 0.7364866938825624, + "grad_norm": 1.0041757077475806, + "learning_rate": 3.4257481072960984e-06, + "loss": 0.7752, + "step": 11997 + }, + { + "epoch": 0.7365480831210289, + "grad_norm": 0.9040735679939753, + "learning_rate": 3.424249976292929e-06, + "loss": 0.7949, + "step": 11998 + }, + { + "epoch": 0.7366094723594954, + "grad_norm": 0.9904217439711049, + "learning_rate": 3.4227521052643288e-06, + "loss": 0.7459, + "step": 11999 + }, + { + "epoch": 0.7366708615979619, + "grad_norm": 1.00822385903031, + "learning_rate": 3.4212544942695115e-06, + "loss": 0.7327, + "step": 12000 + }, + { + "epoch": 0.7367322508364283, + "grad_norm": 0.91141241713595, + "learning_rate": 3.4197571433676935e-06, + "loss": 0.7313, + "step": 12001 + }, + { + "epoch": 0.7367936400748949, + "grad_norm": 1.219478831476151, + "learning_rate": 3.418260052618072e-06, + "loss": 0.754, + "step": 12002 + }, + { + "epoch": 0.7368550293133613, + "grad_norm": 1.0107088001013045, + "learning_rate": 3.4167632220798297e-06, + "loss": 0.7771, + "step": 12003 + }, + { + "epoch": 0.7369164185518279, + "grad_norm": 1.1297953929963422, + "learning_rate": 3.4152666518121424e-06, + "loss": 0.8055, + "step": 12004 + }, + { + "epoch": 0.7369778077902943, + "grad_norm": 0.5646879645756747, + "learning_rate": 3.4137703418741864e-06, + "loss": 0.6697, + "step": 12005 + }, + { + "epoch": 0.7370391970287609, + "grad_norm": 1.7586941275752694, + "learning_rate": 3.412274292325114e-06, + "loss": 0.787, + "step": 12006 + }, + { + "epoch": 0.7371005862672274, + "grad_norm": 0.978847623804697, + "learning_rate": 3.4107785032240725e-06, + "loss": 0.7848, + "step": 12007 + }, + { + "epoch": 0.7371619755056938, + "grad_norm": 1.0010408482249533, + "learning_rate": 3.409282974630198e-06, + "loss": 0.7421, + "step": 12008 + }, + { + "epoch": 0.7372233647441604, + "grad_norm": 1.008941530007666, + "learning_rate": 3.4077877066026177e-06, + "loss": 0.756, + "step": 12009 + }, + { + "epoch": 0.7372847539826268, + "grad_norm": 0.9792448139550648, + "learning_rate": 3.4062926992004463e-06, + "loss": 0.7744, + "step": 12010 + }, + { + "epoch": 0.7373461432210934, + "grad_norm": 0.9967272407645106, + "learning_rate": 3.404797952482787e-06, + "loss": 0.7736, + "step": 12011 + }, + { + "epoch": 0.7374075324595598, + "grad_norm": 1.0097645201799008, + "learning_rate": 3.403303466508745e-06, + "loss": 0.7509, + "step": 12012 + }, + { + "epoch": 0.7374689216980264, + "grad_norm": 0.9467352554862319, + "learning_rate": 3.401809241337396e-06, + "loss": 0.7444, + "step": 12013 + }, + { + "epoch": 0.7375303109364928, + "grad_norm": 0.9876468302013286, + "learning_rate": 3.4003152770278124e-06, + "loss": 0.7534, + "step": 12014 + }, + { + "epoch": 0.7375917001749593, + "grad_norm": 0.962318050304717, + "learning_rate": 3.3988215736390683e-06, + "loss": 0.7093, + "step": 12015 + }, + { + "epoch": 0.7376530894134258, + "grad_norm": 0.9588173765055036, + "learning_rate": 3.397328131230212e-06, + "loss": 0.7131, + "step": 12016 + }, + { + "epoch": 0.7377144786518923, + "grad_norm": 0.9326820375623128, + "learning_rate": 3.3958349498602926e-06, + "loss": 0.797, + "step": 12017 + }, + { + "epoch": 0.7377758678903589, + "grad_norm": 0.8728149546789992, + "learning_rate": 3.3943420295883323e-06, + "loss": 0.7547, + "step": 12018 + }, + { + "epoch": 0.7378372571288253, + "grad_norm": 1.0629700329851008, + "learning_rate": 3.392849370473363e-06, + "loss": 0.7384, + "step": 12019 + }, + { + "epoch": 0.7378986463672919, + "grad_norm": 1.043793816358556, + "learning_rate": 3.3913569725743976e-06, + "loss": 0.7685, + "step": 12020 + }, + { + "epoch": 0.7379600356057583, + "grad_norm": 0.9334477000280711, + "learning_rate": 3.389864835950435e-06, + "loss": 0.7851, + "step": 12021 + }, + { + "epoch": 0.7380214248442248, + "grad_norm": 1.0109219171337307, + "learning_rate": 3.38837296066047e-06, + "loss": 0.7437, + "step": 12022 + }, + { + "epoch": 0.7380828140826913, + "grad_norm": 0.9828517162045739, + "learning_rate": 3.3868813467634833e-06, + "loss": 0.7982, + "step": 12023 + }, + { + "epoch": 0.7381442033211578, + "grad_norm": 0.9375032787677786, + "learning_rate": 3.3853899943184456e-06, + "loss": 0.8261, + "step": 12024 + }, + { + "epoch": 0.7382055925596243, + "grad_norm": 0.8991863010185606, + "learning_rate": 3.383898903384316e-06, + "loss": 0.6992, + "step": 12025 + }, + { + "epoch": 0.7382669817980908, + "grad_norm": 0.9329031577519609, + "learning_rate": 3.3824080740200517e-06, + "loss": 0.7721, + "step": 12026 + }, + { + "epoch": 0.7383283710365572, + "grad_norm": 0.9145253129489863, + "learning_rate": 3.3809175062845924e-06, + "loss": 0.7183, + "step": 12027 + }, + { + "epoch": 0.7383897602750238, + "grad_norm": 0.9798181797001349, + "learning_rate": 3.3794272002368624e-06, + "loss": 0.7393, + "step": 12028 + }, + { + "epoch": 0.7384511495134903, + "grad_norm": 0.9275663981983787, + "learning_rate": 3.377937155935781e-06, + "loss": 0.7428, + "step": 12029 + }, + { + "epoch": 0.7385125387519568, + "grad_norm": 0.9873196190679007, + "learning_rate": 3.3764473734402646e-06, + "loss": 0.7513, + "step": 12030 + }, + { + "epoch": 0.7385739279904233, + "grad_norm": 0.9188659539546018, + "learning_rate": 3.3749578528092086e-06, + "loss": 0.7558, + "step": 12031 + }, + { + "epoch": 0.7386353172288898, + "grad_norm": 0.8771998092316876, + "learning_rate": 3.3734685941015023e-06, + "loss": 0.7335, + "step": 12032 + }, + { + "epoch": 0.7386967064673563, + "grad_norm": 0.9437646758729165, + "learning_rate": 3.3719795973760226e-06, + "loss": 0.7743, + "step": 12033 + }, + { + "epoch": 0.7387580957058227, + "grad_norm": 0.9975868911049681, + "learning_rate": 3.37049086269164e-06, + "loss": 0.766, + "step": 12034 + }, + { + "epoch": 0.7388194849442893, + "grad_norm": 1.0893882797453929, + "learning_rate": 3.36900239010721e-06, + "loss": 0.7594, + "step": 12035 + }, + { + "epoch": 0.7388808741827557, + "grad_norm": 0.987108450657167, + "learning_rate": 3.3675141796815767e-06, + "loss": 0.7661, + "step": 12036 + }, + { + "epoch": 0.7389422634212223, + "grad_norm": 0.9148614997934377, + "learning_rate": 3.366026231473588e-06, + "loss": 0.707, + "step": 12037 + }, + { + "epoch": 0.7390036526596887, + "grad_norm": 0.9646170686435932, + "learning_rate": 3.364538545542061e-06, + "loss": 0.7211, + "step": 12038 + }, + { + "epoch": 0.7390650418981553, + "grad_norm": 1.0196327328815766, + "learning_rate": 3.3630511219458093e-06, + "loss": 0.7549, + "step": 12039 + }, + { + "epoch": 0.7391264311366218, + "grad_norm": 0.8218327681280103, + "learning_rate": 3.3615639607436478e-06, + "loss": 0.7038, + "step": 12040 + }, + { + "epoch": 0.7391878203750882, + "grad_norm": 1.0677754905231704, + "learning_rate": 3.360077061994368e-06, + "loss": 0.7894, + "step": 12041 + }, + { + "epoch": 0.7392492096135548, + "grad_norm": 0.5798854009193747, + "learning_rate": 3.358590425756758e-06, + "loss": 0.6429, + "step": 12042 + }, + { + "epoch": 0.7393105988520212, + "grad_norm": 1.0170627089881403, + "learning_rate": 3.3571040520895825e-06, + "loss": 0.7659, + "step": 12043 + }, + { + "epoch": 0.7393719880904878, + "grad_norm": 1.000731015374547, + "learning_rate": 3.3556179410516155e-06, + "loss": 0.7629, + "step": 12044 + }, + { + "epoch": 0.7394333773289542, + "grad_norm": 1.030033679557863, + "learning_rate": 3.3541320927016086e-06, + "loss": 0.7432, + "step": 12045 + }, + { + "epoch": 0.7394947665674207, + "grad_norm": 1.0560258277908967, + "learning_rate": 3.352646507098304e-06, + "loss": 0.7277, + "step": 12046 + }, + { + "epoch": 0.7395561558058872, + "grad_norm": 1.0263440006877966, + "learning_rate": 3.3511611843004354e-06, + "loss": 0.7513, + "step": 12047 + }, + { + "epoch": 0.7396175450443537, + "grad_norm": 1.0094943286913933, + "learning_rate": 3.3496761243667264e-06, + "loss": 0.7643, + "step": 12048 + }, + { + "epoch": 0.7396789342828202, + "grad_norm": 1.0347283816367363, + "learning_rate": 3.3481913273558885e-06, + "loss": 0.7482, + "step": 12049 + }, + { + "epoch": 0.7397403235212867, + "grad_norm": 0.9307598027928695, + "learning_rate": 3.3467067933266206e-06, + "loss": 0.7347, + "step": 12050 + }, + { + "epoch": 0.7398017127597533, + "grad_norm": 0.9138315872477756, + "learning_rate": 3.3452225223376234e-06, + "loss": 0.784, + "step": 12051 + }, + { + "epoch": 0.7398631019982197, + "grad_norm": 1.004330843131772, + "learning_rate": 3.3437385144475697e-06, + "loss": 0.7788, + "step": 12052 + }, + { + "epoch": 0.7399244912366862, + "grad_norm": 0.9006886660926791, + "learning_rate": 3.3422547697151286e-06, + "loss": 0.7465, + "step": 12053 + }, + { + "epoch": 0.7399858804751527, + "grad_norm": 1.0139062757468733, + "learning_rate": 3.3407712881989683e-06, + "loss": 0.7784, + "step": 12054 + }, + { + "epoch": 0.7400472697136192, + "grad_norm": 0.9713313328645362, + "learning_rate": 3.3392880699577344e-06, + "loss": 0.7052, + "step": 12055 + }, + { + "epoch": 0.7401086589520857, + "grad_norm": 0.9688118933594558, + "learning_rate": 3.337805115050071e-06, + "loss": 0.7678, + "step": 12056 + }, + { + "epoch": 0.7401700481905522, + "grad_norm": 0.9145320639131415, + "learning_rate": 3.336322423534597e-06, + "loss": 0.7756, + "step": 12057 + }, + { + "epoch": 0.7402314374290186, + "grad_norm": 0.9820969324965484, + "learning_rate": 3.334839995469941e-06, + "loss": 0.6934, + "step": 12058 + }, + { + "epoch": 0.7402928266674852, + "grad_norm": 1.0094999726394267, + "learning_rate": 3.3333578309147065e-06, + "loss": 0.7783, + "step": 12059 + }, + { + "epoch": 0.7403542159059517, + "grad_norm": 0.8791936689359378, + "learning_rate": 3.3318759299274927e-06, + "loss": 0.725, + "step": 12060 + }, + { + "epoch": 0.7404156051444182, + "grad_norm": 0.9987004234479805, + "learning_rate": 3.3303942925668886e-06, + "loss": 0.7652, + "step": 12061 + }, + { + "epoch": 0.7404769943828847, + "grad_norm": 0.592629794729052, + "learning_rate": 3.3289129188914684e-06, + "loss": 0.6279, + "step": 12062 + }, + { + "epoch": 0.7405383836213512, + "grad_norm": 0.9315533921494873, + "learning_rate": 3.3274318089598e-06, + "loss": 0.8141, + "step": 12063 + }, + { + "epoch": 0.7405997728598177, + "grad_norm": 0.9303972810944806, + "learning_rate": 3.3259509628304364e-06, + "loss": 0.8244, + "step": 12064 + }, + { + "epoch": 0.7406611620982841, + "grad_norm": 0.6166095995349422, + "learning_rate": 3.3244703805619304e-06, + "loss": 0.7152, + "step": 12065 + }, + { + "epoch": 0.7407225513367507, + "grad_norm": 1.0062100395476978, + "learning_rate": 3.3229900622128165e-06, + "loss": 0.7706, + "step": 12066 + }, + { + "epoch": 0.7407839405752171, + "grad_norm": 1.0263633451673209, + "learning_rate": 3.321510007841613e-06, + "loss": 0.8113, + "step": 12067 + }, + { + "epoch": 0.7408453298136837, + "grad_norm": 0.8874321919637301, + "learning_rate": 3.3200302175068355e-06, + "loss": 0.7328, + "step": 12068 + }, + { + "epoch": 0.7409067190521501, + "grad_norm": 0.9684156038518302, + "learning_rate": 3.318550691266993e-06, + "loss": 0.7382, + "step": 12069 + }, + { + "epoch": 0.7409681082906167, + "grad_norm": 0.9970883939852966, + "learning_rate": 3.3170714291805772e-06, + "loss": 0.77, + "step": 12070 + }, + { + "epoch": 0.7410294975290832, + "grad_norm": 0.9942171582400298, + "learning_rate": 3.3155924313060693e-06, + "loss": 0.8065, + "step": 12071 + }, + { + "epoch": 0.7410908867675496, + "grad_norm": 1.143678566389438, + "learning_rate": 3.314113697701945e-06, + "loss": 0.7554, + "step": 12072 + }, + { + "epoch": 0.7411522760060162, + "grad_norm": 1.0004187716022637, + "learning_rate": 3.3126352284266638e-06, + "loss": 0.7692, + "step": 12073 + }, + { + "epoch": 0.7412136652444826, + "grad_norm": 0.8642636348592849, + "learning_rate": 3.3111570235386793e-06, + "loss": 0.8009, + "step": 12074 + }, + { + "epoch": 0.7412750544829492, + "grad_norm": 0.9379220610643362, + "learning_rate": 3.309679083096428e-06, + "loss": 0.7391, + "step": 12075 + }, + { + "epoch": 0.7413364437214156, + "grad_norm": 1.0175992131131926, + "learning_rate": 3.3082014071583525e-06, + "loss": 0.7436, + "step": 12076 + }, + { + "epoch": 0.7413978329598822, + "grad_norm": 0.9554687659630807, + "learning_rate": 3.3067239957828612e-06, + "loss": 0.7905, + "step": 12077 + }, + { + "epoch": 0.7414592221983486, + "grad_norm": 0.9635893240390633, + "learning_rate": 3.305246849028365e-06, + "loss": 0.7589, + "step": 12078 + }, + { + "epoch": 0.7415206114368151, + "grad_norm": 1.0423789026705865, + "learning_rate": 3.3037699669532718e-06, + "loss": 0.7785, + "step": 12079 + }, + { + "epoch": 0.7415820006752816, + "grad_norm": 0.8868573389746502, + "learning_rate": 3.302293349615965e-06, + "loss": 0.7499, + "step": 12080 + }, + { + "epoch": 0.7416433899137481, + "grad_norm": 0.8985993345897121, + "learning_rate": 3.3008169970748273e-06, + "loss": 0.7723, + "step": 12081 + }, + { + "epoch": 0.7417047791522147, + "grad_norm": 1.0478514685337255, + "learning_rate": 3.2993409093882155e-06, + "loss": 0.8046, + "step": 12082 + }, + { + "epoch": 0.7417661683906811, + "grad_norm": 1.0217801025292716, + "learning_rate": 3.2978650866145e-06, + "loss": 0.7869, + "step": 12083 + }, + { + "epoch": 0.7418275576291476, + "grad_norm": 0.9353211535738029, + "learning_rate": 3.296389528812023e-06, + "loss": 0.7704, + "step": 12084 + }, + { + "epoch": 0.7418889468676141, + "grad_norm": 0.9234003364744557, + "learning_rate": 3.294914236039122e-06, + "loss": 0.7562, + "step": 12085 + }, + { + "epoch": 0.7419503361060806, + "grad_norm": 0.9244073244896477, + "learning_rate": 3.293439208354121e-06, + "loss": 0.7156, + "step": 12086 + }, + { + "epoch": 0.7420117253445471, + "grad_norm": 0.9401036309491186, + "learning_rate": 3.291964445815338e-06, + "loss": 0.7708, + "step": 12087 + }, + { + "epoch": 0.7420731145830136, + "grad_norm": 0.9958999197136645, + "learning_rate": 3.290489948481077e-06, + "loss": 0.7175, + "step": 12088 + }, + { + "epoch": 0.74213450382148, + "grad_norm": 0.9274527442037342, + "learning_rate": 3.2890157164096315e-06, + "loss": 0.7131, + "step": 12089 + }, + { + "epoch": 0.7421958930599466, + "grad_norm": 0.981001489184522, + "learning_rate": 3.28754174965929e-06, + "loss": 0.7995, + "step": 12090 + }, + { + "epoch": 0.742257282298413, + "grad_norm": 1.0888526820611981, + "learning_rate": 3.2860680482883265e-06, + "loss": 0.7483, + "step": 12091 + }, + { + "epoch": 0.7423186715368796, + "grad_norm": 0.9660551582205325, + "learning_rate": 3.2845946123549998e-06, + "loss": 0.7536, + "step": 12092 + }, + { + "epoch": 0.7423800607753461, + "grad_norm": 1.0450782728199342, + "learning_rate": 3.2831214419175604e-06, + "loss": 0.7566, + "step": 12093 + }, + { + "epoch": 0.7424414500138126, + "grad_norm": 1.0025222904715043, + "learning_rate": 3.2816485370342577e-06, + "loss": 0.7492, + "step": 12094 + }, + { + "epoch": 0.7425028392522791, + "grad_norm": 0.8254666507150162, + "learning_rate": 3.280175897763321e-06, + "loss": 0.7382, + "step": 12095 + }, + { + "epoch": 0.7425642284907455, + "grad_norm": 0.9649200665199239, + "learning_rate": 3.278703524162972e-06, + "loss": 0.7591, + "step": 12096 + }, + { + "epoch": 0.7426256177292121, + "grad_norm": 0.9640220337248964, + "learning_rate": 3.2772314162914198e-06, + "loss": 0.7589, + "step": 12097 + }, + { + "epoch": 0.7426870069676785, + "grad_norm": 0.9307564438610786, + "learning_rate": 3.275759574206866e-06, + "loss": 0.7249, + "step": 12098 + }, + { + "epoch": 0.7427483962061451, + "grad_norm": 0.9049996229945472, + "learning_rate": 3.2742879979675e-06, + "loss": 0.733, + "step": 12099 + }, + { + "epoch": 0.7428097854446115, + "grad_norm": 1.0087079168563262, + "learning_rate": 3.272816687631498e-06, + "loss": 0.7343, + "step": 12100 + }, + { + "epoch": 0.7428711746830781, + "grad_norm": 1.0282081920360595, + "learning_rate": 3.2713456432570377e-06, + "loss": 0.7666, + "step": 12101 + }, + { + "epoch": 0.7429325639215446, + "grad_norm": 0.9000486853387403, + "learning_rate": 3.2698748649022693e-06, + "loss": 0.788, + "step": 12102 + }, + { + "epoch": 0.742993953160011, + "grad_norm": 0.9380599645704722, + "learning_rate": 3.268404352625338e-06, + "loss": 0.787, + "step": 12103 + }, + { + "epoch": 0.7430553423984776, + "grad_norm": 1.0624703855849515, + "learning_rate": 3.2669341064843896e-06, + "loss": 0.7626, + "step": 12104 + }, + { + "epoch": 0.743116731636944, + "grad_norm": 0.9589677024243032, + "learning_rate": 3.2654641265375474e-06, + "loss": 0.7387, + "step": 12105 + }, + { + "epoch": 0.7431781208754106, + "grad_norm": 0.9420917691685575, + "learning_rate": 3.26399441284293e-06, + "loss": 0.7437, + "step": 12106 + }, + { + "epoch": 0.743239510113877, + "grad_norm": 0.9718621497588139, + "learning_rate": 3.2625249654586344e-06, + "loss": 0.7077, + "step": 12107 + }, + { + "epoch": 0.7433008993523436, + "grad_norm": 0.8632309582799239, + "learning_rate": 3.2610557844427637e-06, + "loss": 0.7018, + "step": 12108 + }, + { + "epoch": 0.74336228859081, + "grad_norm": 1.0540442950332616, + "learning_rate": 3.2595868698534007e-06, + "loss": 0.7547, + "step": 12109 + }, + { + "epoch": 0.7434236778292765, + "grad_norm": 1.0372408178337353, + "learning_rate": 3.2581182217486184e-06, + "loss": 0.7895, + "step": 12110 + }, + { + "epoch": 0.743485067067743, + "grad_norm": 1.061761442769753, + "learning_rate": 3.256649840186482e-06, + "loss": 0.7612, + "step": 12111 + }, + { + "epoch": 0.7435464563062095, + "grad_norm": 0.947812471336214, + "learning_rate": 3.255181725225043e-06, + "loss": 0.7449, + "step": 12112 + }, + { + "epoch": 0.7436078455446761, + "grad_norm": 0.9766055940229896, + "learning_rate": 3.253713876922343e-06, + "loss": 0.7548, + "step": 12113 + }, + { + "epoch": 0.7436692347831425, + "grad_norm": 1.0821704111602712, + "learning_rate": 3.252246295336413e-06, + "loss": 0.7727, + "step": 12114 + }, + { + "epoch": 0.743730624021609, + "grad_norm": 0.9453496457814118, + "learning_rate": 3.250778980525283e-06, + "loss": 0.7922, + "step": 12115 + }, + { + "epoch": 0.7437920132600755, + "grad_norm": 1.1412972280628688, + "learning_rate": 3.2493119325469546e-06, + "loss": 0.8216, + "step": 12116 + }, + { + "epoch": 0.743853402498542, + "grad_norm": 1.07253272956372, + "learning_rate": 3.2478451514594265e-06, + "loss": 0.7361, + "step": 12117 + }, + { + "epoch": 0.7439147917370085, + "grad_norm": 0.975305368746174, + "learning_rate": 3.2463786373206963e-06, + "loss": 0.7148, + "step": 12118 + }, + { + "epoch": 0.743976180975475, + "grad_norm": 0.9390866998900252, + "learning_rate": 3.244912390188739e-06, + "loss": 0.7813, + "step": 12119 + }, + { + "epoch": 0.7440375702139415, + "grad_norm": 1.017498361159347, + "learning_rate": 3.243446410121527e-06, + "loss": 0.7222, + "step": 12120 + }, + { + "epoch": 0.744098959452408, + "grad_norm": 0.962923784840048, + "learning_rate": 3.2419806971770085e-06, + "loss": 0.7611, + "step": 12121 + }, + { + "epoch": 0.7441603486908744, + "grad_norm": 0.9419809349959686, + "learning_rate": 3.2405152514131413e-06, + "loss": 0.7777, + "step": 12122 + }, + { + "epoch": 0.744221737929341, + "grad_norm": 1.0525876212340919, + "learning_rate": 3.2390500728878584e-06, + "loss": 0.7307, + "step": 12123 + }, + { + "epoch": 0.7442831271678075, + "grad_norm": 0.9323223676546732, + "learning_rate": 3.237585161659086e-06, + "loss": 0.7692, + "step": 12124 + }, + { + "epoch": 0.744344516406274, + "grad_norm": 0.9437825673308169, + "learning_rate": 3.23612051778474e-06, + "loss": 0.7343, + "step": 12125 + }, + { + "epoch": 0.7444059056447405, + "grad_norm": 1.0346078164425787, + "learning_rate": 3.2346561413227252e-06, + "loss": 0.7413, + "step": 12126 + }, + { + "epoch": 0.744467294883207, + "grad_norm": 1.0948312709312205, + "learning_rate": 3.233192032330937e-06, + "loss": 0.7452, + "step": 12127 + }, + { + "epoch": 0.7445286841216735, + "grad_norm": 0.9972375496557188, + "learning_rate": 3.231728190867257e-06, + "loss": 0.7527, + "step": 12128 + }, + { + "epoch": 0.7445900733601399, + "grad_norm": 0.9864842613208674, + "learning_rate": 3.2302646169895634e-06, + "loss": 0.7248, + "step": 12129 + }, + { + "epoch": 0.7446514625986065, + "grad_norm": 0.9260098054515516, + "learning_rate": 3.228801310755719e-06, + "loss": 0.7364, + "step": 12130 + }, + { + "epoch": 0.7447128518370729, + "grad_norm": 0.9780455278338257, + "learning_rate": 3.2273382722235713e-06, + "loss": 0.7889, + "step": 12131 + }, + { + "epoch": 0.7447742410755395, + "grad_norm": 0.9091020014803587, + "learning_rate": 3.2258755014509615e-06, + "loss": 0.7416, + "step": 12132 + }, + { + "epoch": 0.7448356303140059, + "grad_norm": 0.8897042019768766, + "learning_rate": 3.2244129984957264e-06, + "loss": 0.7206, + "step": 12133 + }, + { + "epoch": 0.7448970195524725, + "grad_norm": 0.9343774783879515, + "learning_rate": 3.222950763415684e-06, + "loss": 0.7486, + "step": 12134 + }, + { + "epoch": 0.744958408790939, + "grad_norm": 0.9635031927115287, + "learning_rate": 3.2214887962686445e-06, + "loss": 0.7278, + "step": 12135 + }, + { + "epoch": 0.7450197980294054, + "grad_norm": 1.0386633297586263, + "learning_rate": 3.220027097112406e-06, + "loss": 0.7777, + "step": 12136 + }, + { + "epoch": 0.745081187267872, + "grad_norm": 0.9499049636782004, + "learning_rate": 3.2185656660047592e-06, + "loss": 0.7575, + "step": 12137 + }, + { + "epoch": 0.7451425765063384, + "grad_norm": 0.9640431656794684, + "learning_rate": 3.217104503003481e-06, + "loss": 0.7218, + "step": 12138 + }, + { + "epoch": 0.745203965744805, + "grad_norm": 0.9826988745485228, + "learning_rate": 3.2156436081663356e-06, + "loss": 0.7096, + "step": 12139 + }, + { + "epoch": 0.7452653549832714, + "grad_norm": 0.8372514186233039, + "learning_rate": 3.2141829815510907e-06, + "loss": 0.7153, + "step": 12140 + }, + { + "epoch": 0.745326744221738, + "grad_norm": 0.9144014189557729, + "learning_rate": 3.212722623215482e-06, + "loss": 0.7484, + "step": 12141 + }, + { + "epoch": 0.7453881334602044, + "grad_norm": 0.913865499883123, + "learning_rate": 3.2112625332172453e-06, + "loss": 0.7179, + "step": 12142 + }, + { + "epoch": 0.7454495226986709, + "grad_norm": 0.9703994288740185, + "learning_rate": 3.209802711614113e-06, + "loss": 0.7883, + "step": 12143 + }, + { + "epoch": 0.7455109119371374, + "grad_norm": 1.000212285812023, + "learning_rate": 3.2083431584637958e-06, + "loss": 0.7393, + "step": 12144 + }, + { + "epoch": 0.7455723011756039, + "grad_norm": 0.9367616412032367, + "learning_rate": 3.2068838738240017e-06, + "loss": 0.7528, + "step": 12145 + }, + { + "epoch": 0.7456336904140705, + "grad_norm": 0.9517705304306857, + "learning_rate": 3.205424857752414e-06, + "loss": 0.7449, + "step": 12146 + }, + { + "epoch": 0.7456950796525369, + "grad_norm": 0.9987270764783717, + "learning_rate": 3.2039661103067244e-06, + "loss": 0.7268, + "step": 12147 + }, + { + "epoch": 0.7457564688910034, + "grad_norm": 0.8837646281607725, + "learning_rate": 3.202507631544601e-06, + "loss": 0.7388, + "step": 12148 + }, + { + "epoch": 0.7458178581294699, + "grad_norm": 0.8770424532814711, + "learning_rate": 3.2010494215237086e-06, + "loss": 0.7383, + "step": 12149 + }, + { + "epoch": 0.7458792473679364, + "grad_norm": 0.6485237030672658, + "learning_rate": 3.1995914803016948e-06, + "loss": 0.7116, + "step": 12150 + }, + { + "epoch": 0.7459406366064029, + "grad_norm": 0.9041024057304172, + "learning_rate": 3.1981338079362012e-06, + "loss": 0.752, + "step": 12151 + }, + { + "epoch": 0.7460020258448694, + "grad_norm": 1.038591488965616, + "learning_rate": 3.1966764044848563e-06, + "loss": 0.7439, + "step": 12152 + }, + { + "epoch": 0.7460634150833358, + "grad_norm": 0.9330760222067378, + "learning_rate": 3.1952192700052776e-06, + "loss": 0.7628, + "step": 12153 + }, + { + "epoch": 0.7461248043218024, + "grad_norm": 0.9647313523024891, + "learning_rate": 3.1937624045550787e-06, + "loss": 0.7374, + "step": 12154 + }, + { + "epoch": 0.7461861935602689, + "grad_norm": 1.025810368673837, + "learning_rate": 3.192305808191858e-06, + "loss": 0.7792, + "step": 12155 + }, + { + "epoch": 0.7462475827987354, + "grad_norm": 0.8934553216331313, + "learning_rate": 3.1908494809731917e-06, + "loss": 0.7288, + "step": 12156 + }, + { + "epoch": 0.7463089720372019, + "grad_norm": 0.9509230234529001, + "learning_rate": 3.1893934229566657e-06, + "loss": 0.7101, + "step": 12157 + }, + { + "epoch": 0.7463703612756684, + "grad_norm": 0.9512573538518492, + "learning_rate": 3.1879376341998447e-06, + "loss": 0.7547, + "step": 12158 + }, + { + "epoch": 0.7464317505141349, + "grad_norm": 1.0004662194088036, + "learning_rate": 3.186482114760282e-06, + "loss": 0.7493, + "step": 12159 + }, + { + "epoch": 0.7464931397526013, + "grad_norm": 0.9515121538171096, + "learning_rate": 3.185026864695523e-06, + "loss": 0.7489, + "step": 12160 + }, + { + "epoch": 0.7465545289910679, + "grad_norm": 1.0009105742311204, + "learning_rate": 3.1835718840631e-06, + "loss": 0.7891, + "step": 12161 + }, + { + "epoch": 0.7466159182295343, + "grad_norm": 0.8818202988861442, + "learning_rate": 3.182117172920538e-06, + "loss": 0.7657, + "step": 12162 + }, + { + "epoch": 0.7466773074680009, + "grad_norm": 0.9137173932418913, + "learning_rate": 3.180662731325349e-06, + "loss": 0.7969, + "step": 12163 + }, + { + "epoch": 0.7467386967064673, + "grad_norm": 1.0760060454723173, + "learning_rate": 3.179208559335031e-06, + "loss": 0.7599, + "step": 12164 + }, + { + "epoch": 0.7468000859449339, + "grad_norm": 0.9339418377613239, + "learning_rate": 3.177754657007085e-06, + "loss": 0.7471, + "step": 12165 + }, + { + "epoch": 0.7468614751834004, + "grad_norm": 1.0725839916443711, + "learning_rate": 3.176301024398982e-06, + "loss": 0.7265, + "step": 12166 + }, + { + "epoch": 0.7469228644218668, + "grad_norm": 1.0587141991713742, + "learning_rate": 3.174847661568193e-06, + "loss": 0.7772, + "step": 12167 + }, + { + "epoch": 0.7469842536603334, + "grad_norm": 1.003108408048157, + "learning_rate": 3.1733945685721824e-06, + "loss": 0.7414, + "step": 12168 + }, + { + "epoch": 0.7470456428987998, + "grad_norm": 1.0409307015420064, + "learning_rate": 3.1719417454683954e-06, + "loss": 0.7492, + "step": 12169 + }, + { + "epoch": 0.7471070321372664, + "grad_norm": 0.9687317761051646, + "learning_rate": 3.1704891923142735e-06, + "loss": 0.7478, + "step": 12170 + }, + { + "epoch": 0.7471684213757328, + "grad_norm": 0.9570701136295015, + "learning_rate": 3.1690369091672335e-06, + "loss": 0.767, + "step": 12171 + }, + { + "epoch": 0.7472298106141994, + "grad_norm": 1.0047675193727559, + "learning_rate": 3.1675848960847035e-06, + "loss": 0.6913, + "step": 12172 + }, + { + "epoch": 0.7472911998526658, + "grad_norm": 1.0129715996230952, + "learning_rate": 3.1661331531240835e-06, + "loss": 0.7513, + "step": 12173 + }, + { + "epoch": 0.7473525890911323, + "grad_norm": 0.972330600079578, + "learning_rate": 3.1646816803427714e-06, + "loss": 0.7461, + "step": 12174 + }, + { + "epoch": 0.7474139783295988, + "grad_norm": 0.9424357599096173, + "learning_rate": 3.1632304777981494e-06, + "loss": 0.7046, + "step": 12175 + }, + { + "epoch": 0.7474753675680653, + "grad_norm": 1.0941643599616688, + "learning_rate": 3.161779545547593e-06, + "loss": 0.7616, + "step": 12176 + }, + { + "epoch": 0.7475367568065319, + "grad_norm": 0.9068858300840072, + "learning_rate": 3.1603288836484638e-06, + "loss": 0.7312, + "step": 12177 + }, + { + "epoch": 0.7475981460449983, + "grad_norm": 0.9011417670205771, + "learning_rate": 3.158878492158113e-06, + "loss": 0.7361, + "step": 12178 + }, + { + "epoch": 0.7476595352834648, + "grad_norm": 0.9202722066265139, + "learning_rate": 3.1574283711338894e-06, + "loss": 0.6824, + "step": 12179 + }, + { + "epoch": 0.7477209245219313, + "grad_norm": 1.0707413310835052, + "learning_rate": 3.155978520633116e-06, + "loss": 0.726, + "step": 12180 + }, + { + "epoch": 0.7477823137603978, + "grad_norm": 1.0773563729373596, + "learning_rate": 3.1545289407131128e-06, + "loss": 0.7637, + "step": 12181 + }, + { + "epoch": 0.7478437029988643, + "grad_norm": 0.9259763686772912, + "learning_rate": 3.1530796314311964e-06, + "loss": 0.7782, + "step": 12182 + }, + { + "epoch": 0.7479050922373308, + "grad_norm": 0.9542606280705265, + "learning_rate": 3.1516305928446613e-06, + "loss": 0.7553, + "step": 12183 + }, + { + "epoch": 0.7479664814757973, + "grad_norm": 0.9489787029591986, + "learning_rate": 3.150181825010801e-06, + "loss": 0.7273, + "step": 12184 + }, + { + "epoch": 0.7480278707142638, + "grad_norm": 1.0216913881688927, + "learning_rate": 3.1487333279868814e-06, + "loss": 0.7559, + "step": 12185 + }, + { + "epoch": 0.7480892599527302, + "grad_norm": 0.7744675362984221, + "learning_rate": 3.1472851018301787e-06, + "loss": 0.7517, + "step": 12186 + }, + { + "epoch": 0.7481506491911968, + "grad_norm": 1.1561203731262113, + "learning_rate": 3.145837146597949e-06, + "loss": 0.7383, + "step": 12187 + }, + { + "epoch": 0.7482120384296633, + "grad_norm": 1.0004136520477842, + "learning_rate": 3.1443894623474334e-06, + "loss": 0.723, + "step": 12188 + }, + { + "epoch": 0.7482734276681298, + "grad_norm": 1.0177186771963875, + "learning_rate": 3.1429420491358696e-06, + "loss": 0.7608, + "step": 12189 + }, + { + "epoch": 0.7483348169065963, + "grad_norm": 0.9520448150077948, + "learning_rate": 3.1414949070204814e-06, + "loss": 0.74, + "step": 12190 + }, + { + "epoch": 0.7483962061450627, + "grad_norm": 0.8981341501979231, + "learning_rate": 3.1400480360584806e-06, + "loss": 0.7343, + "step": 12191 + }, + { + "epoch": 0.7484575953835293, + "grad_norm": 0.9978062833153286, + "learning_rate": 3.1386014363070673e-06, + "loss": 0.7631, + "step": 12192 + }, + { + "epoch": 0.7485189846219957, + "grad_norm": 0.9473759214133091, + "learning_rate": 3.13715510782344e-06, + "loss": 0.7454, + "step": 12193 + }, + { + "epoch": 0.7485803738604623, + "grad_norm": 0.9768703319107509, + "learning_rate": 3.1357090506647793e-06, + "loss": 0.7282, + "step": 12194 + }, + { + "epoch": 0.7486417630989287, + "grad_norm": 0.9352832346074013, + "learning_rate": 3.1342632648882465e-06, + "loss": 0.7602, + "step": 12195 + }, + { + "epoch": 0.7487031523373953, + "grad_norm": 1.0676515669154412, + "learning_rate": 3.1328177505510103e-06, + "loss": 0.7168, + "step": 12196 + }, + { + "epoch": 0.7487645415758617, + "grad_norm": 0.9406672415129078, + "learning_rate": 3.1313725077102173e-06, + "loss": 0.7281, + "step": 12197 + }, + { + "epoch": 0.7488259308143282, + "grad_norm": 0.9964633351798791, + "learning_rate": 3.129927536423005e-06, + "loss": 0.7692, + "step": 12198 + }, + { + "epoch": 0.7488873200527948, + "grad_norm": 1.112344949073914, + "learning_rate": 3.1284828367465005e-06, + "loss": 0.7567, + "step": 12199 + }, + { + "epoch": 0.7489487092912612, + "grad_norm": 0.9605668316918615, + "learning_rate": 3.1270384087378215e-06, + "loss": 0.7629, + "step": 12200 + }, + { + "epoch": 0.7490100985297278, + "grad_norm": 0.9525913419481785, + "learning_rate": 3.125594252454073e-06, + "loss": 0.7205, + "step": 12201 + }, + { + "epoch": 0.7490714877681942, + "grad_norm": 0.9317386976789288, + "learning_rate": 3.1241503679523498e-06, + "loss": 0.7068, + "step": 12202 + }, + { + "epoch": 0.7491328770066608, + "grad_norm": 1.0141011499184052, + "learning_rate": 3.122706755289735e-06, + "loss": 0.7148, + "step": 12203 + }, + { + "epoch": 0.7491942662451272, + "grad_norm": 1.0094092451906087, + "learning_rate": 3.121263414523311e-06, + "loss": 0.753, + "step": 12204 + }, + { + "epoch": 0.7492556554835937, + "grad_norm": 0.8406112878979829, + "learning_rate": 3.1198203457101306e-06, + "loss": 0.756, + "step": 12205 + }, + { + "epoch": 0.7493170447220602, + "grad_norm": 0.9946702331562073, + "learning_rate": 3.1183775489072463e-06, + "loss": 0.7683, + "step": 12206 + }, + { + "epoch": 0.7493784339605267, + "grad_norm": 1.0528363106300174, + "learning_rate": 3.116935024171707e-06, + "loss": 0.791, + "step": 12207 + }, + { + "epoch": 0.7494398231989933, + "grad_norm": 0.9717603606575267, + "learning_rate": 3.1154927715605387e-06, + "loss": 0.7554, + "step": 12208 + }, + { + "epoch": 0.7495012124374597, + "grad_norm": 0.9754802798827706, + "learning_rate": 3.114050791130766e-06, + "loss": 0.7597, + "step": 12209 + }, + { + "epoch": 0.7495626016759263, + "grad_norm": 1.0612300160979877, + "learning_rate": 3.1126090829393864e-06, + "loss": 0.7797, + "step": 12210 + }, + { + "epoch": 0.7496239909143927, + "grad_norm": 1.090639956437585, + "learning_rate": 3.1111676470434105e-06, + "loss": 0.7711, + "step": 12211 + }, + { + "epoch": 0.7496853801528592, + "grad_norm": 0.9840196115454058, + "learning_rate": 3.1097264834998207e-06, + "loss": 0.7781, + "step": 12212 + }, + { + "epoch": 0.7497467693913257, + "grad_norm": 0.9303239755987052, + "learning_rate": 3.108285592365596e-06, + "loss": 0.7209, + "step": 12213 + }, + { + "epoch": 0.7498081586297922, + "grad_norm": 0.780140778459716, + "learning_rate": 3.1068449736977015e-06, + "loss": 0.7015, + "step": 12214 + }, + { + "epoch": 0.7498695478682587, + "grad_norm": 0.9099599027628128, + "learning_rate": 3.1054046275530912e-06, + "loss": 0.7463, + "step": 12215 + }, + { + "epoch": 0.7499309371067252, + "grad_norm": 1.03285685643228, + "learning_rate": 3.103964553988711e-06, + "loss": 0.7228, + "step": 12216 + }, + { + "epoch": 0.7499923263451916, + "grad_norm": 0.9860832550626933, + "learning_rate": 3.102524753061491e-06, + "loss": 0.8008, + "step": 12217 + }, + { + "epoch": 0.7500537155836582, + "grad_norm": 0.9246387909782522, + "learning_rate": 3.101085224828362e-06, + "loss": 0.7163, + "step": 12218 + }, + { + "epoch": 0.7501151048221247, + "grad_norm": 0.95530142102506, + "learning_rate": 3.0996459693462346e-06, + "loss": 0.7656, + "step": 12219 + }, + { + "epoch": 0.7501764940605912, + "grad_norm": 1.0527974515753038, + "learning_rate": 3.098206986672002e-06, + "loss": 0.7366, + "step": 12220 + }, + { + "epoch": 0.7502378832990577, + "grad_norm": 1.0929634277024112, + "learning_rate": 3.0967682768625627e-06, + "loss": 0.7407, + "step": 12221 + }, + { + "epoch": 0.7502992725375242, + "grad_norm": 0.9033238370677013, + "learning_rate": 3.0953298399747953e-06, + "loss": 0.7271, + "step": 12222 + }, + { + "epoch": 0.7503606617759907, + "grad_norm": 0.9063200821935532, + "learning_rate": 3.093891676065568e-06, + "loss": 0.7363, + "step": 12223 + }, + { + "epoch": 0.7504220510144571, + "grad_norm": 0.974837755394462, + "learning_rate": 3.092453785191739e-06, + "loss": 0.7265, + "step": 12224 + }, + { + "epoch": 0.7504834402529237, + "grad_norm": 0.9819387216406451, + "learning_rate": 3.0910161674101567e-06, + "loss": 0.7544, + "step": 12225 + }, + { + "epoch": 0.7505448294913901, + "grad_norm": 0.9487143072437225, + "learning_rate": 3.089578822777657e-06, + "loss": 0.7768, + "step": 12226 + }, + { + "epoch": 0.7506062187298567, + "grad_norm": 1.0951857097879976, + "learning_rate": 3.088141751351066e-06, + "loss": 0.7618, + "step": 12227 + }, + { + "epoch": 0.7506676079683231, + "grad_norm": 0.9560254852736935, + "learning_rate": 3.086704953187194e-06, + "loss": 0.7419, + "step": 12228 + }, + { + "epoch": 0.7507289972067896, + "grad_norm": 0.9745360848916584, + "learning_rate": 3.085268428342858e-06, + "loss": 0.7353, + "step": 12229 + }, + { + "epoch": 0.7507903864452562, + "grad_norm": 1.0256730468271473, + "learning_rate": 3.0838321768748405e-06, + "loss": 0.7645, + "step": 12230 + }, + { + "epoch": 0.7508517756837226, + "grad_norm": 0.9757765359123672, + "learning_rate": 3.0823961988399233e-06, + "loss": 0.7561, + "step": 12231 + }, + { + "epoch": 0.7509131649221892, + "grad_norm": 1.0162858265275305, + "learning_rate": 3.0809604942948855e-06, + "loss": 0.7661, + "step": 12232 + }, + { + "epoch": 0.7509745541606556, + "grad_norm": 1.195021264099247, + "learning_rate": 3.0795250632964855e-06, + "loss": 0.8109, + "step": 12233 + }, + { + "epoch": 0.7510359433991222, + "grad_norm": 1.028079659457556, + "learning_rate": 3.0780899059014734e-06, + "loss": 0.7761, + "step": 12234 + }, + { + "epoch": 0.7510973326375886, + "grad_norm": 1.031828198841843, + "learning_rate": 3.076655022166588e-06, + "loss": 0.7495, + "step": 12235 + }, + { + "epoch": 0.7511587218760551, + "grad_norm": 1.0985492966869856, + "learning_rate": 3.0752204121485583e-06, + "loss": 0.736, + "step": 12236 + }, + { + "epoch": 0.7512201111145216, + "grad_norm": 0.9333533472362349, + "learning_rate": 3.0737860759041015e-06, + "loss": 0.7564, + "step": 12237 + }, + { + "epoch": 0.7512815003529881, + "grad_norm": 0.9889994649792847, + "learning_rate": 3.0723520134899254e-06, + "loss": 0.7888, + "step": 12238 + }, + { + "epoch": 0.7513428895914546, + "grad_norm": 0.9854718391768811, + "learning_rate": 3.0709182249627255e-06, + "loss": 0.715, + "step": 12239 + }, + { + "epoch": 0.7514042788299211, + "grad_norm": 0.901518463154075, + "learning_rate": 3.069484710379188e-06, + "loss": 0.759, + "step": 12240 + }, + { + "epoch": 0.7514656680683877, + "grad_norm": 1.0295369287744771, + "learning_rate": 3.0680514697959873e-06, + "loss": 0.7323, + "step": 12241 + }, + { + "epoch": 0.7515270573068541, + "grad_norm": 1.0482940800522136, + "learning_rate": 3.0666185032697824e-06, + "loss": 0.743, + "step": 12242 + }, + { + "epoch": 0.7515884465453206, + "grad_norm": 0.8532967986371455, + "learning_rate": 3.0651858108572375e-06, + "loss": 0.7039, + "step": 12243 + }, + { + "epoch": 0.7516498357837871, + "grad_norm": 0.9768241077608579, + "learning_rate": 3.063753392614984e-06, + "loss": 0.7265, + "step": 12244 + }, + { + "epoch": 0.7517112250222536, + "grad_norm": 0.9822325350086548, + "learning_rate": 3.0623212485996543e-06, + "loss": 0.7207, + "step": 12245 + }, + { + "epoch": 0.7517726142607201, + "grad_norm": 1.0035995569345877, + "learning_rate": 3.060889378867873e-06, + "loss": 0.767, + "step": 12246 + }, + { + "epoch": 0.7518340034991866, + "grad_norm": 0.9401004780142846, + "learning_rate": 3.0594577834762485e-06, + "loss": 0.7303, + "step": 12247 + }, + { + "epoch": 0.751895392737653, + "grad_norm": 0.9336935348001246, + "learning_rate": 3.0580264624813805e-06, + "loss": 0.7752, + "step": 12248 + }, + { + "epoch": 0.7519567819761196, + "grad_norm": 0.9766391417340676, + "learning_rate": 3.056595415939849e-06, + "loss": 0.7017, + "step": 12249 + }, + { + "epoch": 0.752018171214586, + "grad_norm": 1.120079095747793, + "learning_rate": 3.0551646439082393e-06, + "loss": 0.7808, + "step": 12250 + }, + { + "epoch": 0.7520795604530526, + "grad_norm": 0.9268646364874104, + "learning_rate": 3.053734146443116e-06, + "loss": 0.6644, + "step": 12251 + }, + { + "epoch": 0.7521409496915191, + "grad_norm": 0.8388965436090154, + "learning_rate": 3.052303923601032e-06, + "loss": 0.7258, + "step": 12252 + }, + { + "epoch": 0.7522023389299856, + "grad_norm": 0.9611653714720417, + "learning_rate": 3.050873975438533e-06, + "loss": 0.7603, + "step": 12253 + }, + { + "epoch": 0.7522637281684521, + "grad_norm": 1.03453527053511, + "learning_rate": 3.0494443020121523e-06, + "loss": 0.7495, + "step": 12254 + }, + { + "epoch": 0.7523251174069185, + "grad_norm": 0.964248208795431, + "learning_rate": 3.0480149033784122e-06, + "loss": 0.733, + "step": 12255 + }, + { + "epoch": 0.7523865066453851, + "grad_norm": 0.8918162635241188, + "learning_rate": 3.0465857795938226e-06, + "loss": 0.7495, + "step": 12256 + }, + { + "epoch": 0.7524478958838515, + "grad_norm": 0.901261327005425, + "learning_rate": 3.04515693071489e-06, + "loss": 0.7589, + "step": 12257 + }, + { + "epoch": 0.7525092851223181, + "grad_norm": 0.9839738981710618, + "learning_rate": 3.0437283567981025e-06, + "loss": 0.7984, + "step": 12258 + }, + { + "epoch": 0.7525706743607845, + "grad_norm": 0.982839212698085, + "learning_rate": 3.042300057899933e-06, + "loss": 0.791, + "step": 12259 + }, + { + "epoch": 0.752632063599251, + "grad_norm": 0.949884840375122, + "learning_rate": 3.040872034076857e-06, + "loss": 0.7866, + "step": 12260 + }, + { + "epoch": 0.7526934528377176, + "grad_norm": 0.9394072315947841, + "learning_rate": 3.03944428538533e-06, + "loss": 0.7368, + "step": 12261 + }, + { + "epoch": 0.752754842076184, + "grad_norm": 1.036317580898317, + "learning_rate": 3.0380168118817978e-06, + "loss": 0.764, + "step": 12262 + }, + { + "epoch": 0.7528162313146506, + "grad_norm": 1.1038351994028692, + "learning_rate": 3.0365896136226956e-06, + "loss": 0.7963, + "step": 12263 + }, + { + "epoch": 0.752877620553117, + "grad_norm": 1.0041583980141477, + "learning_rate": 3.0351626906644505e-06, + "loss": 0.7278, + "step": 12264 + }, + { + "epoch": 0.7529390097915836, + "grad_norm": 1.0423070404592647, + "learning_rate": 3.033736043063473e-06, + "loss": 0.7672, + "step": 12265 + }, + { + "epoch": 0.75300039903005, + "grad_norm": 0.8995348685369069, + "learning_rate": 3.032309670876169e-06, + "loss": 0.7359, + "step": 12266 + }, + { + "epoch": 0.7530617882685166, + "grad_norm": 0.9923900020674793, + "learning_rate": 3.030883574158927e-06, + "loss": 0.7374, + "step": 12267 + }, + { + "epoch": 0.753123177506983, + "grad_norm": 0.9355275947193135, + "learning_rate": 3.029457752968136e-06, + "loss": 0.8166, + "step": 12268 + }, + { + "epoch": 0.7531845667454495, + "grad_norm": 0.8937030820134827, + "learning_rate": 3.0280322073601585e-06, + "loss": 0.7638, + "step": 12269 + }, + { + "epoch": 0.753245955983916, + "grad_norm": 1.035203029136919, + "learning_rate": 3.026606937391353e-06, + "loss": 0.7185, + "step": 12270 + }, + { + "epoch": 0.7533073452223825, + "grad_norm": 1.0613369506023684, + "learning_rate": 3.0251819431180752e-06, + "loss": 0.7563, + "step": 12271 + }, + { + "epoch": 0.7533687344608491, + "grad_norm": 0.8847236730881037, + "learning_rate": 3.0237572245966585e-06, + "loss": 0.761, + "step": 12272 + }, + { + "epoch": 0.7534301236993155, + "grad_norm": 1.0172745329122137, + "learning_rate": 3.0223327818834313e-06, + "loss": 0.7468, + "step": 12273 + }, + { + "epoch": 0.753491512937782, + "grad_norm": 0.9352941334560216, + "learning_rate": 3.0209086150347078e-06, + "loss": 0.7251, + "step": 12274 + }, + { + "epoch": 0.7535529021762485, + "grad_norm": 1.096237500332658, + "learning_rate": 3.0194847241067928e-06, + "loss": 0.7448, + "step": 12275 + }, + { + "epoch": 0.753614291414715, + "grad_norm": 0.9554813168414447, + "learning_rate": 3.0180611091559818e-06, + "loss": 0.763, + "step": 12276 + }, + { + "epoch": 0.7536756806531815, + "grad_norm": 0.9572085213850782, + "learning_rate": 3.0166377702385576e-06, + "loss": 0.7461, + "step": 12277 + }, + { + "epoch": 0.753737069891648, + "grad_norm": 0.8430840331620771, + "learning_rate": 3.015214707410792e-06, + "loss": 0.7513, + "step": 12278 + }, + { + "epoch": 0.7537984591301145, + "grad_norm": 0.9982462360539114, + "learning_rate": 3.0137919207289457e-06, + "loss": 0.7229, + "step": 12279 + }, + { + "epoch": 0.753859848368581, + "grad_norm": 0.8948343167385809, + "learning_rate": 3.0123694102492695e-06, + "loss": 0.7772, + "step": 12280 + }, + { + "epoch": 0.7539212376070474, + "grad_norm": 1.0339164730137298, + "learning_rate": 3.0109471760279994e-06, + "loss": 0.7981, + "step": 12281 + }, + { + "epoch": 0.753982626845514, + "grad_norm": 1.0197135510962234, + "learning_rate": 3.0095252181213717e-06, + "loss": 0.7023, + "step": 12282 + }, + { + "epoch": 0.7540440160839805, + "grad_norm": 0.9574826566958694, + "learning_rate": 3.0081035365856028e-06, + "loss": 0.7776, + "step": 12283 + }, + { + "epoch": 0.754105405322447, + "grad_norm": 0.9833789774256166, + "learning_rate": 3.00668213147689e-06, + "loss": 0.7512, + "step": 12284 + }, + { + "epoch": 0.7541667945609135, + "grad_norm": 1.001724566600979, + "learning_rate": 3.0052610028514384e-06, + "loss": 0.7909, + "step": 12285 + }, + { + "epoch": 0.75422818379938, + "grad_norm": 0.9493307518811279, + "learning_rate": 3.0038401507654303e-06, + "loss": 0.7098, + "step": 12286 + }, + { + "epoch": 0.7542895730378465, + "grad_norm": 1.1354682113912118, + "learning_rate": 3.0024195752750386e-06, + "loss": 0.8054, + "step": 12287 + }, + { + "epoch": 0.7543509622763129, + "grad_norm": 0.8781122103561023, + "learning_rate": 3.000999276436427e-06, + "loss": 0.6951, + "step": 12288 + }, + { + "epoch": 0.7544123515147795, + "grad_norm": 1.0973284021019243, + "learning_rate": 2.999579254305748e-06, + "loss": 0.7475, + "step": 12289 + }, + { + "epoch": 0.7544737407532459, + "grad_norm": 1.0413866641622764, + "learning_rate": 2.99815950893914e-06, + "loss": 0.7477, + "step": 12290 + }, + { + "epoch": 0.7545351299917125, + "grad_norm": 1.0312391504473846, + "learning_rate": 2.996740040392737e-06, + "loss": 0.7456, + "step": 12291 + }, + { + "epoch": 0.7545965192301789, + "grad_norm": 1.1267589309693895, + "learning_rate": 2.9953208487226527e-06, + "loss": 0.7764, + "step": 12292 + }, + { + "epoch": 0.7546579084686454, + "grad_norm": 0.8266942493740315, + "learning_rate": 2.9939019339850053e-06, + "loss": 0.7361, + "step": 12293 + }, + { + "epoch": 0.754719297707112, + "grad_norm": 0.9783342464541885, + "learning_rate": 2.992483296235882e-06, + "loss": 0.7471, + "step": 12294 + }, + { + "epoch": 0.7547806869455784, + "grad_norm": 1.01205747858736, + "learning_rate": 2.991064935531369e-06, + "loss": 0.7418, + "step": 12295 + }, + { + "epoch": 0.754842076184045, + "grad_norm": 0.9802306910988013, + "learning_rate": 2.98964685192755e-06, + "loss": 0.7595, + "step": 12296 + }, + { + "epoch": 0.7549034654225114, + "grad_norm": 0.906326553022236, + "learning_rate": 2.988229045480484e-06, + "loss": 0.7755, + "step": 12297 + }, + { + "epoch": 0.754964854660978, + "grad_norm": 0.9880730439095167, + "learning_rate": 2.9868115162462263e-06, + "loss": 0.744, + "step": 12298 + }, + { + "epoch": 0.7550262438994444, + "grad_norm": 0.9161583029514796, + "learning_rate": 2.9853942642808187e-06, + "loss": 0.7292, + "step": 12299 + }, + { + "epoch": 0.7550876331379109, + "grad_norm": 0.9484990612820422, + "learning_rate": 2.983977289640292e-06, + "loss": 0.7799, + "step": 12300 + }, + { + "epoch": 0.7551490223763774, + "grad_norm": 0.971644869398021, + "learning_rate": 2.9825605923806666e-06, + "loss": 0.7575, + "step": 12301 + }, + { + "epoch": 0.7552104116148439, + "grad_norm": 0.9696798454836578, + "learning_rate": 2.9811441725579536e-06, + "loss": 0.7631, + "step": 12302 + }, + { + "epoch": 0.7552718008533104, + "grad_norm": 0.9585636185082311, + "learning_rate": 2.9797280302281516e-06, + "loss": 0.7048, + "step": 12303 + }, + { + "epoch": 0.7553331900917769, + "grad_norm": 0.9852956691242674, + "learning_rate": 2.978312165447247e-06, + "loss": 0.7899, + "step": 12304 + }, + { + "epoch": 0.7553945793302435, + "grad_norm": 0.926495496777551, + "learning_rate": 2.9768965782712177e-06, + "loss": 0.7336, + "step": 12305 + }, + { + "epoch": 0.7554559685687099, + "grad_norm": 0.9773921831468392, + "learning_rate": 2.975481268756025e-06, + "loss": 0.7607, + "step": 12306 + }, + { + "epoch": 0.7555173578071764, + "grad_norm": 0.9190334159909673, + "learning_rate": 2.9740662369576334e-06, + "loss": 0.7351, + "step": 12307 + }, + { + "epoch": 0.7555787470456429, + "grad_norm": 0.9763084529757506, + "learning_rate": 2.9726514829319784e-06, + "loss": 0.739, + "step": 12308 + }, + { + "epoch": 0.7556401362841094, + "grad_norm": 0.9190400394185287, + "learning_rate": 2.9712370067349915e-06, + "loss": 0.7415, + "step": 12309 + }, + { + "epoch": 0.7557015255225759, + "grad_norm": 1.0061933592718018, + "learning_rate": 2.969822808422602e-06, + "loss": 0.7508, + "step": 12310 + }, + { + "epoch": 0.7557629147610424, + "grad_norm": 0.9007071591972885, + "learning_rate": 2.968408888050717e-06, + "loss": 0.7782, + "step": 12311 + }, + { + "epoch": 0.7558243039995088, + "grad_norm": 0.9870133778862075, + "learning_rate": 2.966995245675236e-06, + "loss": 0.7941, + "step": 12312 + }, + { + "epoch": 0.7558856932379754, + "grad_norm": 0.8950080898444366, + "learning_rate": 2.9655818813520475e-06, + "loss": 0.7755, + "step": 12313 + }, + { + "epoch": 0.7559470824764419, + "grad_norm": 1.0691223326648431, + "learning_rate": 2.96416879513703e-06, + "loss": 0.7684, + "step": 12314 + }, + { + "epoch": 0.7560084717149084, + "grad_norm": 0.9449326714575109, + "learning_rate": 2.9627559870860513e-06, + "loss": 0.7264, + "step": 12315 + }, + { + "epoch": 0.7560698609533749, + "grad_norm": 1.0081938422728074, + "learning_rate": 2.961343457254966e-06, + "loss": 0.7042, + "step": 12316 + }, + { + "epoch": 0.7561312501918414, + "grad_norm": 1.001513933359413, + "learning_rate": 2.959931205699619e-06, + "loss": 0.7442, + "step": 12317 + }, + { + "epoch": 0.7561926394303079, + "grad_norm": 1.0412701706872154, + "learning_rate": 2.9585192324758436e-06, + "loss": 0.7598, + "step": 12318 + }, + { + "epoch": 0.7562540286687743, + "grad_norm": 0.588547069120699, + "learning_rate": 2.9571075376394643e-06, + "loss": 0.6679, + "step": 12319 + }, + { + "epoch": 0.7563154179072409, + "grad_norm": 0.9655953474442707, + "learning_rate": 2.9556961212462885e-06, + "loss": 0.7496, + "step": 12320 + }, + { + "epoch": 0.7563768071457073, + "grad_norm": 0.9945536138423768, + "learning_rate": 2.9542849833521235e-06, + "loss": 0.7421, + "step": 12321 + }, + { + "epoch": 0.7564381963841739, + "grad_norm": 1.0510326499280858, + "learning_rate": 2.95287412401276e-06, + "loss": 0.785, + "step": 12322 + }, + { + "epoch": 0.7564995856226403, + "grad_norm": 0.9763073834075316, + "learning_rate": 2.9514635432839666e-06, + "loss": 0.7464, + "step": 12323 + }, + { + "epoch": 0.7565609748611068, + "grad_norm": 0.933342511878571, + "learning_rate": 2.950053241221521e-06, + "loss": 0.7215, + "step": 12324 + }, + { + "epoch": 0.7566223640995734, + "grad_norm": 0.92974644464314, + "learning_rate": 2.9486432178811764e-06, + "loss": 0.7968, + "step": 12325 + }, + { + "epoch": 0.7566837533380398, + "grad_norm": 0.963079264158469, + "learning_rate": 2.9472334733186793e-06, + "loss": 0.7135, + "step": 12326 + }, + { + "epoch": 0.7567451425765064, + "grad_norm": 0.9545324326888727, + "learning_rate": 2.9458240075897625e-06, + "loss": 0.7739, + "step": 12327 + }, + { + "epoch": 0.7568065318149728, + "grad_norm": 0.8802569996109264, + "learning_rate": 2.944414820750152e-06, + "loss": 0.7927, + "step": 12328 + }, + { + "epoch": 0.7568679210534394, + "grad_norm": 1.0100300138340188, + "learning_rate": 2.9430059128555586e-06, + "loss": 0.761, + "step": 12329 + }, + { + "epoch": 0.7569293102919058, + "grad_norm": 0.987691789022341, + "learning_rate": 2.9415972839616855e-06, + "loss": 0.7868, + "step": 12330 + }, + { + "epoch": 0.7569906995303723, + "grad_norm": 1.0015776465685713, + "learning_rate": 2.9401889341242196e-06, + "loss": 0.7702, + "step": 12331 + }, + { + "epoch": 0.7570520887688388, + "grad_norm": 0.9540458167809706, + "learning_rate": 2.9387808633988503e-06, + "loss": 0.7175, + "step": 12332 + }, + { + "epoch": 0.7571134780073053, + "grad_norm": 1.0861420326696054, + "learning_rate": 2.937373071841236e-06, + "loss": 0.7357, + "step": 12333 + }, + { + "epoch": 0.7571748672457718, + "grad_norm": 0.9529565879577651, + "learning_rate": 2.935965559507035e-06, + "loss": 0.7679, + "step": 12334 + }, + { + "epoch": 0.7572362564842383, + "grad_norm": 0.9705267112261216, + "learning_rate": 2.9345583264518993e-06, + "loss": 0.7526, + "step": 12335 + }, + { + "epoch": 0.7572976457227049, + "grad_norm": 1.036661188681863, + "learning_rate": 2.933151372731462e-06, + "loss": 0.7655, + "step": 12336 + }, + { + "epoch": 0.7573590349611713, + "grad_norm": 0.8537951010598619, + "learning_rate": 2.9317446984013466e-06, + "loss": 0.7813, + "step": 12337 + }, + { + "epoch": 0.7574204241996378, + "grad_norm": 1.0004709622721897, + "learning_rate": 2.9303383035171672e-06, + "loss": 0.7316, + "step": 12338 + }, + { + "epoch": 0.7574818134381043, + "grad_norm": 0.9662626727708539, + "learning_rate": 2.9289321881345257e-06, + "loss": 0.7965, + "step": 12339 + }, + { + "epoch": 0.7575432026765708, + "grad_norm": 0.9317191132343503, + "learning_rate": 2.9275263523090135e-06, + "loss": 0.7366, + "step": 12340 + }, + { + "epoch": 0.7576045919150373, + "grad_norm": 0.9073376604678329, + "learning_rate": 2.9261207960962114e-06, + "loss": 0.7551, + "step": 12341 + }, + { + "epoch": 0.7576659811535038, + "grad_norm": 0.9649880620747844, + "learning_rate": 2.9247155195516876e-06, + "loss": 0.7217, + "step": 12342 + }, + { + "epoch": 0.7577273703919702, + "grad_norm": 0.9972795919718958, + "learning_rate": 2.923310522731e-06, + "loss": 0.7308, + "step": 12343 + }, + { + "epoch": 0.7577887596304368, + "grad_norm": 0.9693778557997449, + "learning_rate": 2.9219058056896967e-06, + "loss": 0.7549, + "step": 12344 + }, + { + "epoch": 0.7578501488689032, + "grad_norm": 1.0458772844517978, + "learning_rate": 2.9205013684833108e-06, + "loss": 0.7741, + "step": 12345 + }, + { + "epoch": 0.7579115381073698, + "grad_norm": 0.9158246779511489, + "learning_rate": 2.9190972111673723e-06, + "loss": 0.7348, + "step": 12346 + }, + { + "epoch": 0.7579729273458363, + "grad_norm": 1.1184754968206712, + "learning_rate": 2.9176933337973946e-06, + "loss": 0.761, + "step": 12347 + }, + { + "epoch": 0.7580343165843028, + "grad_norm": 0.6372164977190187, + "learning_rate": 2.9162897364288735e-06, + "loss": 0.668, + "step": 12348 + }, + { + "epoch": 0.7580957058227693, + "grad_norm": 0.9340542869619388, + "learning_rate": 2.9148864191173075e-06, + "loss": 0.7034, + "step": 12349 + }, + { + "epoch": 0.7581570950612357, + "grad_norm": 1.0084194337829537, + "learning_rate": 2.913483381918175e-06, + "loss": 0.7482, + "step": 12350 + }, + { + "epoch": 0.7582184842997023, + "grad_norm": 0.9817903893584298, + "learning_rate": 2.912080624886947e-06, + "loss": 0.6973, + "step": 12351 + }, + { + "epoch": 0.7582798735381687, + "grad_norm": 1.0116230657073118, + "learning_rate": 2.91067814807908e-06, + "loss": 0.7544, + "step": 12352 + }, + { + "epoch": 0.7583412627766353, + "grad_norm": 0.925800538761176, + "learning_rate": 2.9092759515500225e-06, + "loss": 0.7554, + "step": 12353 + }, + { + "epoch": 0.7584026520151017, + "grad_norm": 0.9494638998091989, + "learning_rate": 2.9078740353552093e-06, + "loss": 0.7452, + "step": 12354 + }, + { + "epoch": 0.7584640412535683, + "grad_norm": 0.9928255299194861, + "learning_rate": 2.906472399550068e-06, + "loss": 0.7815, + "step": 12355 + }, + { + "epoch": 0.7585254304920347, + "grad_norm": 0.8823484763155747, + "learning_rate": 2.905071044190009e-06, + "loss": 0.6937, + "step": 12356 + }, + { + "epoch": 0.7585868197305012, + "grad_norm": 1.0498697211862038, + "learning_rate": 2.903669969330443e-06, + "loss": 0.7395, + "step": 12357 + }, + { + "epoch": 0.7586482089689678, + "grad_norm": 0.9646693974259856, + "learning_rate": 2.9022691750267538e-06, + "loss": 0.772, + "step": 12358 + }, + { + "epoch": 0.7587095982074342, + "grad_norm": 1.01366520530044, + "learning_rate": 2.900868661334323e-06, + "loss": 0.7116, + "step": 12359 + }, + { + "epoch": 0.7587709874459008, + "grad_norm": 0.987884059900162, + "learning_rate": 2.899468428308526e-06, + "loss": 0.7911, + "step": 12360 + }, + { + "epoch": 0.7588323766843672, + "grad_norm": 0.9552799462673043, + "learning_rate": 2.8980684760047182e-06, + "loss": 0.7655, + "step": 12361 + }, + { + "epoch": 0.7588937659228338, + "grad_norm": 1.0322964468099998, + "learning_rate": 2.8966688044782476e-06, + "loss": 0.7631, + "step": 12362 + }, + { + "epoch": 0.7589551551613002, + "grad_norm": 1.0655989666710803, + "learning_rate": 2.8952694137844494e-06, + "loss": 0.7534, + "step": 12363 + }, + { + "epoch": 0.7590165443997667, + "grad_norm": 0.9462130646022289, + "learning_rate": 2.8938703039786507e-06, + "loss": 0.7468, + "step": 12364 + }, + { + "epoch": 0.7590779336382332, + "grad_norm": 0.9141297680328399, + "learning_rate": 2.8924714751161653e-06, + "loss": 0.7392, + "step": 12365 + }, + { + "epoch": 0.7591393228766997, + "grad_norm": 0.9369582852357042, + "learning_rate": 2.8910729272522963e-06, + "loss": 0.7568, + "step": 12366 + }, + { + "epoch": 0.7592007121151663, + "grad_norm": 1.0076180221123914, + "learning_rate": 2.8896746604423355e-06, + "loss": 0.761, + "step": 12367 + }, + { + "epoch": 0.7592621013536327, + "grad_norm": 1.0743244189642331, + "learning_rate": 2.8882766747415636e-06, + "loss": 0.6925, + "step": 12368 + }, + { + "epoch": 0.7593234905920992, + "grad_norm": 1.110449530347945, + "learning_rate": 2.8868789702052513e-06, + "loss": 0.7312, + "step": 12369 + }, + { + "epoch": 0.7593848798305657, + "grad_norm": 1.004122255184409, + "learning_rate": 2.8854815468886544e-06, + "loss": 0.7906, + "step": 12370 + }, + { + "epoch": 0.7594462690690322, + "grad_norm": 0.9774422147357631, + "learning_rate": 2.884084404847025e-06, + "loss": 0.7181, + "step": 12371 + }, + { + "epoch": 0.7595076583074987, + "grad_norm": 0.9929104849526189, + "learning_rate": 2.8826875441356016e-06, + "loss": 0.7623, + "step": 12372 + }, + { + "epoch": 0.7595690475459652, + "grad_norm": 1.1156555900486196, + "learning_rate": 2.8812909648096e-06, + "loss": 0.7872, + "step": 12373 + }, + { + "epoch": 0.7596304367844317, + "grad_norm": 0.792603671503129, + "learning_rate": 2.879894666924242e-06, + "loss": 0.7488, + "step": 12374 + }, + { + "epoch": 0.7596918260228982, + "grad_norm": 0.9612988615098775, + "learning_rate": 2.8784986505347302e-06, + "loss": 0.737, + "step": 12375 + }, + { + "epoch": 0.7597532152613646, + "grad_norm": 0.9783130148294925, + "learning_rate": 2.877102915696254e-06, + "loss": 0.7452, + "step": 12376 + }, + { + "epoch": 0.7598146044998312, + "grad_norm": 0.9861797761567641, + "learning_rate": 2.8757074624639958e-06, + "loss": 0.6958, + "step": 12377 + }, + { + "epoch": 0.7598759937382977, + "grad_norm": 0.941514574515971, + "learning_rate": 2.8743122908931243e-06, + "loss": 0.7086, + "step": 12378 + }, + { + "epoch": 0.7599373829767642, + "grad_norm": 0.9594342822490121, + "learning_rate": 2.8729174010387996e-06, + "loss": 0.7704, + "step": 12379 + }, + { + "epoch": 0.7599987722152307, + "grad_norm": 0.9645413173994156, + "learning_rate": 2.8715227929561685e-06, + "loss": 0.7345, + "step": 12380 + }, + { + "epoch": 0.7600601614536971, + "grad_norm": 1.0016044393690313, + "learning_rate": 2.870128466700367e-06, + "loss": 0.7648, + "step": 12381 + }, + { + "epoch": 0.7601215506921637, + "grad_norm": 0.93380978522813, + "learning_rate": 2.86873442232652e-06, + "loss": 0.8333, + "step": 12382 + }, + { + "epoch": 0.7601829399306301, + "grad_norm": 1.0001643402772018, + "learning_rate": 2.8673406598897423e-06, + "loss": 0.7481, + "step": 12383 + }, + { + "epoch": 0.7602443291690967, + "grad_norm": 0.9492044102248799, + "learning_rate": 2.8659471794451345e-06, + "loss": 0.7325, + "step": 12384 + }, + { + "epoch": 0.7603057184075631, + "grad_norm": 0.8012829113141293, + "learning_rate": 2.8645539810477916e-06, + "loss": 0.7116, + "step": 12385 + }, + { + "epoch": 0.7603671076460297, + "grad_norm": 1.1040783612199103, + "learning_rate": 2.8631610647527965e-06, + "loss": 0.7399, + "step": 12386 + }, + { + "epoch": 0.7604284968844961, + "grad_norm": 0.9935492024949374, + "learning_rate": 2.8617684306152092e-06, + "loss": 0.7496, + "step": 12387 + }, + { + "epoch": 0.7604898861229626, + "grad_norm": 0.9928559368767448, + "learning_rate": 2.860376078690097e-06, + "loss": 0.7288, + "step": 12388 + }, + { + "epoch": 0.7605512753614292, + "grad_norm": 1.0238073862320012, + "learning_rate": 2.8589840090325028e-06, + "loss": 0.7843, + "step": 12389 + }, + { + "epoch": 0.7606126645998956, + "grad_norm": 0.9436557187465585, + "learning_rate": 2.857592221697465e-06, + "loss": 0.7191, + "step": 12390 + }, + { + "epoch": 0.7606740538383622, + "grad_norm": 1.0765537393422253, + "learning_rate": 2.8562007167400064e-06, + "loss": 0.8099, + "step": 12391 + }, + { + "epoch": 0.7607354430768286, + "grad_norm": 0.9594872382212712, + "learning_rate": 2.8548094942151405e-06, + "loss": 0.7388, + "step": 12392 + }, + { + "epoch": 0.7607968323152952, + "grad_norm": 0.9017572140701408, + "learning_rate": 2.8534185541778712e-06, + "loss": 0.7181, + "step": 12393 + }, + { + "epoch": 0.7608582215537616, + "grad_norm": 1.0254177028031985, + "learning_rate": 2.8520278966831883e-06, + "loss": 0.7781, + "step": 12394 + }, + { + "epoch": 0.7609196107922281, + "grad_norm": 1.0790629806533556, + "learning_rate": 2.8506375217860706e-06, + "loss": 0.7727, + "step": 12395 + }, + { + "epoch": 0.7609810000306946, + "grad_norm": 1.0662767998641671, + "learning_rate": 2.849247429541494e-06, + "loss": 0.8092, + "step": 12396 + }, + { + "epoch": 0.7610423892691611, + "grad_norm": 1.0735382066081114, + "learning_rate": 2.8478576200044095e-06, + "loss": 0.7313, + "step": 12397 + }, + { + "epoch": 0.7611037785076276, + "grad_norm": 1.0667691431684294, + "learning_rate": 2.8464680932297627e-06, + "loss": 0.722, + "step": 12398 + }, + { + "epoch": 0.7611651677460941, + "grad_norm": 0.9115709052625787, + "learning_rate": 2.8450788492724946e-06, + "loss": 0.7977, + "step": 12399 + }, + { + "epoch": 0.7612265569845607, + "grad_norm": 0.9666767791121355, + "learning_rate": 2.8436898881875265e-06, + "loss": 0.6809, + "step": 12400 + }, + { + "epoch": 0.7612879462230271, + "grad_norm": 0.8991059611598484, + "learning_rate": 2.842301210029772e-06, + "loss": 0.799, + "step": 12401 + }, + { + "epoch": 0.7613493354614936, + "grad_norm": 1.172285100263101, + "learning_rate": 2.8409128148541322e-06, + "loss": 0.7951, + "step": 12402 + }, + { + "epoch": 0.7614107246999601, + "grad_norm": 1.02815669268329, + "learning_rate": 2.8395247027154994e-06, + "loss": 0.7556, + "step": 12403 + }, + { + "epoch": 0.7614721139384266, + "grad_norm": 0.9701034974768261, + "learning_rate": 2.838136873668751e-06, + "loss": 0.7008, + "step": 12404 + }, + { + "epoch": 0.7615335031768931, + "grad_norm": 0.8802485298597438, + "learning_rate": 2.8367493277687576e-06, + "loss": 0.728, + "step": 12405 + }, + { + "epoch": 0.7615948924153596, + "grad_norm": 0.9841296733069653, + "learning_rate": 2.835362065070374e-06, + "loss": 0.7519, + "step": 12406 + }, + { + "epoch": 0.761656281653826, + "grad_norm": 1.0315844365125437, + "learning_rate": 2.8339750856284464e-06, + "loss": 0.8004, + "step": 12407 + }, + { + "epoch": 0.7617176708922926, + "grad_norm": 1.061740782468289, + "learning_rate": 2.832588389497812e-06, + "loss": 0.8086, + "step": 12408 + }, + { + "epoch": 0.761779060130759, + "grad_norm": 1.014130801432635, + "learning_rate": 2.8312019767332888e-06, + "loss": 0.7629, + "step": 12409 + }, + { + "epoch": 0.7618404493692256, + "grad_norm": 0.5640980809404907, + "learning_rate": 2.8298158473896953e-06, + "loss": 0.6047, + "step": 12410 + }, + { + "epoch": 0.7619018386076921, + "grad_norm": 0.9858018491841142, + "learning_rate": 2.8284300015218347e-06, + "loss": 0.7327, + "step": 12411 + }, + { + "epoch": 0.7619632278461586, + "grad_norm": 1.0299697702366097, + "learning_rate": 2.827044439184485e-06, + "loss": 0.7985, + "step": 12412 + }, + { + "epoch": 0.7620246170846251, + "grad_norm": 1.062297974960552, + "learning_rate": 2.8256591604324357e-06, + "loss": 0.7398, + "step": 12413 + }, + { + "epoch": 0.7620860063230915, + "grad_norm": 0.970093853003359, + "learning_rate": 2.8242741653204508e-06, + "loss": 0.7053, + "step": 12414 + }, + { + "epoch": 0.7621473955615581, + "grad_norm": 1.0016233070909366, + "learning_rate": 2.822889453903287e-06, + "loss": 0.742, + "step": 12415 + }, + { + "epoch": 0.7622087848000245, + "grad_norm": 1.0483258133687827, + "learning_rate": 2.821505026235688e-06, + "loss": 0.7248, + "step": 12416 + }, + { + "epoch": 0.7622701740384911, + "grad_norm": 1.0029123681927576, + "learning_rate": 2.820120882372389e-06, + "loss": 0.7424, + "step": 12417 + }, + { + "epoch": 0.7623315632769575, + "grad_norm": 0.9162472459846625, + "learning_rate": 2.8187370223681134e-06, + "loss": 0.7898, + "step": 12418 + }, + { + "epoch": 0.762392952515424, + "grad_norm": 1.1128032887012034, + "learning_rate": 2.81735344627757e-06, + "loss": 0.7895, + "step": 12419 + }, + { + "epoch": 0.7624543417538906, + "grad_norm": 0.8557775128092072, + "learning_rate": 2.8159701541554587e-06, + "loss": 0.7665, + "step": 12420 + }, + { + "epoch": 0.762515730992357, + "grad_norm": 0.9029913780785519, + "learning_rate": 2.8145871460564745e-06, + "loss": 0.7241, + "step": 12421 + }, + { + "epoch": 0.7625771202308236, + "grad_norm": 0.8955854903454842, + "learning_rate": 2.8132044220352884e-06, + "loss": 0.7648, + "step": 12422 + }, + { + "epoch": 0.76263850946929, + "grad_norm": 1.0165332281145176, + "learning_rate": 2.8118219821465666e-06, + "loss": 0.7407, + "step": 12423 + }, + { + "epoch": 0.7626998987077566, + "grad_norm": 0.9449555607194516, + "learning_rate": 2.8104398264449693e-06, + "loss": 0.7181, + "step": 12424 + }, + { + "epoch": 0.762761287946223, + "grad_norm": 0.9314816439946427, + "learning_rate": 2.8090579549851384e-06, + "loss": 0.7685, + "step": 12425 + }, + { + "epoch": 0.7628226771846895, + "grad_norm": 0.9558667429734744, + "learning_rate": 2.807676367821707e-06, + "loss": 0.737, + "step": 12426 + }, + { + "epoch": 0.762884066423156, + "grad_norm": 0.9426699486664045, + "learning_rate": 2.8062950650092944e-06, + "loss": 0.7596, + "step": 12427 + }, + { + "epoch": 0.7629454556616225, + "grad_norm": 1.0132513025560272, + "learning_rate": 2.804914046602514e-06, + "loss": 0.7758, + "step": 12428 + }, + { + "epoch": 0.763006844900089, + "grad_norm": 1.0254209696641705, + "learning_rate": 2.8035333126559627e-06, + "loss": 0.7998, + "step": 12429 + }, + { + "epoch": 0.7630682341385555, + "grad_norm": 1.035461996809843, + "learning_rate": 2.802152863224227e-06, + "loss": 0.7465, + "step": 12430 + }, + { + "epoch": 0.7631296233770221, + "grad_norm": 0.952248616059993, + "learning_rate": 2.80077269836189e-06, + "loss": 0.7818, + "step": 12431 + }, + { + "epoch": 0.7631910126154885, + "grad_norm": 0.9487109004060976, + "learning_rate": 2.7993928181235095e-06, + "loss": 0.7863, + "step": 12432 + }, + { + "epoch": 0.763252401853955, + "grad_norm": 0.9716602479289043, + "learning_rate": 2.7980132225636437e-06, + "loss": 0.8049, + "step": 12433 + }, + { + "epoch": 0.7633137910924215, + "grad_norm": 1.0033515702662001, + "learning_rate": 2.79663391173683e-06, + "loss": 0.7546, + "step": 12434 + }, + { + "epoch": 0.763375180330888, + "grad_norm": 0.9428778001025775, + "learning_rate": 2.795254885697608e-06, + "loss": 0.7471, + "step": 12435 + }, + { + "epoch": 0.7634365695693545, + "grad_norm": 1.0333364113695347, + "learning_rate": 2.793876144500497e-06, + "loss": 0.7285, + "step": 12436 + }, + { + "epoch": 0.763497958807821, + "grad_norm": 1.0282807580035682, + "learning_rate": 2.7924976881999955e-06, + "loss": 0.7278, + "step": 12437 + }, + { + "epoch": 0.7635593480462874, + "grad_norm": 0.9122772723159738, + "learning_rate": 2.7911195168506133e-06, + "loss": 0.7573, + "step": 12438 + }, + { + "epoch": 0.763620737284754, + "grad_norm": 0.9499342008740775, + "learning_rate": 2.7897416305068325e-06, + "loss": 0.7117, + "step": 12439 + }, + { + "epoch": 0.7636821265232204, + "grad_norm": 0.9794788213378216, + "learning_rate": 2.7883640292231272e-06, + "loss": 0.7494, + "step": 12440 + }, + { + "epoch": 0.763743515761687, + "grad_norm": 0.971547429578804, + "learning_rate": 2.786986713053963e-06, + "loss": 0.7728, + "step": 12441 + }, + { + "epoch": 0.7638049050001535, + "grad_norm": 1.0502892914335094, + "learning_rate": 2.7856096820537915e-06, + "loss": 0.7548, + "step": 12442 + }, + { + "epoch": 0.76386629423862, + "grad_norm": 1.0406737422114833, + "learning_rate": 2.7842329362770547e-06, + "loss": 0.7597, + "step": 12443 + }, + { + "epoch": 0.7639276834770865, + "grad_norm": 0.936032239002887, + "learning_rate": 2.782856475778183e-06, + "loss": 0.7609, + "step": 12444 + }, + { + "epoch": 0.7639890727155529, + "grad_norm": 0.9425611284452392, + "learning_rate": 2.7814803006115956e-06, + "loss": 0.7345, + "step": 12445 + }, + { + "epoch": 0.7640504619540195, + "grad_norm": 0.8409289646811798, + "learning_rate": 2.780104410831698e-06, + "loss": 0.7503, + "step": 12446 + }, + { + "epoch": 0.7641118511924859, + "grad_norm": 1.0547827025994247, + "learning_rate": 2.7787288064928875e-06, + "loss": 0.8275, + "step": 12447 + }, + { + "epoch": 0.7641732404309525, + "grad_norm": 0.9495296753599293, + "learning_rate": 2.7773534876495466e-06, + "loss": 0.7667, + "step": 12448 + }, + { + "epoch": 0.7642346296694189, + "grad_norm": 0.9993498221765588, + "learning_rate": 2.775978454356055e-06, + "loss": 0.7466, + "step": 12449 + }, + { + "epoch": 0.7642960189078855, + "grad_norm": 0.9563349862456156, + "learning_rate": 2.774603706666775e-06, + "loss": 0.7681, + "step": 12450 + }, + { + "epoch": 0.7643574081463519, + "grad_norm": 1.032857165945474, + "learning_rate": 2.7732292446360487e-06, + "loss": 0.7396, + "step": 12451 + }, + { + "epoch": 0.7644187973848184, + "grad_norm": 1.064465182868989, + "learning_rate": 2.7718550683182245e-06, + "loss": 0.738, + "step": 12452 + }, + { + "epoch": 0.764480186623285, + "grad_norm": 1.0023106112454183, + "learning_rate": 2.770481177767629e-06, + "loss": 0.7282, + "step": 12453 + }, + { + "epoch": 0.7645415758617514, + "grad_norm": 0.9645275138347694, + "learning_rate": 2.7691075730385774e-06, + "loss": 0.7889, + "step": 12454 + }, + { + "epoch": 0.764602965100218, + "grad_norm": 0.9986150961596947, + "learning_rate": 2.767734254185378e-06, + "loss": 0.7133, + "step": 12455 + }, + { + "epoch": 0.7646643543386844, + "grad_norm": 0.9609627193652349, + "learning_rate": 2.7663612212623237e-06, + "loss": 0.7565, + "step": 12456 + }, + { + "epoch": 0.764725743577151, + "grad_norm": 1.0960028563513158, + "learning_rate": 2.7649884743236997e-06, + "loss": 0.7557, + "step": 12457 + }, + { + "epoch": 0.7647871328156174, + "grad_norm": 0.9183157586813192, + "learning_rate": 2.7636160134237753e-06, + "loss": 0.7417, + "step": 12458 + }, + { + "epoch": 0.7648485220540839, + "grad_norm": 1.0503300008392482, + "learning_rate": 2.7622438386168115e-06, + "loss": 0.7998, + "step": 12459 + }, + { + "epoch": 0.7649099112925504, + "grad_norm": 1.060625797808571, + "learning_rate": 2.7608719499570637e-06, + "loss": 0.7145, + "step": 12460 + }, + { + "epoch": 0.7649713005310169, + "grad_norm": 0.981074040850596, + "learning_rate": 2.7595003474987623e-06, + "loss": 0.7522, + "step": 12461 + }, + { + "epoch": 0.7650326897694835, + "grad_norm": 0.8964831839822531, + "learning_rate": 2.758129031296135e-06, + "loss": 0.7614, + "step": 12462 + }, + { + "epoch": 0.7650940790079499, + "grad_norm": 0.9915435444135138, + "learning_rate": 2.7567580014034024e-06, + "loss": 0.7827, + "step": 12463 + }, + { + "epoch": 0.7651554682464164, + "grad_norm": 0.9582891741061126, + "learning_rate": 2.755387257874764e-06, + "loss": 0.7241, + "step": 12464 + }, + { + "epoch": 0.7652168574848829, + "grad_norm": 0.8811718633797337, + "learning_rate": 2.7540168007644152e-06, + "loss": 0.7032, + "step": 12465 + }, + { + "epoch": 0.7652782467233494, + "grad_norm": 1.010402370035662, + "learning_rate": 2.7526466301265375e-06, + "loss": 0.7237, + "step": 12466 + }, + { + "epoch": 0.7653396359618159, + "grad_norm": 0.5554672338990756, + "learning_rate": 2.751276746015299e-06, + "loss": 0.6162, + "step": 12467 + }, + { + "epoch": 0.7654010252002824, + "grad_norm": 0.9606959381586654, + "learning_rate": 2.7499071484848593e-06, + "loss": 0.7973, + "step": 12468 + }, + { + "epoch": 0.7654624144387489, + "grad_norm": 0.9716753187442397, + "learning_rate": 2.7485378375893634e-06, + "loss": 0.7513, + "step": 12469 + }, + { + "epoch": 0.7655238036772154, + "grad_norm": 1.0134634819399249, + "learning_rate": 2.7471688133829576e-06, + "loss": 0.7217, + "step": 12470 + }, + { + "epoch": 0.7655851929156818, + "grad_norm": 0.9590422455024185, + "learning_rate": 2.745800075919756e-06, + "loss": 0.7019, + "step": 12471 + }, + { + "epoch": 0.7656465821541484, + "grad_norm": 0.9836863838101059, + "learning_rate": 2.7444316252538738e-06, + "loss": 0.7709, + "step": 12472 + }, + { + "epoch": 0.7657079713926149, + "grad_norm": 1.0773455431155472, + "learning_rate": 2.7430634614394135e-06, + "loss": 0.6821, + "step": 12473 + }, + { + "epoch": 0.7657693606310814, + "grad_norm": 0.970742126183311, + "learning_rate": 2.7416955845304705e-06, + "loss": 0.741, + "step": 12474 + }, + { + "epoch": 0.7658307498695479, + "grad_norm": 1.0016180768677982, + "learning_rate": 2.7403279945811234e-06, + "loss": 0.7451, + "step": 12475 + }, + { + "epoch": 0.7658921391080143, + "grad_norm": 1.0115522000661294, + "learning_rate": 2.7389606916454325e-06, + "loss": 0.76, + "step": 12476 + }, + { + "epoch": 0.7659535283464809, + "grad_norm": 1.0431055276512555, + "learning_rate": 2.7375936757774635e-06, + "loss": 0.7581, + "step": 12477 + }, + { + "epoch": 0.7660149175849473, + "grad_norm": 0.8584009407000573, + "learning_rate": 2.7362269470312587e-06, + "loss": 0.7297, + "step": 12478 + }, + { + "epoch": 0.7660763068234139, + "grad_norm": 0.9711611998308907, + "learning_rate": 2.734860505460851e-06, + "loss": 0.7345, + "step": 12479 + }, + { + "epoch": 0.7661376960618803, + "grad_norm": 0.9779557003217648, + "learning_rate": 2.733494351120265e-06, + "loss": 0.7826, + "step": 12480 + }, + { + "epoch": 0.7661990853003469, + "grad_norm": 0.5883109784998166, + "learning_rate": 2.732128484063512e-06, + "loss": 0.6292, + "step": 12481 + }, + { + "epoch": 0.7662604745388133, + "grad_norm": 0.9134014982100019, + "learning_rate": 2.7307629043445907e-06, + "loss": 0.7315, + "step": 12482 + }, + { + "epoch": 0.7663218637772798, + "grad_norm": 0.9568575505589394, + "learning_rate": 2.7293976120174903e-06, + "loss": 0.7153, + "step": 12483 + }, + { + "epoch": 0.7663832530157464, + "grad_norm": 1.0815272300544263, + "learning_rate": 2.7280326071361853e-06, + "loss": 0.7084, + "step": 12484 + }, + { + "epoch": 0.7664446422542128, + "grad_norm": 1.016421461536005, + "learning_rate": 2.7266678897546504e-06, + "loss": 0.7577, + "step": 12485 + }, + { + "epoch": 0.7665060314926794, + "grad_norm": 0.9935545386815309, + "learning_rate": 2.7253034599268314e-06, + "loss": 0.7382, + "step": 12486 + }, + { + "epoch": 0.7665674207311458, + "grad_norm": 1.0449028349621923, + "learning_rate": 2.7239393177066708e-06, + "loss": 0.7818, + "step": 12487 + }, + { + "epoch": 0.7666288099696124, + "grad_norm": 1.1052927889589086, + "learning_rate": 2.7225754631481084e-06, + "loss": 0.7527, + "step": 12488 + }, + { + "epoch": 0.7666901992080788, + "grad_norm": 1.0747968349863928, + "learning_rate": 2.721211896305059e-06, + "loss": 0.7251, + "step": 12489 + }, + { + "epoch": 0.7667515884465453, + "grad_norm": 1.0395049407009913, + "learning_rate": 2.7198486172314342e-06, + "loss": 0.7812, + "step": 12490 + }, + { + "epoch": 0.7668129776850118, + "grad_norm": 0.9119437810666433, + "learning_rate": 2.71848562598113e-06, + "loss": 0.751, + "step": 12491 + }, + { + "epoch": 0.7668743669234783, + "grad_norm": 1.0115980942830514, + "learning_rate": 2.717122922608033e-06, + "loss": 0.7789, + "step": 12492 + }, + { + "epoch": 0.7669357561619448, + "grad_norm": 0.5805917685194878, + "learning_rate": 2.7157605071660188e-06, + "loss": 0.6529, + "step": 12493 + }, + { + "epoch": 0.7669971454004113, + "grad_norm": 0.8204267416637807, + "learning_rate": 2.714398379708948e-06, + "loss": 0.7259, + "step": 12494 + }, + { + "epoch": 0.7670585346388779, + "grad_norm": 1.0036280926008758, + "learning_rate": 2.713036540290681e-06, + "loss": 0.7677, + "step": 12495 + }, + { + "epoch": 0.7671199238773443, + "grad_norm": 0.9344963589772225, + "learning_rate": 2.7116749889650498e-06, + "loss": 0.7058, + "step": 12496 + }, + { + "epoch": 0.7671813131158108, + "grad_norm": 0.8696178205671645, + "learning_rate": 2.7103137257858867e-06, + "loss": 0.7403, + "step": 12497 + }, + { + "epoch": 0.7672427023542773, + "grad_norm": 0.9822538851983337, + "learning_rate": 2.708952750807008e-06, + "loss": 0.7525, + "step": 12498 + }, + { + "epoch": 0.7673040915927438, + "grad_norm": 0.8847786540630774, + "learning_rate": 2.707592064082224e-06, + "loss": 0.7342, + "step": 12499 + }, + { + "epoch": 0.7673654808312103, + "grad_norm": 1.1162390138831861, + "learning_rate": 2.706231665665332e-06, + "loss": 0.7904, + "step": 12500 + }, + { + "epoch": 0.7674268700696768, + "grad_norm": 1.0836607326130467, + "learning_rate": 2.704871555610107e-06, + "loss": 0.7653, + "step": 12501 + }, + { + "epoch": 0.7674882593081432, + "grad_norm": 1.064003144864705, + "learning_rate": 2.7035117339703276e-06, + "loss": 0.8202, + "step": 12502 + }, + { + "epoch": 0.7675496485466098, + "grad_norm": 0.9572570969611915, + "learning_rate": 2.7021522007997545e-06, + "loss": 0.6693, + "step": 12503 + }, + { + "epoch": 0.7676110377850762, + "grad_norm": 0.9411948059986358, + "learning_rate": 2.700792956152137e-06, + "loss": 0.7079, + "step": 12504 + }, + { + "epoch": 0.7676724270235428, + "grad_norm": 1.1151115097194033, + "learning_rate": 2.6994340000812123e-06, + "loss": 0.7534, + "step": 12505 + }, + { + "epoch": 0.7677338162620093, + "grad_norm": 1.0473976536907077, + "learning_rate": 2.6980753326407084e-06, + "loss": 0.7592, + "step": 12506 + }, + { + "epoch": 0.7677952055004758, + "grad_norm": 0.8368543474449823, + "learning_rate": 2.6967169538843396e-06, + "loss": 0.751, + "step": 12507 + }, + { + "epoch": 0.7678565947389423, + "grad_norm": 0.9685400498800225, + "learning_rate": 2.695358863865808e-06, + "loss": 0.7607, + "step": 12508 + }, + { + "epoch": 0.7679179839774087, + "grad_norm": 0.8866281627909051, + "learning_rate": 2.6940010626388134e-06, + "loss": 0.7771, + "step": 12509 + }, + { + "epoch": 0.7679793732158753, + "grad_norm": 0.9560286742477653, + "learning_rate": 2.6926435502570293e-06, + "loss": 0.7378, + "step": 12510 + }, + { + "epoch": 0.7680407624543417, + "grad_norm": 1.0201989151345774, + "learning_rate": 2.6912863267741285e-06, + "loss": 0.7461, + "step": 12511 + }, + { + "epoch": 0.7681021516928083, + "grad_norm": 0.9099215797002751, + "learning_rate": 2.6899293922437652e-06, + "loss": 0.6963, + "step": 12512 + }, + { + "epoch": 0.7681635409312747, + "grad_norm": 1.0140177679097182, + "learning_rate": 2.6885727467195943e-06, + "loss": 0.7319, + "step": 12513 + }, + { + "epoch": 0.7682249301697412, + "grad_norm": 0.9435858824867432, + "learning_rate": 2.6872163902552494e-06, + "loss": 0.7877, + "step": 12514 + }, + { + "epoch": 0.7682863194082078, + "grad_norm": 0.5642213910625865, + "learning_rate": 2.6858603229043456e-06, + "loss": 0.6713, + "step": 12515 + }, + { + "epoch": 0.7683477086466742, + "grad_norm": 0.9996079604497384, + "learning_rate": 2.6845045447205056e-06, + "loss": 0.7459, + "step": 12516 + }, + { + "epoch": 0.7684090978851408, + "grad_norm": 0.9054949336176018, + "learning_rate": 2.683149055757327e-06, + "loss": 0.7196, + "step": 12517 + }, + { + "epoch": 0.7684704871236072, + "grad_norm": 1.0441672718303434, + "learning_rate": 2.681793856068399e-06, + "loss": 0.7811, + "step": 12518 + }, + { + "epoch": 0.7685318763620738, + "grad_norm": 1.0622278563445744, + "learning_rate": 2.680438945707301e-06, + "loss": 0.7795, + "step": 12519 + }, + { + "epoch": 0.7685932656005402, + "grad_norm": 0.9689563964995813, + "learning_rate": 2.679084324727599e-06, + "loss": 0.7179, + "step": 12520 + }, + { + "epoch": 0.7686546548390067, + "grad_norm": 1.0155054780066386, + "learning_rate": 2.6777299931828482e-06, + "loss": 0.7451, + "step": 12521 + }, + { + "epoch": 0.7687160440774732, + "grad_norm": 1.0387155071053527, + "learning_rate": 2.676375951126593e-06, + "loss": 0.7569, + "step": 12522 + }, + { + "epoch": 0.7687774333159397, + "grad_norm": 0.9748788329085564, + "learning_rate": 2.675022198612364e-06, + "loss": 0.7614, + "step": 12523 + }, + { + "epoch": 0.7688388225544062, + "grad_norm": 1.0155016314113439, + "learning_rate": 2.6736687356936888e-06, + "loss": 0.7385, + "step": 12524 + }, + { + "epoch": 0.7689002117928727, + "grad_norm": 0.9233200248869935, + "learning_rate": 2.6723155624240706e-06, + "loss": 0.6964, + "step": 12525 + }, + { + "epoch": 0.7689616010313393, + "grad_norm": 1.009732948855654, + "learning_rate": 2.6709626788570053e-06, + "loss": 0.7149, + "step": 12526 + }, + { + "epoch": 0.7690229902698057, + "grad_norm": 0.9760321332254489, + "learning_rate": 2.6696100850459883e-06, + "loss": 0.7094, + "step": 12527 + }, + { + "epoch": 0.7690843795082722, + "grad_norm": 1.0932851498823695, + "learning_rate": 2.6682577810444887e-06, + "loss": 0.7299, + "step": 12528 + }, + { + "epoch": 0.7691457687467387, + "grad_norm": 1.0855805960755465, + "learning_rate": 2.6669057669059727e-06, + "loss": 0.7679, + "step": 12529 + }, + { + "epoch": 0.7692071579852052, + "grad_norm": 1.0246658079152011, + "learning_rate": 2.665554042683892e-06, + "loss": 0.7324, + "step": 12530 + }, + { + "epoch": 0.7692685472236717, + "grad_norm": 0.9466481788185632, + "learning_rate": 2.6642026084316874e-06, + "loss": 0.7225, + "step": 12531 + }, + { + "epoch": 0.7693299364621382, + "grad_norm": 1.1074232751326514, + "learning_rate": 2.6628514642027882e-06, + "loss": 0.745, + "step": 12532 + }, + { + "epoch": 0.7693913257006046, + "grad_norm": 0.9922436702665131, + "learning_rate": 2.661500610050609e-06, + "loss": 0.7831, + "step": 12533 + }, + { + "epoch": 0.7694527149390712, + "grad_norm": 1.0300300878968442, + "learning_rate": 2.660150046028567e-06, + "loss": 0.7256, + "step": 12534 + }, + { + "epoch": 0.7695141041775376, + "grad_norm": 0.8750526677639425, + "learning_rate": 2.658799772190046e-06, + "loss": 0.6997, + "step": 12535 + }, + { + "epoch": 0.7695754934160042, + "grad_norm": 0.9656277425110735, + "learning_rate": 2.6574497885884333e-06, + "loss": 0.7259, + "step": 12536 + }, + { + "epoch": 0.7696368826544707, + "grad_norm": 1.0153227609776727, + "learning_rate": 2.6561000952770987e-06, + "loss": 0.7191, + "step": 12537 + }, + { + "epoch": 0.7696982718929372, + "grad_norm": 1.144454392434127, + "learning_rate": 2.654750692309408e-06, + "loss": 0.7645, + "step": 12538 + }, + { + "epoch": 0.7697596611314037, + "grad_norm": 0.9902122461211466, + "learning_rate": 2.6534015797387103e-06, + "loss": 0.7203, + "step": 12539 + }, + { + "epoch": 0.7698210503698701, + "grad_norm": 1.0308604763556686, + "learning_rate": 2.6520527576183354e-06, + "loss": 0.7407, + "step": 12540 + }, + { + "epoch": 0.7698824396083367, + "grad_norm": 0.9969061538043358, + "learning_rate": 2.6507042260016167e-06, + "loss": 0.7323, + "step": 12541 + }, + { + "epoch": 0.7699438288468031, + "grad_norm": 0.8987472918451664, + "learning_rate": 2.649355984941867e-06, + "loss": 0.7557, + "step": 12542 + }, + { + "epoch": 0.7700052180852697, + "grad_norm": 0.9370167775464409, + "learning_rate": 2.6480080344923896e-06, + "loss": 0.7875, + "step": 12543 + }, + { + "epoch": 0.7700666073237361, + "grad_norm": 1.070789001252731, + "learning_rate": 2.6466603747064755e-06, + "loss": 0.757, + "step": 12544 + }, + { + "epoch": 0.7701279965622027, + "grad_norm": 1.0969771496051008, + "learning_rate": 2.6453130056374054e-06, + "loss": 0.7552, + "step": 12545 + }, + { + "epoch": 0.7701893858006691, + "grad_norm": 0.9133450619380086, + "learning_rate": 2.643965927338448e-06, + "loss": 0.7614, + "step": 12546 + }, + { + "epoch": 0.7702507750391356, + "grad_norm": 0.9818965889086574, + "learning_rate": 2.6426191398628564e-06, + "loss": 0.7063, + "step": 12547 + }, + { + "epoch": 0.7703121642776022, + "grad_norm": 1.0458559369090936, + "learning_rate": 2.6412726432638834e-06, + "loss": 0.7543, + "step": 12548 + }, + { + "epoch": 0.7703735535160686, + "grad_norm": 1.0416887348834039, + "learning_rate": 2.6399264375947632e-06, + "loss": 0.7753, + "step": 12549 + }, + { + "epoch": 0.7704349427545352, + "grad_norm": 0.9338537326214363, + "learning_rate": 2.6385805229087138e-06, + "loss": 0.7758, + "step": 12550 + }, + { + "epoch": 0.7704963319930016, + "grad_norm": 1.0792432155295502, + "learning_rate": 2.6372348992589426e-06, + "loss": 0.7675, + "step": 12551 + }, + { + "epoch": 0.7705577212314682, + "grad_norm": 1.043168472851846, + "learning_rate": 2.6358895666986596e-06, + "loss": 0.7056, + "step": 12552 + }, + { + "epoch": 0.7706191104699346, + "grad_norm": 1.0162535021610677, + "learning_rate": 2.6345445252810476e-06, + "loss": 0.7103, + "step": 12553 + }, + { + "epoch": 0.7706804997084011, + "grad_norm": 1.0095483827860723, + "learning_rate": 2.633199775059283e-06, + "loss": 0.7797, + "step": 12554 + }, + { + "epoch": 0.7707418889468676, + "grad_norm": 0.9742641652879762, + "learning_rate": 2.6318553160865323e-06, + "loss": 0.7307, + "step": 12555 + }, + { + "epoch": 0.7708032781853341, + "grad_norm": 1.0092835939543225, + "learning_rate": 2.6305111484159485e-06, + "loss": 0.7553, + "step": 12556 + }, + { + "epoch": 0.7708646674238006, + "grad_norm": 0.9075749307338352, + "learning_rate": 2.6291672721006733e-06, + "loss": 0.769, + "step": 12557 + }, + { + "epoch": 0.7709260566622671, + "grad_norm": 0.9831057529467916, + "learning_rate": 2.6278236871938356e-06, + "loss": 0.7753, + "step": 12558 + }, + { + "epoch": 0.7709874459007336, + "grad_norm": 0.894807816067641, + "learning_rate": 2.6264803937485617e-06, + "loss": 0.7495, + "step": 12559 + }, + { + "epoch": 0.7710488351392001, + "grad_norm": 1.1402343418998415, + "learning_rate": 2.6251373918179525e-06, + "loss": 0.793, + "step": 12560 + }, + { + "epoch": 0.7711102243776666, + "grad_norm": 0.9912453844680034, + "learning_rate": 2.623794681455105e-06, + "loss": 0.7026, + "step": 12561 + }, + { + "epoch": 0.7711716136161331, + "grad_norm": 0.9133876195443174, + "learning_rate": 2.622452262713101e-06, + "loss": 0.757, + "step": 12562 + }, + { + "epoch": 0.7712330028545996, + "grad_norm": 0.8664530176944196, + "learning_rate": 2.621110135645021e-06, + "loss": 0.8056, + "step": 12563 + }, + { + "epoch": 0.771294392093066, + "grad_norm": 0.9204110388719496, + "learning_rate": 2.6197683003039253e-06, + "loss": 0.7524, + "step": 12564 + }, + { + "epoch": 0.7713557813315326, + "grad_norm": 0.993121897805211, + "learning_rate": 2.6184267567428545e-06, + "loss": 0.7236, + "step": 12565 + }, + { + "epoch": 0.771417170569999, + "grad_norm": 1.0140537618568595, + "learning_rate": 2.617085505014856e-06, + "loss": 0.717, + "step": 12566 + }, + { + "epoch": 0.7714785598084656, + "grad_norm": 0.9336814200428707, + "learning_rate": 2.6157445451729547e-06, + "loss": 0.6943, + "step": 12567 + }, + { + "epoch": 0.7715399490469321, + "grad_norm": 0.9644472508090913, + "learning_rate": 2.6144038772701653e-06, + "loss": 0.745, + "step": 12568 + }, + { + "epoch": 0.7716013382853986, + "grad_norm": 0.951446122458316, + "learning_rate": 2.613063501359492e-06, + "loss": 0.7591, + "step": 12569 + }, + { + "epoch": 0.7716627275238651, + "grad_norm": 0.6064112805596004, + "learning_rate": 2.6117234174939253e-06, + "loss": 0.6651, + "step": 12570 + }, + { + "epoch": 0.7717241167623315, + "grad_norm": 0.984642867446391, + "learning_rate": 2.6103836257264483e-06, + "loss": 0.718, + "step": 12571 + }, + { + "epoch": 0.7717855060007981, + "grad_norm": 0.9865153594529679, + "learning_rate": 2.609044126110025e-06, + "loss": 0.728, + "step": 12572 + }, + { + "epoch": 0.7718468952392645, + "grad_norm": 0.9849639851884262, + "learning_rate": 2.6077049186976243e-06, + "loss": 0.7771, + "step": 12573 + }, + { + "epoch": 0.7719082844777311, + "grad_norm": 0.9500302666550496, + "learning_rate": 2.6063660035421813e-06, + "loss": 0.7592, + "step": 12574 + }, + { + "epoch": 0.7719696737161975, + "grad_norm": 1.118773628685888, + "learning_rate": 2.605027380696634e-06, + "loss": 0.8178, + "step": 12575 + }, + { + "epoch": 0.7720310629546641, + "grad_norm": 0.9786460652918585, + "learning_rate": 2.603689050213902e-06, + "loss": 0.7425, + "step": 12576 + }, + { + "epoch": 0.7720924521931305, + "grad_norm": 0.9528498333631747, + "learning_rate": 2.6023510121469043e-06, + "loss": 0.7828, + "step": 12577 + }, + { + "epoch": 0.772153841431597, + "grad_norm": 1.0210165282602475, + "learning_rate": 2.6010132665485388e-06, + "loss": 0.8035, + "step": 12578 + }, + { + "epoch": 0.7722152306700636, + "grad_norm": 0.956023089071713, + "learning_rate": 2.599675813471686e-06, + "loss": 0.7229, + "step": 12579 + }, + { + "epoch": 0.77227661990853, + "grad_norm": 0.9805043033975156, + "learning_rate": 2.59833865296923e-06, + "loss": 0.7097, + "step": 12580 + }, + { + "epoch": 0.7723380091469966, + "grad_norm": 1.0186015687096888, + "learning_rate": 2.5970017850940345e-06, + "loss": 0.8074, + "step": 12581 + }, + { + "epoch": 0.772399398385463, + "grad_norm": 1.0640840009268218, + "learning_rate": 2.595665209898952e-06, + "loss": 0.7264, + "step": 12582 + }, + { + "epoch": 0.7724607876239296, + "grad_norm": 1.0522571411196735, + "learning_rate": 2.5943289274368254e-06, + "loss": 0.7901, + "step": 12583 + }, + { + "epoch": 0.772522176862396, + "grad_norm": 0.9908224742332935, + "learning_rate": 2.5929929377604845e-06, + "loss": 0.6884, + "step": 12584 + }, + { + "epoch": 0.7725835661008625, + "grad_norm": 1.052713308410128, + "learning_rate": 2.5916572409227492e-06, + "loss": 0.7846, + "step": 12585 + }, + { + "epoch": 0.772644955339329, + "grad_norm": 1.0210791039988067, + "learning_rate": 2.5903218369764215e-06, + "loss": 0.7523, + "step": 12586 + }, + { + "epoch": 0.7727063445777955, + "grad_norm": 1.0095710721889275, + "learning_rate": 2.588986725974304e-06, + "loss": 0.7271, + "step": 12587 + }, + { + "epoch": 0.772767733816262, + "grad_norm": 0.9646686043079915, + "learning_rate": 2.587651907969182e-06, + "loss": 0.7623, + "step": 12588 + }, + { + "epoch": 0.7728291230547285, + "grad_norm": 1.0561759370930666, + "learning_rate": 2.5863173830138212e-06, + "loss": 0.7499, + "step": 12589 + }, + { + "epoch": 0.772890512293195, + "grad_norm": 1.0349475339398206, + "learning_rate": 2.5849831511609814e-06, + "loss": 0.7599, + "step": 12590 + }, + { + "epoch": 0.7729519015316615, + "grad_norm": 0.986580139857335, + "learning_rate": 2.5836492124634205e-06, + "loss": 0.7069, + "step": 12591 + }, + { + "epoch": 0.773013290770128, + "grad_norm": 0.9685650999644093, + "learning_rate": 2.58231556697387e-06, + "loss": 0.7387, + "step": 12592 + }, + { + "epoch": 0.7730746800085945, + "grad_norm": 0.9005733673910677, + "learning_rate": 2.580982214745059e-06, + "loss": 0.7243, + "step": 12593 + }, + { + "epoch": 0.773136069247061, + "grad_norm": 1.0605210680894475, + "learning_rate": 2.5796491558297e-06, + "loss": 0.7581, + "step": 12594 + }, + { + "epoch": 0.7731974584855275, + "grad_norm": 0.9162876896277697, + "learning_rate": 2.5783163902804966e-06, + "loss": 0.7563, + "step": 12595 + }, + { + "epoch": 0.773258847723994, + "grad_norm": 0.9492567557804726, + "learning_rate": 2.576983918150141e-06, + "loss": 0.7524, + "step": 12596 + }, + { + "epoch": 0.7733202369624604, + "grad_norm": 0.9674460845434084, + "learning_rate": 2.5756517394913085e-06, + "loss": 0.7352, + "step": 12597 + }, + { + "epoch": 0.773381626200927, + "grad_norm": 0.9804101328317659, + "learning_rate": 2.574319854356677e-06, + "loss": 0.7853, + "step": 12598 + }, + { + "epoch": 0.7734430154393934, + "grad_norm": 1.0366759687379765, + "learning_rate": 2.5729882627988945e-06, + "loss": 0.78, + "step": 12599 + }, + { + "epoch": 0.77350440467786, + "grad_norm": 0.9174263855015335, + "learning_rate": 2.571656964870608e-06, + "loss": 0.7406, + "step": 12600 + }, + { + "epoch": 0.7735657939163265, + "grad_norm": 0.9112952489254533, + "learning_rate": 2.570325960624448e-06, + "loss": 0.7762, + "step": 12601 + }, + { + "epoch": 0.773627183154793, + "grad_norm": 0.8951163135419676, + "learning_rate": 2.568995250113043e-06, + "loss": 0.7151, + "step": 12602 + }, + { + "epoch": 0.7736885723932595, + "grad_norm": 1.0384197464112934, + "learning_rate": 2.567664833389003e-06, + "loss": 0.7279, + "step": 12603 + }, + { + "epoch": 0.7737499616317259, + "grad_norm": 0.9678391576144331, + "learning_rate": 2.566334710504916e-06, + "loss": 0.6701, + "step": 12604 + }, + { + "epoch": 0.7738113508701925, + "grad_norm": 1.0556423208303771, + "learning_rate": 2.5650048815133797e-06, + "loss": 0.7197, + "step": 12605 + }, + { + "epoch": 0.7738727401086589, + "grad_norm": 0.8791471417848854, + "learning_rate": 2.563675346466965e-06, + "loss": 0.7696, + "step": 12606 + }, + { + "epoch": 0.7739341293471255, + "grad_norm": 0.9016711484600775, + "learning_rate": 2.5623461054182364e-06, + "loss": 0.7143, + "step": 12607 + }, + { + "epoch": 0.7739955185855919, + "grad_norm": 0.9378113493001812, + "learning_rate": 2.5610171584197454e-06, + "loss": 0.719, + "step": 12608 + }, + { + "epoch": 0.7740569078240584, + "grad_norm": 0.944403086287971, + "learning_rate": 2.559688505524033e-06, + "loss": 0.7355, + "step": 12609 + }, + { + "epoch": 0.7741182970625249, + "grad_norm": 1.0241158413349878, + "learning_rate": 2.558360146783627e-06, + "loss": 0.7307, + "step": 12610 + }, + { + "epoch": 0.7741796863009914, + "grad_norm": 1.026600452565516, + "learning_rate": 2.557032082251043e-06, + "loss": 0.7844, + "step": 12611 + }, + { + "epoch": 0.774241075539458, + "grad_norm": 0.9282588616999481, + "learning_rate": 2.5557043119787906e-06, + "loss": 0.7546, + "step": 12612 + }, + { + "epoch": 0.7743024647779244, + "grad_norm": 1.0255191375950126, + "learning_rate": 2.5543768360193656e-06, + "loss": 0.7097, + "step": 12613 + }, + { + "epoch": 0.774363854016391, + "grad_norm": 1.093720249933161, + "learning_rate": 2.5530496544252426e-06, + "loss": 0.7392, + "step": 12614 + }, + { + "epoch": 0.7744252432548574, + "grad_norm": 1.0402878920367042, + "learning_rate": 2.551722767248893e-06, + "loss": 0.7335, + "step": 12615 + }, + { + "epoch": 0.774486632493324, + "grad_norm": 0.951136181412417, + "learning_rate": 2.5503961745427817e-06, + "loss": 0.7421, + "step": 12616 + }, + { + "epoch": 0.7745480217317904, + "grad_norm": 0.8852801580761958, + "learning_rate": 2.5490698763593523e-06, + "loss": 0.755, + "step": 12617 + }, + { + "epoch": 0.7746094109702569, + "grad_norm": 0.9928020620291339, + "learning_rate": 2.5477438727510418e-06, + "loss": 0.7872, + "step": 12618 + }, + { + "epoch": 0.7746708002087234, + "grad_norm": 0.9450391432469633, + "learning_rate": 2.5464181637702734e-06, + "loss": 0.7442, + "step": 12619 + }, + { + "epoch": 0.7747321894471899, + "grad_norm": 0.9960932932539284, + "learning_rate": 2.545092749469459e-06, + "loss": 0.7388, + "step": 12620 + }, + { + "epoch": 0.7747935786856565, + "grad_norm": 0.9908557507675025, + "learning_rate": 2.5437676299010007e-06, + "loss": 0.778, + "step": 12621 + }, + { + "epoch": 0.7748549679241229, + "grad_norm": 1.0234773819255083, + "learning_rate": 2.5424428051172833e-06, + "loss": 0.7946, + "step": 12622 + }, + { + "epoch": 0.7749163571625894, + "grad_norm": 0.9522353704304876, + "learning_rate": 2.5411182751706933e-06, + "loss": 0.6913, + "step": 12623 + }, + { + "epoch": 0.7749777464010559, + "grad_norm": 0.9621832774934068, + "learning_rate": 2.5397940401135878e-06, + "loss": 0.7462, + "step": 12624 + }, + { + "epoch": 0.7750391356395224, + "grad_norm": 1.0241570271103333, + "learning_rate": 2.538470099998325e-06, + "loss": 0.7564, + "step": 12625 + }, + { + "epoch": 0.7751005248779889, + "grad_norm": 0.8536915963279945, + "learning_rate": 2.537146454877242e-06, + "loss": 0.702, + "step": 12626 + }, + { + "epoch": 0.7751619141164554, + "grad_norm": 0.8956638426416624, + "learning_rate": 2.535823104802677e-06, + "loss": 0.7385, + "step": 12627 + }, + { + "epoch": 0.7752233033549218, + "grad_norm": 1.088757355997269, + "learning_rate": 2.534500049826949e-06, + "loss": 0.8011, + "step": 12628 + }, + { + "epoch": 0.7752846925933884, + "grad_norm": 0.9781802492004819, + "learning_rate": 2.5331772900023566e-06, + "loss": 0.7513, + "step": 12629 + }, + { + "epoch": 0.7753460818318548, + "grad_norm": 1.0321405539159219, + "learning_rate": 2.5318548253812036e-06, + "loss": 0.7306, + "step": 12630 + }, + { + "epoch": 0.7754074710703214, + "grad_norm": 1.0227942981914417, + "learning_rate": 2.5305326560157726e-06, + "loss": 0.7336, + "step": 12631 + }, + { + "epoch": 0.7754688603087879, + "grad_norm": 0.9096771369170082, + "learning_rate": 2.5292107819583347e-06, + "loss": 0.7469, + "step": 12632 + }, + { + "epoch": 0.7755302495472544, + "grad_norm": 1.1145429402072264, + "learning_rate": 2.527889203261151e-06, + "loss": 0.7834, + "step": 12633 + }, + { + "epoch": 0.7755916387857209, + "grad_norm": 0.9419556341469036, + "learning_rate": 2.5265679199764713e-06, + "loss": 0.7412, + "step": 12634 + }, + { + "epoch": 0.7756530280241873, + "grad_norm": 1.0478293337538926, + "learning_rate": 2.525246932156532e-06, + "loss": 0.7512, + "step": 12635 + }, + { + "epoch": 0.7757144172626539, + "grad_norm": 0.9404681624148407, + "learning_rate": 2.523926239853557e-06, + "loss": 0.7545, + "step": 12636 + }, + { + "epoch": 0.7757758065011203, + "grad_norm": 1.0866069343438756, + "learning_rate": 2.5226058431197674e-06, + "loss": 0.8437, + "step": 12637 + }, + { + "epoch": 0.7758371957395869, + "grad_norm": 0.9486655671088002, + "learning_rate": 2.521285742007359e-06, + "loss": 0.7464, + "step": 12638 + }, + { + "epoch": 0.7758985849780533, + "grad_norm": 0.9805664787293716, + "learning_rate": 2.5199659365685235e-06, + "loss": 0.7118, + "step": 12639 + }, + { + "epoch": 0.7759599742165199, + "grad_norm": 0.9957186765700108, + "learning_rate": 2.5186464268554376e-06, + "loss": 0.7489, + "step": 12640 + }, + { + "epoch": 0.7760213634549863, + "grad_norm": 1.0349929134770646, + "learning_rate": 2.517327212920275e-06, + "loss": 0.7306, + "step": 12641 + }, + { + "epoch": 0.7760827526934528, + "grad_norm": 0.993834914471383, + "learning_rate": 2.516008294815191e-06, + "loss": 0.76, + "step": 12642 + }, + { + "epoch": 0.7761441419319194, + "grad_norm": 0.9652079613283001, + "learning_rate": 2.5146896725923196e-06, + "loss": 0.7695, + "step": 12643 + }, + { + "epoch": 0.7762055311703858, + "grad_norm": 0.9034096741086659, + "learning_rate": 2.5133713463038023e-06, + "loss": 0.7265, + "step": 12644 + }, + { + "epoch": 0.7762669204088524, + "grad_norm": 0.9354645786834925, + "learning_rate": 2.512053316001758e-06, + "loss": 0.7872, + "step": 12645 + }, + { + "epoch": 0.7763283096473188, + "grad_norm": 0.9080916091246163, + "learning_rate": 2.510735581738294e-06, + "loss": 0.7725, + "step": 12646 + }, + { + "epoch": 0.7763896988857854, + "grad_norm": 0.9146568133019712, + "learning_rate": 2.5094181435655075e-06, + "loss": 0.7628, + "step": 12647 + }, + { + "epoch": 0.7764510881242518, + "grad_norm": 0.9016880610382999, + "learning_rate": 2.5081010015354844e-06, + "loss": 0.7189, + "step": 12648 + }, + { + "epoch": 0.7765124773627183, + "grad_norm": 0.8904982546223278, + "learning_rate": 2.5067841557002994e-06, + "loss": 0.7547, + "step": 12649 + }, + { + "epoch": 0.7765738666011848, + "grad_norm": 0.9862714609591997, + "learning_rate": 2.5054676061120087e-06, + "loss": 0.7492, + "step": 12650 + }, + { + "epoch": 0.7766352558396513, + "grad_norm": 0.9453565276298395, + "learning_rate": 2.5041513528226712e-06, + "loss": 0.7806, + "step": 12651 + }, + { + "epoch": 0.7766966450781178, + "grad_norm": 0.8961512738991121, + "learning_rate": 2.5028353958843233e-06, + "loss": 0.6896, + "step": 12652 + }, + { + "epoch": 0.7767580343165843, + "grad_norm": 1.0538859881680651, + "learning_rate": 2.501519735348987e-06, + "loss": 0.7583, + "step": 12653 + }, + { + "epoch": 0.7768194235550508, + "grad_norm": 1.011745712464008, + "learning_rate": 2.5002043712686785e-06, + "loss": 0.7802, + "step": 12654 + }, + { + "epoch": 0.7768808127935173, + "grad_norm": 0.947035155824303, + "learning_rate": 2.4988893036954045e-06, + "loss": 0.7555, + "step": 12655 + }, + { + "epoch": 0.7769422020319838, + "grad_norm": 0.941975141381861, + "learning_rate": 2.4975745326811563e-06, + "loss": 0.7106, + "step": 12656 + }, + { + "epoch": 0.7770035912704503, + "grad_norm": 1.0362437570684424, + "learning_rate": 2.496260058277912e-06, + "loss": 0.7515, + "step": 12657 + }, + { + "epoch": 0.7770649805089168, + "grad_norm": 0.8747882742111559, + "learning_rate": 2.49494588053764e-06, + "loss": 0.6814, + "step": 12658 + }, + { + "epoch": 0.7771263697473832, + "grad_norm": 0.9186165179593951, + "learning_rate": 2.493631999512298e-06, + "loss": 0.7516, + "step": 12659 + }, + { + "epoch": 0.7771877589858498, + "grad_norm": 1.0365337144481241, + "learning_rate": 2.4923184152538293e-06, + "loss": 0.7813, + "step": 12660 + }, + { + "epoch": 0.7772491482243162, + "grad_norm": 0.9715100037358276, + "learning_rate": 2.4910051278141643e-06, + "loss": 0.7369, + "step": 12661 + }, + { + "epoch": 0.7773105374627828, + "grad_norm": 1.0663297958846132, + "learning_rate": 2.4896921372452345e-06, + "loss": 0.7228, + "step": 12662 + }, + { + "epoch": 0.7773719267012492, + "grad_norm": 0.9967769283509845, + "learning_rate": 2.4883794435989385e-06, + "loss": 0.7877, + "step": 12663 + }, + { + "epoch": 0.7774333159397158, + "grad_norm": 0.9574232336657028, + "learning_rate": 2.4870670469271783e-06, + "loss": 0.7431, + "step": 12664 + }, + { + "epoch": 0.7774947051781823, + "grad_norm": 0.9355655344998886, + "learning_rate": 2.4857549472818376e-06, + "loss": 0.7298, + "step": 12665 + }, + { + "epoch": 0.7775560944166487, + "grad_norm": 1.0376872299328217, + "learning_rate": 2.4844431447147955e-06, + "loss": 0.7778, + "step": 12666 + }, + { + "epoch": 0.7776174836551153, + "grad_norm": 0.9858316171082424, + "learning_rate": 2.4831316392779137e-06, + "loss": 0.7902, + "step": 12667 + }, + { + "epoch": 0.7776788728935817, + "grad_norm": 1.0158992767556494, + "learning_rate": 2.4818204310230365e-06, + "loss": 0.747, + "step": 12668 + }, + { + "epoch": 0.7777402621320483, + "grad_norm": 0.9091650869907488, + "learning_rate": 2.48050952000201e-06, + "loss": 0.6779, + "step": 12669 + }, + { + "epoch": 0.7778016513705147, + "grad_norm": 1.119497794083036, + "learning_rate": 2.47919890626666e-06, + "loss": 0.706, + "step": 12670 + }, + { + "epoch": 0.7778630406089813, + "grad_norm": 1.0273217877272733, + "learning_rate": 2.477888589868801e-06, + "loss": 0.7582, + "step": 12671 + }, + { + "epoch": 0.7779244298474477, + "grad_norm": 1.1037248523148555, + "learning_rate": 2.4765785708602375e-06, + "loss": 0.7339, + "step": 12672 + }, + { + "epoch": 0.7779858190859142, + "grad_norm": 1.0064877024870915, + "learning_rate": 2.4752688492927602e-06, + "loss": 0.748, + "step": 12673 + }, + { + "epoch": 0.7780472083243808, + "grad_norm": 0.8670598987283414, + "learning_rate": 2.473959425218151e-06, + "loss": 0.7392, + "step": 12674 + }, + { + "epoch": 0.7781085975628472, + "grad_norm": 1.0171316957265815, + "learning_rate": 2.4726502986881753e-06, + "loss": 0.7509, + "step": 12675 + }, + { + "epoch": 0.7781699868013138, + "grad_norm": 1.076483947994574, + "learning_rate": 2.4713414697545945e-06, + "loss": 0.7158, + "step": 12676 + }, + { + "epoch": 0.7782313760397802, + "grad_norm": 0.9448838724907447, + "learning_rate": 2.4700329384691545e-06, + "loss": 0.7282, + "step": 12677 + }, + { + "epoch": 0.7782927652782468, + "grad_norm": 1.1261196083314957, + "learning_rate": 2.468724704883583e-06, + "loss": 0.7768, + "step": 12678 + }, + { + "epoch": 0.7783541545167132, + "grad_norm": 1.0874713591730536, + "learning_rate": 2.467416769049601e-06, + "loss": 0.7866, + "step": 12679 + }, + { + "epoch": 0.7784155437551797, + "grad_norm": 1.0998231065092106, + "learning_rate": 2.4661091310189233e-06, + "loss": 0.7709, + "step": 12680 + }, + { + "epoch": 0.7784769329936462, + "grad_norm": 1.0756427267149669, + "learning_rate": 2.4648017908432463e-06, + "loss": 0.7839, + "step": 12681 + }, + { + "epoch": 0.7785383222321127, + "grad_norm": 0.9812543407302355, + "learning_rate": 2.463494748574257e-06, + "loss": 0.7564, + "step": 12682 + }, + { + "epoch": 0.7785997114705792, + "grad_norm": 0.9981346184002765, + "learning_rate": 2.462188004263626e-06, + "loss": 0.7487, + "step": 12683 + }, + { + "epoch": 0.7786611007090457, + "grad_norm": 0.9117309353966608, + "learning_rate": 2.4608815579630196e-06, + "loss": 0.7179, + "step": 12684 + }, + { + "epoch": 0.7787224899475123, + "grad_norm": 0.9667616566461574, + "learning_rate": 2.4595754097240876e-06, + "loss": 0.6934, + "step": 12685 + }, + { + "epoch": 0.7787838791859787, + "grad_norm": 0.9342953666992142, + "learning_rate": 2.4582695595984652e-06, + "loss": 0.7571, + "step": 12686 + }, + { + "epoch": 0.7788452684244452, + "grad_norm": 0.9439515311941087, + "learning_rate": 2.4569640076377886e-06, + "loss": 0.7756, + "step": 12687 + }, + { + "epoch": 0.7789066576629117, + "grad_norm": 0.9476380388226313, + "learning_rate": 2.455658753893665e-06, + "loss": 0.7687, + "step": 12688 + }, + { + "epoch": 0.7789680469013782, + "grad_norm": 0.9425782661730735, + "learning_rate": 2.454353798417698e-06, + "loss": 0.7125, + "step": 12689 + }, + { + "epoch": 0.7790294361398447, + "grad_norm": 1.0697450848835588, + "learning_rate": 2.4530491412614853e-06, + "loss": 0.757, + "step": 12690 + }, + { + "epoch": 0.7790908253783112, + "grad_norm": 0.9972418671846435, + "learning_rate": 2.451744782476604e-06, + "loss": 0.7562, + "step": 12691 + }, + { + "epoch": 0.7791522146167776, + "grad_norm": 0.5881530836119836, + "learning_rate": 2.4504407221146256e-06, + "loss": 0.635, + "step": 12692 + }, + { + "epoch": 0.7792136038552442, + "grad_norm": 1.1004816630111591, + "learning_rate": 2.4491369602270965e-06, + "loss": 0.7378, + "step": 12693 + }, + { + "epoch": 0.7792749930937106, + "grad_norm": 1.0999114378907162, + "learning_rate": 2.4478334968655716e-06, + "loss": 0.7483, + "step": 12694 + }, + { + "epoch": 0.7793363823321772, + "grad_norm": 1.0796762794797792, + "learning_rate": 2.4465303320815813e-06, + "loss": 0.7051, + "step": 12695 + }, + { + "epoch": 0.7793977715706437, + "grad_norm": 1.0231293699934574, + "learning_rate": 2.445227465926645e-06, + "loss": 0.7502, + "step": 12696 + }, + { + "epoch": 0.7794591608091102, + "grad_norm": 0.8961079806118892, + "learning_rate": 2.4439248984522723e-06, + "loss": 0.6818, + "step": 12697 + }, + { + "epoch": 0.7795205500475767, + "grad_norm": 1.0311780923281952, + "learning_rate": 2.442622629709962e-06, + "loss": 0.7607, + "step": 12698 + }, + { + "epoch": 0.7795819392860431, + "grad_norm": 1.017280553104686, + "learning_rate": 2.4413206597511983e-06, + "loss": 0.7575, + "step": 12699 + }, + { + "epoch": 0.7796433285245097, + "grad_norm": 0.9092149959100116, + "learning_rate": 2.440018988627453e-06, + "loss": 0.6762, + "step": 12700 + }, + { + "epoch": 0.7797047177629761, + "grad_norm": 0.9175875980098877, + "learning_rate": 2.4387176163901925e-06, + "loss": 0.8189, + "step": 12701 + }, + { + "epoch": 0.7797661070014427, + "grad_norm": 0.9534993725736871, + "learning_rate": 2.437416543090869e-06, + "loss": 0.7857, + "step": 12702 + }, + { + "epoch": 0.7798274962399091, + "grad_norm": 0.9769061936912731, + "learning_rate": 2.4361157687809147e-06, + "loss": 0.695, + "step": 12703 + }, + { + "epoch": 0.7798888854783756, + "grad_norm": 0.9328370421153143, + "learning_rate": 2.434815293511755e-06, + "loss": 0.7614, + "step": 12704 + }, + { + "epoch": 0.7799502747168421, + "grad_norm": 1.019279182656602, + "learning_rate": 2.4335151173348115e-06, + "loss": 0.727, + "step": 12705 + }, + { + "epoch": 0.7800116639553086, + "grad_norm": 0.9286283995089711, + "learning_rate": 2.4322152403014865e-06, + "loss": 0.7163, + "step": 12706 + }, + { + "epoch": 0.7800730531937752, + "grad_norm": 0.9713572064095298, + "learning_rate": 2.4309156624631624e-06, + "loss": 0.7473, + "step": 12707 + }, + { + "epoch": 0.7801344424322416, + "grad_norm": 1.1042946494770471, + "learning_rate": 2.4296163838712274e-06, + "loss": 0.7961, + "step": 12708 + }, + { + "epoch": 0.7801958316707082, + "grad_norm": 1.0342302329264104, + "learning_rate": 2.4283174045770464e-06, + "loss": 0.7493, + "step": 12709 + }, + { + "epoch": 0.7802572209091746, + "grad_norm": 0.9975165215736274, + "learning_rate": 2.427018724631974e-06, + "loss": 0.7651, + "step": 12710 + }, + { + "epoch": 0.7803186101476411, + "grad_norm": 1.131836027460846, + "learning_rate": 2.4257203440873554e-06, + "loss": 0.8236, + "step": 12711 + }, + { + "epoch": 0.7803799993861076, + "grad_norm": 1.0213415523034943, + "learning_rate": 2.4244222629945214e-06, + "loss": 0.7065, + "step": 12712 + }, + { + "epoch": 0.7804413886245741, + "grad_norm": 0.9370521664260815, + "learning_rate": 2.4231244814047914e-06, + "loss": 0.7329, + "step": 12713 + }, + { + "epoch": 0.7805027778630406, + "grad_norm": 1.0782994909481158, + "learning_rate": 2.4218269993694733e-06, + "loss": 0.6761, + "step": 12714 + }, + { + "epoch": 0.7805641671015071, + "grad_norm": 1.1600787865506916, + "learning_rate": 2.420529816939866e-06, + "loss": 0.7994, + "step": 12715 + }, + { + "epoch": 0.7806255563399735, + "grad_norm": 0.9449257108704415, + "learning_rate": 2.419232934167257e-06, + "loss": 0.697, + "step": 12716 + }, + { + "epoch": 0.7806869455784401, + "grad_norm": 0.5875823514886067, + "learning_rate": 2.417936351102912e-06, + "loss": 0.6597, + "step": 12717 + }, + { + "epoch": 0.7807483348169066, + "grad_norm": 1.0705235642055844, + "learning_rate": 2.416640067798092e-06, + "loss": 0.7288, + "step": 12718 + }, + { + "epoch": 0.7808097240553731, + "grad_norm": 0.9592413665344914, + "learning_rate": 2.415344084304051e-06, + "loss": 0.7139, + "step": 12719 + }, + { + "epoch": 0.7808711132938396, + "grad_norm": 0.9819846111034852, + "learning_rate": 2.4140484006720244e-06, + "loss": 0.7218, + "step": 12720 + }, + { + "epoch": 0.7809325025323061, + "grad_norm": 0.9693367636808023, + "learning_rate": 2.4127530169532363e-06, + "loss": 0.6917, + "step": 12721 + }, + { + "epoch": 0.7809938917707726, + "grad_norm": 1.0243196317368757, + "learning_rate": 2.411457933198902e-06, + "loss": 0.7813, + "step": 12722 + }, + { + "epoch": 0.781055281009239, + "grad_norm": 1.0484661880134976, + "learning_rate": 2.4101631494602217e-06, + "loss": 0.7504, + "step": 12723 + }, + { + "epoch": 0.7811166702477056, + "grad_norm": 0.9155785684100035, + "learning_rate": 2.4088686657883853e-06, + "loss": 0.728, + "step": 12724 + }, + { + "epoch": 0.781178059486172, + "grad_norm": 0.9277277285899409, + "learning_rate": 2.407574482234567e-06, + "loss": 0.6949, + "step": 12725 + }, + { + "epoch": 0.7812394487246386, + "grad_norm": 1.0017088412900248, + "learning_rate": 2.4062805988499436e-06, + "loss": 0.7582, + "step": 12726 + }, + { + "epoch": 0.7813008379631051, + "grad_norm": 1.0268755035448225, + "learning_rate": 2.404987015685658e-06, + "loss": 0.7692, + "step": 12727 + }, + { + "epoch": 0.7813622272015716, + "grad_norm": 1.0336729803785998, + "learning_rate": 2.4036937327928543e-06, + "loss": 0.7707, + "step": 12728 + }, + { + "epoch": 0.7814236164400381, + "grad_norm": 0.9549183064778106, + "learning_rate": 2.402400750222669e-06, + "loss": 0.7741, + "step": 12729 + }, + { + "epoch": 0.7814850056785045, + "grad_norm": 1.0215523063133094, + "learning_rate": 2.4011080680262167e-06, + "loss": 0.745, + "step": 12730 + }, + { + "epoch": 0.7815463949169711, + "grad_norm": 0.9958164052193165, + "learning_rate": 2.399815686254606e-06, + "loss": 0.7619, + "step": 12731 + }, + { + "epoch": 0.7816077841554375, + "grad_norm": 1.0692962446752086, + "learning_rate": 2.3985236049589244e-06, + "loss": 0.7281, + "step": 12732 + }, + { + "epoch": 0.7816691733939041, + "grad_norm": 0.9669944216030332, + "learning_rate": 2.397231824190264e-06, + "loss": 0.7194, + "step": 12733 + }, + { + "epoch": 0.7817305626323705, + "grad_norm": 1.0453096726837667, + "learning_rate": 2.395940343999691e-06, + "loss": 0.7601, + "step": 12734 + }, + { + "epoch": 0.781791951870837, + "grad_norm": 1.0229218146079542, + "learning_rate": 2.3946491644382662e-06, + "loss": 0.701, + "step": 12735 + }, + { + "epoch": 0.7818533411093035, + "grad_norm": 0.9841148815937927, + "learning_rate": 2.393358285557036e-06, + "loss": 0.7533, + "step": 12736 + }, + { + "epoch": 0.78191473034777, + "grad_norm": 1.0849875046539141, + "learning_rate": 2.3920677074070364e-06, + "loss": 0.753, + "step": 12737 + }, + { + "epoch": 0.7819761195862366, + "grad_norm": 0.9703599789135879, + "learning_rate": 2.3907774300392906e-06, + "loss": 0.7188, + "step": 12738 + }, + { + "epoch": 0.782037508824703, + "grad_norm": 1.0341619490421603, + "learning_rate": 2.389487453504806e-06, + "loss": 0.7451, + "step": 12739 + }, + { + "epoch": 0.7820988980631696, + "grad_norm": 0.9367111557078326, + "learning_rate": 2.3881977778545895e-06, + "loss": 0.7423, + "step": 12740 + }, + { + "epoch": 0.782160287301636, + "grad_norm": 0.982287499187125, + "learning_rate": 2.3869084031396284e-06, + "loss": 0.7657, + "step": 12741 + }, + { + "epoch": 0.7822216765401026, + "grad_norm": 0.8996168106535065, + "learning_rate": 2.385619329410893e-06, + "loss": 0.7665, + "step": 12742 + }, + { + "epoch": 0.782283065778569, + "grad_norm": 1.013500752342613, + "learning_rate": 2.3843305567193475e-06, + "loss": 0.7662, + "step": 12743 + }, + { + "epoch": 0.7823444550170355, + "grad_norm": 1.0358464817503026, + "learning_rate": 2.38304208511595e-06, + "loss": 0.7627, + "step": 12744 + }, + { + "epoch": 0.782405844255502, + "grad_norm": 0.8864269660317374, + "learning_rate": 2.3817539146516365e-06, + "loss": 0.7021, + "step": 12745 + }, + { + "epoch": 0.7824672334939685, + "grad_norm": 0.9450577115905441, + "learning_rate": 2.3804660453773353e-06, + "loss": 0.7641, + "step": 12746 + }, + { + "epoch": 0.782528622732435, + "grad_norm": 0.9772570454420146, + "learning_rate": 2.379178477343965e-06, + "loss": 0.7495, + "step": 12747 + }, + { + "epoch": 0.7825900119709015, + "grad_norm": 0.9938216048433977, + "learning_rate": 2.377891210602428e-06, + "loss": 0.748, + "step": 12748 + }, + { + "epoch": 0.782651401209368, + "grad_norm": 1.060088174406336, + "learning_rate": 2.3766042452036164e-06, + "loss": 0.7057, + "step": 12749 + }, + { + "epoch": 0.7827127904478345, + "grad_norm": 1.0522746586792093, + "learning_rate": 2.37531758119841e-06, + "loss": 0.7092, + "step": 12750 + }, + { + "epoch": 0.782774179686301, + "grad_norm": 0.9202483251431358, + "learning_rate": 2.3740312186376845e-06, + "loss": 0.7337, + "step": 12751 + }, + { + "epoch": 0.7828355689247675, + "grad_norm": 1.0421518992397212, + "learning_rate": 2.372745157572288e-06, + "loss": 0.7458, + "step": 12752 + }, + { + "epoch": 0.782896958163234, + "grad_norm": 0.9993523050203176, + "learning_rate": 2.3714593980530666e-06, + "loss": 0.7207, + "step": 12753 + }, + { + "epoch": 0.7829583474017004, + "grad_norm": 1.062062730264497, + "learning_rate": 2.3701739401308586e-06, + "loss": 0.7288, + "step": 12754 + }, + { + "epoch": 0.783019736640167, + "grad_norm": 0.9631741225200499, + "learning_rate": 2.3688887838564824e-06, + "loss": 0.7126, + "step": 12755 + }, + { + "epoch": 0.7830811258786334, + "grad_norm": 0.8984317587218316, + "learning_rate": 2.3676039292807484e-06, + "loss": 0.757, + "step": 12756 + }, + { + "epoch": 0.7831425151171, + "grad_norm": 1.1009488357580326, + "learning_rate": 2.366319376454447e-06, + "loss": 0.7742, + "step": 12757 + }, + { + "epoch": 0.7832039043555664, + "grad_norm": 1.0771271712016635, + "learning_rate": 2.365035125428371e-06, + "loss": 0.7528, + "step": 12758 + }, + { + "epoch": 0.783265293594033, + "grad_norm": 1.0610265234004186, + "learning_rate": 2.3637511762532904e-06, + "loss": 0.8116, + "step": 12759 + }, + { + "epoch": 0.7833266828324995, + "grad_norm": 0.9647189914034177, + "learning_rate": 2.362467528979968e-06, + "loss": 0.7498, + "step": 12760 + }, + { + "epoch": 0.783388072070966, + "grad_norm": 0.9844852507821323, + "learning_rate": 2.3611841836591533e-06, + "loss": 0.7924, + "step": 12761 + }, + { + "epoch": 0.7834494613094325, + "grad_norm": 0.9267364877380022, + "learning_rate": 2.359901140341583e-06, + "loss": 0.8126, + "step": 12762 + }, + { + "epoch": 0.7835108505478989, + "grad_norm": 1.0303323079327698, + "learning_rate": 2.358618399077982e-06, + "loss": 0.7878, + "step": 12763 + }, + { + "epoch": 0.7835722397863655, + "grad_norm": 0.9243154586793942, + "learning_rate": 2.3573359599190616e-06, + "loss": 0.7425, + "step": 12764 + }, + { + "epoch": 0.7836336290248319, + "grad_norm": 0.9216640407568779, + "learning_rate": 2.3560538229155293e-06, + "loss": 0.7485, + "step": 12765 + }, + { + "epoch": 0.7836950182632985, + "grad_norm": 0.9907343607099599, + "learning_rate": 2.3547719881180763e-06, + "loss": 0.7552, + "step": 12766 + }, + { + "epoch": 0.7837564075017649, + "grad_norm": 0.9821747973443848, + "learning_rate": 2.3534904555773696e-06, + "loss": 0.748, + "step": 12767 + }, + { + "epoch": 0.7838177967402314, + "grad_norm": 0.9989988390133123, + "learning_rate": 2.3522092253440843e-06, + "loss": 0.7593, + "step": 12768 + }, + { + "epoch": 0.7838791859786979, + "grad_norm": 1.0071521631006057, + "learning_rate": 2.350928297468872e-06, + "loss": 0.7388, + "step": 12769 + }, + { + "epoch": 0.7839405752171644, + "grad_norm": 1.04653533920507, + "learning_rate": 2.3496476720023764e-06, + "loss": 0.77, + "step": 12770 + }, + { + "epoch": 0.784001964455631, + "grad_norm": 0.9271626917882799, + "learning_rate": 2.3483673489952196e-06, + "loss": 0.7052, + "step": 12771 + }, + { + "epoch": 0.7840633536940974, + "grad_norm": 1.051615241865444, + "learning_rate": 2.347087328498029e-06, + "loss": 0.6935, + "step": 12772 + }, + { + "epoch": 0.784124742932564, + "grad_norm": 1.0238831333556124, + "learning_rate": 2.345807610561407e-06, + "loss": 0.7504, + "step": 12773 + }, + { + "epoch": 0.7841861321710304, + "grad_norm": 0.9919619194626935, + "learning_rate": 2.3445281952359466e-06, + "loss": 0.7983, + "step": 12774 + }, + { + "epoch": 0.7842475214094969, + "grad_norm": 0.9828977775892644, + "learning_rate": 2.343249082572232e-06, + "loss": 0.7591, + "step": 12775 + }, + { + "epoch": 0.7843089106479634, + "grad_norm": 1.094097685384466, + "learning_rate": 2.3419702726208315e-06, + "loss": 0.733, + "step": 12776 + }, + { + "epoch": 0.7843702998864299, + "grad_norm": 0.6108173879815499, + "learning_rate": 2.340691765432305e-06, + "loss": 0.6855, + "step": 12777 + }, + { + "epoch": 0.7844316891248964, + "grad_norm": 1.0733786864001325, + "learning_rate": 2.3394135610571946e-06, + "loss": 0.7761, + "step": 12778 + }, + { + "epoch": 0.7844930783633629, + "grad_norm": 1.0071077272888662, + "learning_rate": 2.33813565954604e-06, + "loss": 0.7394, + "step": 12779 + }, + { + "epoch": 0.7845544676018295, + "grad_norm": 0.9436337810930095, + "learning_rate": 2.336858060949365e-06, + "loss": 0.7272, + "step": 12780 + }, + { + "epoch": 0.7846158568402959, + "grad_norm": 0.9092672286445055, + "learning_rate": 2.335580765317673e-06, + "loss": 0.7273, + "step": 12781 + }, + { + "epoch": 0.7846772460787624, + "grad_norm": 1.0244901177804095, + "learning_rate": 2.3343037727014627e-06, + "loss": 0.7591, + "step": 12782 + }, + { + "epoch": 0.7847386353172289, + "grad_norm": 1.084982157733408, + "learning_rate": 2.3330270831512268e-06, + "loss": 0.702, + "step": 12783 + }, + { + "epoch": 0.7848000245556954, + "grad_norm": 0.9699672625568572, + "learning_rate": 2.3317506967174354e-06, + "loss": 0.7413, + "step": 12784 + }, + { + "epoch": 0.7848614137941619, + "grad_norm": 0.6427319526727995, + "learning_rate": 2.3304746134505517e-06, + "loss": 0.6416, + "step": 12785 + }, + { + "epoch": 0.7849228030326284, + "grad_norm": 0.9666813800699279, + "learning_rate": 2.3291988334010265e-06, + "loss": 0.7664, + "step": 12786 + }, + { + "epoch": 0.7849841922710948, + "grad_norm": 0.9818656967527605, + "learning_rate": 2.3279233566192973e-06, + "loss": 0.7441, + "step": 12787 + }, + { + "epoch": 0.7850455815095614, + "grad_norm": 1.1227731177186406, + "learning_rate": 2.326648183155791e-06, + "loss": 0.7863, + "step": 12788 + }, + { + "epoch": 0.7851069707480278, + "grad_norm": 0.9667434591438161, + "learning_rate": 2.325373313060919e-06, + "loss": 0.7279, + "step": 12789 + }, + { + "epoch": 0.7851683599864944, + "grad_norm": 1.1666306013081502, + "learning_rate": 2.3240987463850927e-06, + "loss": 0.7676, + "step": 12790 + }, + { + "epoch": 0.7852297492249609, + "grad_norm": 0.9317224995019939, + "learning_rate": 2.322824483178694e-06, + "loss": 0.7113, + "step": 12791 + }, + { + "epoch": 0.7852911384634274, + "grad_norm": 1.016748453968543, + "learning_rate": 2.321550523492101e-06, + "loss": 0.7422, + "step": 12792 + }, + { + "epoch": 0.7853525277018939, + "grad_norm": 0.9330484462397104, + "learning_rate": 2.320276867375686e-06, + "loss": 0.716, + "step": 12793 + }, + { + "epoch": 0.7854139169403603, + "grad_norm": 0.9575792690849781, + "learning_rate": 2.3190035148797996e-06, + "loss": 0.7637, + "step": 12794 + }, + { + "epoch": 0.7854753061788269, + "grad_norm": 0.9925845298643674, + "learning_rate": 2.3177304660547882e-06, + "loss": 0.7491, + "step": 12795 + }, + { + "epoch": 0.7855366954172933, + "grad_norm": 0.9834233116001332, + "learning_rate": 2.316457720950974e-06, + "loss": 0.767, + "step": 12796 + }, + { + "epoch": 0.7855980846557599, + "grad_norm": 1.0008743808451381, + "learning_rate": 2.3151852796186834e-06, + "loss": 0.7505, + "step": 12797 + }, + { + "epoch": 0.7856594738942263, + "grad_norm": 1.1197840739291125, + "learning_rate": 2.3139131421082195e-06, + "loss": 0.7401, + "step": 12798 + }, + { + "epoch": 0.7857208631326928, + "grad_norm": 1.0015651695260563, + "learning_rate": 2.312641308469877e-06, + "loss": 0.7259, + "step": 12799 + }, + { + "epoch": 0.7857822523711593, + "grad_norm": 1.0493904979307274, + "learning_rate": 2.3113697787539392e-06, + "loss": 0.7209, + "step": 12800 + }, + { + "epoch": 0.7858436416096258, + "grad_norm": 1.0098820364299008, + "learning_rate": 2.310098553010676e-06, + "loss": 0.7705, + "step": 12801 + }, + { + "epoch": 0.7859050308480924, + "grad_norm": 1.0400370454763583, + "learning_rate": 2.3088276312903445e-06, + "loss": 0.7707, + "step": 12802 + }, + { + "epoch": 0.7859664200865588, + "grad_norm": 1.0539102412005068, + "learning_rate": 2.307557013643189e-06, + "loss": 0.7328, + "step": 12803 + }, + { + "epoch": 0.7860278093250254, + "grad_norm": 1.0301318607680592, + "learning_rate": 2.30628670011945e-06, + "loss": 0.7174, + "step": 12804 + }, + { + "epoch": 0.7860891985634918, + "grad_norm": 1.0241528723428495, + "learning_rate": 2.3050166907693504e-06, + "loss": 0.737, + "step": 12805 + }, + { + "epoch": 0.7861505878019583, + "grad_norm": 0.9259412304940536, + "learning_rate": 2.3037469856430896e-06, + "loss": 0.7374, + "step": 12806 + }, + { + "epoch": 0.7862119770404248, + "grad_norm": 0.961365037485703, + "learning_rate": 2.3024775847908763e-06, + "loss": 0.6903, + "step": 12807 + }, + { + "epoch": 0.7862733662788913, + "grad_norm": 1.0640575964234196, + "learning_rate": 2.3012084882628936e-06, + "loss": 0.7535, + "step": 12808 + }, + { + "epoch": 0.7863347555173578, + "grad_norm": 0.8589978250817698, + "learning_rate": 2.2999396961093157e-06, + "loss": 0.7428, + "step": 12809 + }, + { + "epoch": 0.7863961447558243, + "grad_norm": 0.8532356547270966, + "learning_rate": 2.298671208380304e-06, + "loss": 0.7385, + "step": 12810 + }, + { + "epoch": 0.7864575339942907, + "grad_norm": 0.9464612668046547, + "learning_rate": 2.297403025126008e-06, + "loss": 0.7502, + "step": 12811 + }, + { + "epoch": 0.7865189232327573, + "grad_norm": 0.9408076772482015, + "learning_rate": 2.2961351463965687e-06, + "loss": 0.7153, + "step": 12812 + }, + { + "epoch": 0.7865803124712238, + "grad_norm": 1.0936049278539146, + "learning_rate": 2.2948675722421086e-06, + "loss": 0.7382, + "step": 12813 + }, + { + "epoch": 0.7866417017096903, + "grad_norm": 0.9686213776320018, + "learning_rate": 2.2936003027127418e-06, + "loss": 0.7505, + "step": 12814 + }, + { + "epoch": 0.7867030909481568, + "grad_norm": 1.0976330479018872, + "learning_rate": 2.2923333378585765e-06, + "loss": 0.7931, + "step": 12815 + }, + { + "epoch": 0.7867644801866233, + "grad_norm": 0.8458902699977179, + "learning_rate": 2.2910666777296953e-06, + "loss": 0.7801, + "step": 12816 + }, + { + "epoch": 0.7868258694250898, + "grad_norm": 1.0534438118818554, + "learning_rate": 2.2898003223761756e-06, + "loss": 0.7491, + "step": 12817 + }, + { + "epoch": 0.7868872586635562, + "grad_norm": 1.0665000218992828, + "learning_rate": 2.2885342718480897e-06, + "loss": 0.7476, + "step": 12818 + }, + { + "epoch": 0.7869486479020228, + "grad_norm": 1.0281223759921034, + "learning_rate": 2.2872685261954877e-06, + "loss": 0.7492, + "step": 12819 + }, + { + "epoch": 0.7870100371404892, + "grad_norm": 1.0634813610981702, + "learning_rate": 2.2860030854684133e-06, + "loss": 0.7647, + "step": 12820 + }, + { + "epoch": 0.7870714263789558, + "grad_norm": 1.0541915086077192, + "learning_rate": 2.28473794971689e-06, + "loss": 0.6942, + "step": 12821 + }, + { + "epoch": 0.7871328156174223, + "grad_norm": 1.0789020607188469, + "learning_rate": 2.283473118990941e-06, + "loss": 0.7091, + "step": 12822 + }, + { + "epoch": 0.7871942048558888, + "grad_norm": 1.0075687112135567, + "learning_rate": 2.2822085933405713e-06, + "loss": 0.7485, + "step": 12823 + }, + { + "epoch": 0.7872555940943553, + "grad_norm": 0.9366253079180007, + "learning_rate": 2.280944372815774e-06, + "loss": 0.7069, + "step": 12824 + }, + { + "epoch": 0.7873169833328217, + "grad_norm": 0.9877395066765023, + "learning_rate": 2.2796804574665298e-06, + "loss": 0.7166, + "step": 12825 + }, + { + "epoch": 0.7873783725712883, + "grad_norm": 0.9632514310858766, + "learning_rate": 2.278416847342808e-06, + "loss": 0.7311, + "step": 12826 + }, + { + "epoch": 0.7874397618097547, + "grad_norm": 1.029051044057031, + "learning_rate": 2.277153542494566e-06, + "loss": 0.7514, + "step": 12827 + }, + { + "epoch": 0.7875011510482213, + "grad_norm": 1.0083302944211456, + "learning_rate": 2.275890542971747e-06, + "loss": 0.7334, + "step": 12828 + }, + { + "epoch": 0.7875625402866877, + "grad_norm": 0.9875214260375857, + "learning_rate": 2.274627848824288e-06, + "loss": 0.7257, + "step": 12829 + }, + { + "epoch": 0.7876239295251543, + "grad_norm": 1.0453050684873477, + "learning_rate": 2.2733654601021126e-06, + "loss": 0.721, + "step": 12830 + }, + { + "epoch": 0.7876853187636207, + "grad_norm": 1.1069396056483858, + "learning_rate": 2.272103376855118e-06, + "loss": 0.6802, + "step": 12831 + }, + { + "epoch": 0.7877467080020872, + "grad_norm": 1.0898549864539495, + "learning_rate": 2.2708415991332135e-06, + "loss": 0.7618, + "step": 12832 + }, + { + "epoch": 0.7878080972405538, + "grad_norm": 0.9387323363032922, + "learning_rate": 2.269580126986277e-06, + "loss": 0.7486, + "step": 12833 + }, + { + "epoch": 0.7878694864790202, + "grad_norm": 1.0339004294429126, + "learning_rate": 2.2683189604641877e-06, + "loss": 0.7703, + "step": 12834 + }, + { + "epoch": 0.7879308757174868, + "grad_norm": 1.0422902484796959, + "learning_rate": 2.267058099616796e-06, + "loss": 0.7837, + "step": 12835 + }, + { + "epoch": 0.7879922649559532, + "grad_norm": 1.015081821919328, + "learning_rate": 2.2657975444939582e-06, + "loss": 0.7656, + "step": 12836 + }, + { + "epoch": 0.7880536541944198, + "grad_norm": 0.9717648142293948, + "learning_rate": 2.26453729514551e-06, + "loss": 0.7253, + "step": 12837 + }, + { + "epoch": 0.7881150434328862, + "grad_norm": 1.029413971293043, + "learning_rate": 2.2632773516212738e-06, + "loss": 0.7527, + "step": 12838 + }, + { + "epoch": 0.7881764326713527, + "grad_norm": 0.9767846471036822, + "learning_rate": 2.262017713971063e-06, + "loss": 0.7643, + "step": 12839 + }, + { + "epoch": 0.7882378219098192, + "grad_norm": 0.9487326640296669, + "learning_rate": 2.2607583822446778e-06, + "loss": 0.7303, + "step": 12840 + }, + { + "epoch": 0.7882992111482857, + "grad_norm": 0.924329802080268, + "learning_rate": 2.2594993564919067e-06, + "loss": 0.7616, + "step": 12841 + }, + { + "epoch": 0.7883606003867522, + "grad_norm": 0.9908491215111704, + "learning_rate": 2.258240636762521e-06, + "loss": 0.7284, + "step": 12842 + }, + { + "epoch": 0.7884219896252187, + "grad_norm": 0.9504637027615855, + "learning_rate": 2.256982223106292e-06, + "loss": 0.6663, + "step": 12843 + }, + { + "epoch": 0.7884833788636852, + "grad_norm": 0.8285776121733708, + "learning_rate": 2.2557241155729714e-06, + "loss": 0.7232, + "step": 12844 + }, + { + "epoch": 0.7885447681021517, + "grad_norm": 1.0289179519934324, + "learning_rate": 2.2544663142122903e-06, + "loss": 0.7292, + "step": 12845 + }, + { + "epoch": 0.7886061573406182, + "grad_norm": 1.059127750172857, + "learning_rate": 2.2532088190739843e-06, + "loss": 0.7015, + "step": 12846 + }, + { + "epoch": 0.7886675465790847, + "grad_norm": 0.5857042074837742, + "learning_rate": 2.251951630207767e-06, + "loss": 0.6882, + "step": 12847 + }, + { + "epoch": 0.7887289358175512, + "grad_norm": 0.9812647130718986, + "learning_rate": 2.250694747663341e-06, + "loss": 0.7685, + "step": 12848 + }, + { + "epoch": 0.7887903250560176, + "grad_norm": 1.0180847377793791, + "learning_rate": 2.249438171490398e-06, + "loss": 0.7109, + "step": 12849 + }, + { + "epoch": 0.7888517142944842, + "grad_norm": 0.976601677399797, + "learning_rate": 2.2481819017386163e-06, + "loss": 0.6948, + "step": 12850 + }, + { + "epoch": 0.7889131035329506, + "grad_norm": 0.9242932543760818, + "learning_rate": 2.2469259384576637e-06, + "loss": 0.7165, + "step": 12851 + }, + { + "epoch": 0.7889744927714172, + "grad_norm": 0.8587753844592043, + "learning_rate": 2.2456702816971954e-06, + "loss": 0.7483, + "step": 12852 + }, + { + "epoch": 0.7890358820098836, + "grad_norm": 1.0111526992602926, + "learning_rate": 2.244414931506852e-06, + "loss": 0.7334, + "step": 12853 + }, + { + "epoch": 0.7890972712483502, + "grad_norm": 1.06468206441124, + "learning_rate": 2.2431598879362702e-06, + "loss": 0.7366, + "step": 12854 + }, + { + "epoch": 0.7891586604868167, + "grad_norm": 0.579873191539084, + "learning_rate": 2.241905151035063e-06, + "loss": 0.6544, + "step": 12855 + }, + { + "epoch": 0.7892200497252831, + "grad_norm": 0.9424833315598424, + "learning_rate": 2.240650720852835e-06, + "loss": 0.7469, + "step": 12856 + }, + { + "epoch": 0.7892814389637497, + "grad_norm": 0.935244983698256, + "learning_rate": 2.239396597439186e-06, + "loss": 0.7218, + "step": 12857 + }, + { + "epoch": 0.7893428282022161, + "grad_norm": 1.1532760630618366, + "learning_rate": 2.2381427808436973e-06, + "loss": 0.7382, + "step": 12858 + }, + { + "epoch": 0.7894042174406827, + "grad_norm": 1.0149913075155923, + "learning_rate": 2.236889271115941e-06, + "loss": 0.7228, + "step": 12859 + }, + { + "epoch": 0.7894656066791491, + "grad_norm": 1.0974290712121804, + "learning_rate": 2.2356360683054644e-06, + "loss": 0.6888, + "step": 12860 + }, + { + "epoch": 0.7895269959176157, + "grad_norm": 1.0281911188908346, + "learning_rate": 2.234383172461825e-06, + "loss": 0.7467, + "step": 12861 + }, + { + "epoch": 0.7895883851560821, + "grad_norm": 0.9445585700677025, + "learning_rate": 2.2331305836345517e-06, + "loss": 0.7569, + "step": 12862 + }, + { + "epoch": 0.7896497743945486, + "grad_norm": 1.0188464551171712, + "learning_rate": 2.231878301873167e-06, + "loss": 0.7448, + "step": 12863 + }, + { + "epoch": 0.7897111636330151, + "grad_norm": 0.9893967929996765, + "learning_rate": 2.2306263272271787e-06, + "loss": 0.7669, + "step": 12864 + }, + { + "epoch": 0.7897725528714816, + "grad_norm": 0.9198211933757985, + "learning_rate": 2.2293746597460864e-06, + "loss": 0.7122, + "step": 12865 + }, + { + "epoch": 0.7898339421099482, + "grad_norm": 1.073821334193936, + "learning_rate": 2.2281232994793743e-06, + "loss": 0.6997, + "step": 12866 + }, + { + "epoch": 0.7898953313484146, + "grad_norm": 1.006357740081314, + "learning_rate": 2.2268722464765112e-06, + "loss": 0.799, + "step": 12867 + }, + { + "epoch": 0.7899567205868812, + "grad_norm": 0.5729338774494254, + "learning_rate": 2.225621500786965e-06, + "loss": 0.6315, + "step": 12868 + }, + { + "epoch": 0.7900181098253476, + "grad_norm": 0.6064120413567793, + "learning_rate": 2.224371062460184e-06, + "loss": 0.6714, + "step": 12869 + }, + { + "epoch": 0.7900794990638141, + "grad_norm": 0.9941986147386845, + "learning_rate": 2.223120931545597e-06, + "loss": 0.7745, + "step": 12870 + }, + { + "epoch": 0.7901408883022806, + "grad_norm": 0.9313012563788543, + "learning_rate": 2.2218711080926346e-06, + "loss": 0.674, + "step": 12871 + }, + { + "epoch": 0.7902022775407471, + "grad_norm": 0.958058182851468, + "learning_rate": 2.220621592150709e-06, + "loss": 0.7064, + "step": 12872 + }, + { + "epoch": 0.7902636667792136, + "grad_norm": 0.5835958007682628, + "learning_rate": 2.2193723837692183e-06, + "loss": 0.6684, + "step": 12873 + }, + { + "epoch": 0.7903250560176801, + "grad_norm": 0.997534725804702, + "learning_rate": 2.2181234829975505e-06, + "loss": 0.7446, + "step": 12874 + }, + { + "epoch": 0.7903864452561467, + "grad_norm": 1.0772377543827658, + "learning_rate": 2.2168748898850835e-06, + "loss": 0.7266, + "step": 12875 + }, + { + "epoch": 0.7904478344946131, + "grad_norm": 0.599238000676888, + "learning_rate": 2.215626604481177e-06, + "loss": 0.7049, + "step": 12876 + }, + { + "epoch": 0.7905092237330796, + "grad_norm": 0.9454615858037595, + "learning_rate": 2.2143786268351864e-06, + "loss": 0.725, + "step": 12877 + }, + { + "epoch": 0.7905706129715461, + "grad_norm": 1.1019629396409334, + "learning_rate": 2.2131309569964454e-06, + "loss": 0.719, + "step": 12878 + }, + { + "epoch": 0.7906320022100126, + "grad_norm": 0.9298600973256768, + "learning_rate": 2.21188359501429e-06, + "loss": 0.7392, + "step": 12879 + }, + { + "epoch": 0.790693391448479, + "grad_norm": 1.0553728106951255, + "learning_rate": 2.210636540938028e-06, + "loss": 0.7917, + "step": 12880 + }, + { + "epoch": 0.7907547806869456, + "grad_norm": 0.9964256939626647, + "learning_rate": 2.2093897948169607e-06, + "loss": 0.7717, + "step": 12881 + }, + { + "epoch": 0.790816169925412, + "grad_norm": 1.021138156244776, + "learning_rate": 2.208143356700385e-06, + "loss": 0.7847, + "step": 12882 + }, + { + "epoch": 0.7908775591638786, + "grad_norm": 1.0078755763417533, + "learning_rate": 2.2068972266375756e-06, + "loss": 0.7537, + "step": 12883 + }, + { + "epoch": 0.790938948402345, + "grad_norm": 1.0722845195353636, + "learning_rate": 2.2056514046778e-06, + "loss": 0.7326, + "step": 12884 + }, + { + "epoch": 0.7910003376408116, + "grad_norm": 1.0153980796465596, + "learning_rate": 2.2044058908703115e-06, + "loss": 0.7349, + "step": 12885 + }, + { + "epoch": 0.7910617268792781, + "grad_norm": 0.9632816179589011, + "learning_rate": 2.2031606852643504e-06, + "loss": 0.7059, + "step": 12886 + }, + { + "epoch": 0.7911231161177446, + "grad_norm": 0.6026487501109664, + "learning_rate": 2.201915787909149e-06, + "loss": 0.65, + "step": 12887 + }, + { + "epoch": 0.7911845053562111, + "grad_norm": 0.9946297511846462, + "learning_rate": 2.2006711988539243e-06, + "loss": 0.7351, + "step": 12888 + }, + { + "epoch": 0.7912458945946775, + "grad_norm": 0.9660600849155405, + "learning_rate": 2.19942691814788e-06, + "loss": 0.7638, + "step": 12889 + }, + { + "epoch": 0.7913072838331441, + "grad_norm": 1.045263438282889, + "learning_rate": 2.1981829458402104e-06, + "loss": 0.7653, + "step": 12890 + }, + { + "epoch": 0.7913686730716105, + "grad_norm": 1.020545256691432, + "learning_rate": 2.196939281980095e-06, + "loss": 0.7638, + "step": 12891 + }, + { + "epoch": 0.7914300623100771, + "grad_norm": 0.9786023588581864, + "learning_rate": 2.195695926616702e-06, + "loss": 0.6949, + "step": 12892 + }, + { + "epoch": 0.7914914515485435, + "grad_norm": 0.985744982321208, + "learning_rate": 2.1944528797991914e-06, + "loss": 0.7524, + "step": 12893 + }, + { + "epoch": 0.79155284078701, + "grad_norm": 1.031034539319823, + "learning_rate": 2.193210141576708e-06, + "loss": 0.7465, + "step": 12894 + }, + { + "epoch": 0.7916142300254765, + "grad_norm": 0.8806112187422338, + "learning_rate": 2.1919677119983764e-06, + "loss": 0.7282, + "step": 12895 + }, + { + "epoch": 0.791675619263943, + "grad_norm": 1.0710552833575655, + "learning_rate": 2.190725591113324e-06, + "loss": 0.7655, + "step": 12896 + }, + { + "epoch": 0.7917370085024096, + "grad_norm": 0.9652465701738688, + "learning_rate": 2.189483778970656e-06, + "loss": 0.7512, + "step": 12897 + }, + { + "epoch": 0.791798397740876, + "grad_norm": 0.9554035071000035, + "learning_rate": 2.1882422756194676e-06, + "loss": 0.7278, + "step": 12898 + }, + { + "epoch": 0.7918597869793426, + "grad_norm": 0.9175472504327044, + "learning_rate": 2.187001081108843e-06, + "loss": 0.7368, + "step": 12899 + }, + { + "epoch": 0.791921176217809, + "grad_norm": 1.0711676553805396, + "learning_rate": 2.1857601954878516e-06, + "loss": 0.764, + "step": 12900 + }, + { + "epoch": 0.7919825654562755, + "grad_norm": 1.0381081670320467, + "learning_rate": 2.184519618805554e-06, + "loss": 0.7153, + "step": 12901 + }, + { + "epoch": 0.792043954694742, + "grad_norm": 1.0276493461156802, + "learning_rate": 2.1832793511109953e-06, + "loss": 0.745, + "step": 12902 + }, + { + "epoch": 0.7921053439332085, + "grad_norm": 1.0322959871678963, + "learning_rate": 2.1820393924532103e-06, + "loss": 0.7767, + "step": 12903 + }, + { + "epoch": 0.792166733171675, + "grad_norm": 1.0150219884812968, + "learning_rate": 2.1807997428812222e-06, + "loss": 0.7397, + "step": 12904 + }, + { + "epoch": 0.7922281224101415, + "grad_norm": 1.0479788065698497, + "learning_rate": 2.1795604024440397e-06, + "loss": 0.7511, + "step": 12905 + }, + { + "epoch": 0.792289511648608, + "grad_norm": 0.9943664042616501, + "learning_rate": 2.178321371190659e-06, + "loss": 0.75, + "step": 12906 + }, + { + "epoch": 0.7923509008870745, + "grad_norm": 0.9880862200235513, + "learning_rate": 2.17708264917007e-06, + "loss": 0.7859, + "step": 12907 + }, + { + "epoch": 0.792412290125541, + "grad_norm": 0.9297151062896252, + "learning_rate": 2.1758442364312473e-06, + "loss": 0.6952, + "step": 12908 + }, + { + "epoch": 0.7924736793640075, + "grad_norm": 0.9791277231374353, + "learning_rate": 2.1746061330231427e-06, + "loss": 0.7472, + "step": 12909 + }, + { + "epoch": 0.792535068602474, + "grad_norm": 0.9981446736063505, + "learning_rate": 2.1733683389947135e-06, + "loss": 0.7572, + "step": 12910 + }, + { + "epoch": 0.7925964578409405, + "grad_norm": 1.0276059149863574, + "learning_rate": 2.1721308543948938e-06, + "loss": 0.7396, + "step": 12911 + }, + { + "epoch": 0.792657847079407, + "grad_norm": 0.9974221008126295, + "learning_rate": 2.1708936792726064e-06, + "loss": 0.7282, + "step": 12912 + }, + { + "epoch": 0.7927192363178734, + "grad_norm": 1.021656073568544, + "learning_rate": 2.169656813676767e-06, + "loss": 0.7339, + "step": 12913 + }, + { + "epoch": 0.79278062555634, + "grad_norm": 1.0377048607272128, + "learning_rate": 2.1684202576562718e-06, + "loss": 0.7287, + "step": 12914 + }, + { + "epoch": 0.7928420147948064, + "grad_norm": 0.8833482128889761, + "learning_rate": 2.1671840112600106e-06, + "loss": 0.6913, + "step": 12915 + }, + { + "epoch": 0.792903404033273, + "grad_norm": 0.9861699940539626, + "learning_rate": 2.165948074536859e-06, + "loss": 0.7198, + "step": 12916 + }, + { + "epoch": 0.7929647932717394, + "grad_norm": 0.9491704932736338, + "learning_rate": 2.1647124475356752e-06, + "loss": 0.7007, + "step": 12917 + }, + { + "epoch": 0.793026182510206, + "grad_norm": 0.9277175659704003, + "learning_rate": 2.1634771303053215e-06, + "loss": 0.7572, + "step": 12918 + }, + { + "epoch": 0.7930875717486725, + "grad_norm": 0.9480133271658946, + "learning_rate": 2.1622421228946255e-06, + "loss": 0.7412, + "step": 12919 + }, + { + "epoch": 0.7931489609871389, + "grad_norm": 0.9368456440563964, + "learning_rate": 2.161007425352415e-06, + "loss": 0.7096, + "step": 12920 + }, + { + "epoch": 0.7932103502256055, + "grad_norm": 1.1219036580683452, + "learning_rate": 2.1597730377275106e-06, + "loss": 0.7629, + "step": 12921 + }, + { + "epoch": 0.7932717394640719, + "grad_norm": 1.0517141751763506, + "learning_rate": 2.15853896006871e-06, + "loss": 0.7074, + "step": 12922 + }, + { + "epoch": 0.7933331287025385, + "grad_norm": 1.0262873197636544, + "learning_rate": 2.1573051924248055e-06, + "loss": 0.7718, + "step": 12923 + }, + { + "epoch": 0.7933945179410049, + "grad_norm": 1.0791019970741942, + "learning_rate": 2.156071734844567e-06, + "loss": 0.7578, + "step": 12924 + }, + { + "epoch": 0.7934559071794715, + "grad_norm": 1.0270765205339225, + "learning_rate": 2.1548385873767687e-06, + "loss": 0.7946, + "step": 12925 + }, + { + "epoch": 0.7935172964179379, + "grad_norm": 1.1224849521371414, + "learning_rate": 2.15360575007016e-06, + "loss": 0.8247, + "step": 12926 + }, + { + "epoch": 0.7935786856564044, + "grad_norm": 0.9984305593853311, + "learning_rate": 2.1523732229734806e-06, + "loss": 0.7729, + "step": 12927 + }, + { + "epoch": 0.793640074894871, + "grad_norm": 1.086294001540674, + "learning_rate": 2.15114100613546e-06, + "loss": 0.7677, + "step": 12928 + }, + { + "epoch": 0.7937014641333374, + "grad_norm": 1.009565451531365, + "learning_rate": 2.1499090996048146e-06, + "loss": 0.7638, + "step": 12929 + }, + { + "epoch": 0.793762853371804, + "grad_norm": 1.0524457013087143, + "learning_rate": 2.1486775034302467e-06, + "loss": 0.7183, + "step": 12930 + }, + { + "epoch": 0.7938242426102704, + "grad_norm": 1.037199582284609, + "learning_rate": 2.147446217660447e-06, + "loss": 0.7336, + "step": 12931 + }, + { + "epoch": 0.793885631848737, + "grad_norm": 1.028924753203816, + "learning_rate": 2.1462152423440994e-06, + "loss": 0.787, + "step": 12932 + }, + { + "epoch": 0.7939470210872034, + "grad_norm": 1.0408317875373028, + "learning_rate": 2.1449845775298704e-06, + "loss": 0.735, + "step": 12933 + }, + { + "epoch": 0.7940084103256699, + "grad_norm": 1.058433424479194, + "learning_rate": 2.1437542232664077e-06, + "loss": 0.7695, + "step": 12934 + }, + { + "epoch": 0.7940697995641364, + "grad_norm": 1.0201971505269876, + "learning_rate": 2.142524179602362e-06, + "loss": 0.7683, + "step": 12935 + }, + { + "epoch": 0.7941311888026029, + "grad_norm": 0.9519629732068124, + "learning_rate": 2.1412944465863595e-06, + "loss": 0.7902, + "step": 12936 + }, + { + "epoch": 0.7941925780410694, + "grad_norm": 0.9846311743593665, + "learning_rate": 2.1400650242670185e-06, + "loss": 0.7123, + "step": 12937 + }, + { + "epoch": 0.7942539672795359, + "grad_norm": 0.9955579752450189, + "learning_rate": 2.138835912692946e-06, + "loss": 0.7603, + "step": 12938 + }, + { + "epoch": 0.7943153565180024, + "grad_norm": 0.8950836592462887, + "learning_rate": 2.137607111912734e-06, + "loss": 0.698, + "step": 12939 + }, + { + "epoch": 0.7943767457564689, + "grad_norm": 1.058664712825954, + "learning_rate": 2.1363786219749627e-06, + "loss": 0.7259, + "step": 12940 + }, + { + "epoch": 0.7944381349949354, + "grad_norm": 0.9849652858583423, + "learning_rate": 2.135150442928203e-06, + "loss": 0.7423, + "step": 12941 + }, + { + "epoch": 0.7944995242334019, + "grad_norm": 0.9935954708116546, + "learning_rate": 2.133922574821008e-06, + "loss": 0.7332, + "step": 12942 + }, + { + "epoch": 0.7945609134718684, + "grad_norm": 1.130457564373579, + "learning_rate": 2.1326950177019302e-06, + "loss": 0.763, + "step": 12943 + }, + { + "epoch": 0.7946223027103348, + "grad_norm": 0.9583042646019246, + "learning_rate": 2.131467771619492e-06, + "loss": 0.7556, + "step": 12944 + }, + { + "epoch": 0.7946836919488014, + "grad_norm": 1.0787970353831728, + "learning_rate": 2.1302408366222137e-06, + "loss": 0.8088, + "step": 12945 + }, + { + "epoch": 0.7947450811872678, + "grad_norm": 1.0849191587714768, + "learning_rate": 2.129014212758609e-06, + "loss": 0.7105, + "step": 12946 + }, + { + "epoch": 0.7948064704257344, + "grad_norm": 0.9767406552845944, + "learning_rate": 2.1277879000771697e-06, + "loss": 0.7768, + "step": 12947 + }, + { + "epoch": 0.7948678596642008, + "grad_norm": 1.1813956031733104, + "learning_rate": 2.126561898626377e-06, + "loss": 0.7451, + "step": 12948 + }, + { + "epoch": 0.7949292489026674, + "grad_norm": 0.8745226672619968, + "learning_rate": 2.1253362084547037e-06, + "loss": 0.7429, + "step": 12949 + }, + { + "epoch": 0.7949906381411339, + "grad_norm": 0.8500323929281688, + "learning_rate": 2.124110829610606e-06, + "loss": 0.7143, + "step": 12950 + }, + { + "epoch": 0.7950520273796003, + "grad_norm": 0.8939464487744386, + "learning_rate": 2.1228857621425314e-06, + "loss": 0.7191, + "step": 12951 + }, + { + "epoch": 0.7951134166180669, + "grad_norm": 0.9312443265552668, + "learning_rate": 2.1216610060989116e-06, + "loss": 0.763, + "step": 12952 + }, + { + "epoch": 0.7951748058565333, + "grad_norm": 0.9950357319706387, + "learning_rate": 2.1204365615281687e-06, + "loss": 0.7577, + "step": 12953 + }, + { + "epoch": 0.7952361950949999, + "grad_norm": 1.069348345187072, + "learning_rate": 2.119212428478712e-06, + "loss": 0.7382, + "step": 12954 + }, + { + "epoch": 0.7952975843334663, + "grad_norm": 0.9309905538349996, + "learning_rate": 2.1179886069989363e-06, + "loss": 0.7541, + "step": 12955 + }, + { + "epoch": 0.7953589735719329, + "grad_norm": 1.0058090421739678, + "learning_rate": 2.1167650971372254e-06, + "loss": 0.7075, + "step": 12956 + }, + { + "epoch": 0.7954203628103993, + "grad_norm": 0.9700525118240289, + "learning_rate": 2.115541898941954e-06, + "loss": 0.7594, + "step": 12957 + }, + { + "epoch": 0.7954817520488658, + "grad_norm": 1.012941606489692, + "learning_rate": 2.1143190124614845e-06, + "loss": 0.8073, + "step": 12958 + }, + { + "epoch": 0.7955431412873323, + "grad_norm": 1.116010109446644, + "learning_rate": 2.1130964377441543e-06, + "loss": 0.6979, + "step": 12959 + }, + { + "epoch": 0.7956045305257988, + "grad_norm": 1.0188252790425374, + "learning_rate": 2.1118741748383066e-06, + "loss": 0.7406, + "step": 12960 + }, + { + "epoch": 0.7956659197642654, + "grad_norm": 1.0115279942734485, + "learning_rate": 2.1106522237922612e-06, + "loss": 0.755, + "step": 12961 + }, + { + "epoch": 0.7957273090027318, + "grad_norm": 1.0251364043960138, + "learning_rate": 2.1094305846543284e-06, + "loss": 0.7346, + "step": 12962 + }, + { + "epoch": 0.7957886982411984, + "grad_norm": 1.0724877645474749, + "learning_rate": 2.108209257472806e-06, + "loss": 0.7018, + "step": 12963 + }, + { + "epoch": 0.7958500874796648, + "grad_norm": 1.1029874820430838, + "learning_rate": 2.106988242295981e-06, + "loss": 0.756, + "step": 12964 + }, + { + "epoch": 0.7959114767181313, + "grad_norm": 0.9895961147288371, + "learning_rate": 2.1057675391721255e-06, + "loss": 0.7864, + "step": 12965 + }, + { + "epoch": 0.7959728659565978, + "grad_norm": 1.071544082979369, + "learning_rate": 2.1045471481494995e-06, + "loss": 0.778, + "step": 12966 + }, + { + "epoch": 0.7960342551950643, + "grad_norm": 1.0557835634948316, + "learning_rate": 2.103327069276353e-06, + "loss": 0.7594, + "step": 12967 + }, + { + "epoch": 0.7960956444335308, + "grad_norm": 0.9800151350514825, + "learning_rate": 2.102107302600922e-06, + "loss": 0.7434, + "step": 12968 + }, + { + "epoch": 0.7961570336719973, + "grad_norm": 1.0327046509259967, + "learning_rate": 2.100887848171431e-06, + "loss": 0.7215, + "step": 12969 + }, + { + "epoch": 0.7962184229104637, + "grad_norm": 0.9365298388762935, + "learning_rate": 2.0996687060360863e-06, + "loss": 0.7588, + "step": 12970 + }, + { + "epoch": 0.7962798121489303, + "grad_norm": 1.050865031298617, + "learning_rate": 2.098449876243096e-06, + "loss": 0.7349, + "step": 12971 + }, + { + "epoch": 0.7963412013873968, + "grad_norm": 1.0953273600340272, + "learning_rate": 2.0972313588406447e-06, + "loss": 0.7875, + "step": 12972 + }, + { + "epoch": 0.7964025906258633, + "grad_norm": 0.9803916394468489, + "learning_rate": 2.096013153876899e-06, + "loss": 0.7235, + "step": 12973 + }, + { + "epoch": 0.7964639798643298, + "grad_norm": 1.0212383705117904, + "learning_rate": 2.09479526140003e-06, + "loss": 0.719, + "step": 12974 + }, + { + "epoch": 0.7965253691027963, + "grad_norm": 1.111432408352299, + "learning_rate": 2.0935776814581843e-06, + "loss": 0.772, + "step": 12975 + }, + { + "epoch": 0.7965867583412628, + "grad_norm": 1.0578045992372134, + "learning_rate": 2.092360414099499e-06, + "loss": 0.7149, + "step": 12976 + }, + { + "epoch": 0.7966481475797292, + "grad_norm": 0.9888710043125267, + "learning_rate": 2.091143459372099e-06, + "loss": 0.7255, + "step": 12977 + }, + { + "epoch": 0.7967095368181958, + "grad_norm": 0.9005931293457199, + "learning_rate": 2.0899268173240984e-06, + "loss": 0.7575, + "step": 12978 + }, + { + "epoch": 0.7967709260566622, + "grad_norm": 0.932301389357202, + "learning_rate": 2.088710488003597e-06, + "loss": 0.7432, + "step": 12979 + }, + { + "epoch": 0.7968323152951288, + "grad_norm": 1.04771464265876, + "learning_rate": 2.087494471458682e-06, + "loss": 0.748, + "step": 12980 + }, + { + "epoch": 0.7968937045335953, + "grad_norm": 0.9004132430167989, + "learning_rate": 2.0862787677374273e-06, + "loss": 0.7261, + "step": 12981 + }, + { + "epoch": 0.7969550937720618, + "grad_norm": 1.0068435815821823, + "learning_rate": 2.0850633768879034e-06, + "loss": 0.7185, + "step": 12982 + }, + { + "epoch": 0.7970164830105283, + "grad_norm": 1.040138764032876, + "learning_rate": 2.0838482989581543e-06, + "loss": 0.7221, + "step": 12983 + }, + { + "epoch": 0.7970778722489947, + "grad_norm": 0.5912418565859804, + "learning_rate": 2.082633533996217e-06, + "loss": 0.6632, + "step": 12984 + }, + { + "epoch": 0.7971392614874613, + "grad_norm": 1.198974045597515, + "learning_rate": 2.0814190820501245e-06, + "loss": 0.7854, + "step": 12985 + }, + { + "epoch": 0.7972006507259277, + "grad_norm": 0.9441306055793126, + "learning_rate": 2.0802049431678873e-06, + "loss": 0.806, + "step": 12986 + }, + { + "epoch": 0.7972620399643943, + "grad_norm": 1.123206226492296, + "learning_rate": 2.0789911173975064e-06, + "loss": 0.7511, + "step": 12987 + }, + { + "epoch": 0.7973234292028607, + "grad_norm": 1.0088522233535868, + "learning_rate": 2.07777760478697e-06, + "loss": 0.7127, + "step": 12988 + }, + { + "epoch": 0.7973848184413272, + "grad_norm": 1.1020267829508588, + "learning_rate": 2.0765644053842583e-06, + "loss": 0.7034, + "step": 12989 + }, + { + "epoch": 0.7974462076797937, + "grad_norm": 0.9746773551323211, + "learning_rate": 2.0753515192373307e-06, + "loss": 0.7829, + "step": 12990 + }, + { + "epoch": 0.7975075969182602, + "grad_norm": 1.0211554046032323, + "learning_rate": 2.074138946394143e-06, + "loss": 0.7626, + "step": 12991 + }, + { + "epoch": 0.7975689861567268, + "grad_norm": 1.0095655123727907, + "learning_rate": 2.072926686902633e-06, + "loss": 0.724, + "step": 12992 + }, + { + "epoch": 0.7976303753951932, + "grad_norm": 1.0483639988027393, + "learning_rate": 2.0717147408107284e-06, + "loss": 0.767, + "step": 12993 + }, + { + "epoch": 0.7976917646336598, + "grad_norm": 1.0136222246473277, + "learning_rate": 2.070503108166343e-06, + "loss": 0.7158, + "step": 12994 + }, + { + "epoch": 0.7977531538721262, + "grad_norm": 1.0260521332244894, + "learning_rate": 2.069291789017377e-06, + "loss": 0.7603, + "step": 12995 + }, + { + "epoch": 0.7978145431105927, + "grad_norm": 1.009138221270783, + "learning_rate": 2.0680807834117258e-06, + "loss": 0.7744, + "step": 12996 + }, + { + "epoch": 0.7978759323490592, + "grad_norm": 0.9137614440957462, + "learning_rate": 2.0668700913972674e-06, + "loss": 0.7222, + "step": 12997 + }, + { + "epoch": 0.7979373215875257, + "grad_norm": 0.967374610584622, + "learning_rate": 2.065659713021857e-06, + "loss": 0.7681, + "step": 12998 + }, + { + "epoch": 0.7979987108259922, + "grad_norm": 1.1245877782159386, + "learning_rate": 2.0644496483333576e-06, + "loss": 0.7049, + "step": 12999 + }, + { + "epoch": 0.7980601000644587, + "grad_norm": 1.0201542592192967, + "learning_rate": 2.0632398973796052e-06, + "loss": 0.6774, + "step": 13000 + }, + { + "epoch": 0.7981214893029251, + "grad_norm": 1.1100925956177636, + "learning_rate": 2.0620304602084297e-06, + "loss": 0.7193, + "step": 13001 + }, + { + "epoch": 0.7981828785413917, + "grad_norm": 0.9487404674029689, + "learning_rate": 2.0608213368676444e-06, + "loss": 0.7327, + "step": 13002 + }, + { + "epoch": 0.7982442677798582, + "grad_norm": 1.0950061561627618, + "learning_rate": 2.0596125274050537e-06, + "loss": 0.764, + "step": 13003 + }, + { + "epoch": 0.7983056570183247, + "grad_norm": 0.9721212372348683, + "learning_rate": 2.058404031868447e-06, + "loss": 0.7605, + "step": 13004 + }, + { + "epoch": 0.7983670462567912, + "grad_norm": 1.0055423037644844, + "learning_rate": 2.0571958503056044e-06, + "loss": 0.7407, + "step": 13005 + }, + { + "epoch": 0.7984284354952577, + "grad_norm": 0.9774302541877329, + "learning_rate": 2.0559879827642894e-06, + "loss": 0.7879, + "step": 13006 + }, + { + "epoch": 0.7984898247337242, + "grad_norm": 1.0154916734088084, + "learning_rate": 2.05478042929226e-06, + "loss": 0.7374, + "step": 13007 + }, + { + "epoch": 0.7985512139721906, + "grad_norm": 0.979226343772416, + "learning_rate": 2.0535731899372536e-06, + "loss": 0.8009, + "step": 13008 + }, + { + "epoch": 0.7986126032106572, + "grad_norm": 0.5746905186706963, + "learning_rate": 2.0523662647469954e-06, + "loss": 0.6674, + "step": 13009 + }, + { + "epoch": 0.7986739924491236, + "grad_norm": 0.7636019542111444, + "learning_rate": 2.0511596537692093e-06, + "loss": 0.7458, + "step": 13010 + }, + { + "epoch": 0.7987353816875902, + "grad_norm": 0.9441090224570444, + "learning_rate": 2.049953357051595e-06, + "loss": 0.7625, + "step": 13011 + }, + { + "epoch": 0.7987967709260566, + "grad_norm": 1.030208842907448, + "learning_rate": 2.048747374641844e-06, + "loss": 0.7624, + "step": 13012 + }, + { + "epoch": 0.7988581601645232, + "grad_norm": 1.0072636652896927, + "learning_rate": 2.047541706587637e-06, + "loss": 0.7344, + "step": 13013 + }, + { + "epoch": 0.7989195494029897, + "grad_norm": 1.0973577153433471, + "learning_rate": 2.0463363529366375e-06, + "loss": 0.7362, + "step": 13014 + }, + { + "epoch": 0.7989809386414561, + "grad_norm": 1.027080672643261, + "learning_rate": 2.0451313137365016e-06, + "loss": 0.7593, + "step": 13015 + }, + { + "epoch": 0.7990423278799227, + "grad_norm": 1.11588296453516, + "learning_rate": 2.0439265890348705e-06, + "loss": 0.7737, + "step": 13016 + }, + { + "epoch": 0.7991037171183891, + "grad_norm": 1.1626172250916182, + "learning_rate": 2.0427221788793736e-06, + "loss": 0.8028, + "step": 13017 + }, + { + "epoch": 0.7991651063568557, + "grad_norm": 0.9986527622323703, + "learning_rate": 2.0415180833176275e-06, + "loss": 0.7483, + "step": 13018 + }, + { + "epoch": 0.7992264955953221, + "grad_norm": 0.9998525339772598, + "learning_rate": 2.040314302397236e-06, + "loss": 0.7153, + "step": 13019 + }, + { + "epoch": 0.7992878848337887, + "grad_norm": 0.9702310734490961, + "learning_rate": 2.0391108361657898e-06, + "loss": 0.7056, + "step": 13020 + }, + { + "epoch": 0.7993492740722551, + "grad_norm": 1.1471065531733569, + "learning_rate": 2.0379076846708725e-06, + "loss": 0.7639, + "step": 13021 + }, + { + "epoch": 0.7994106633107216, + "grad_norm": 0.9017143168579558, + "learning_rate": 2.0367048479600503e-06, + "loss": 0.6871, + "step": 13022 + }, + { + "epoch": 0.7994720525491881, + "grad_norm": 0.9368538629374081, + "learning_rate": 2.0355023260808713e-06, + "loss": 0.7194, + "step": 13023 + }, + { + "epoch": 0.7995334417876546, + "grad_norm": 0.9065245414106619, + "learning_rate": 2.0343001190808864e-06, + "loss": 0.685, + "step": 13024 + }, + { + "epoch": 0.7995948310261212, + "grad_norm": 1.1019584037821022, + "learning_rate": 2.0330982270076204e-06, + "loss": 0.7403, + "step": 13025 + }, + { + "epoch": 0.7996562202645876, + "grad_norm": 0.9356185205071789, + "learning_rate": 2.031896649908591e-06, + "loss": 0.7424, + "step": 13026 + }, + { + "epoch": 0.7997176095030541, + "grad_norm": 0.9780021347954473, + "learning_rate": 2.030695387831304e-06, + "loss": 0.7025, + "step": 13027 + }, + { + "epoch": 0.7997789987415206, + "grad_norm": 1.006981330532955, + "learning_rate": 2.0294944408232508e-06, + "loss": 0.7802, + "step": 13028 + }, + { + "epoch": 0.7998403879799871, + "grad_norm": 0.892447894537189, + "learning_rate": 2.0282938089319125e-06, + "loss": 0.708, + "step": 13029 + }, + { + "epoch": 0.7999017772184536, + "grad_norm": 0.9060530970570748, + "learning_rate": 2.0270934922047547e-06, + "loss": 0.7196, + "step": 13030 + }, + { + "epoch": 0.7999631664569201, + "grad_norm": 1.003183643423875, + "learning_rate": 2.0258934906892335e-06, + "loss": 0.7167, + "step": 13031 + }, + { + "epoch": 0.8000245556953866, + "grad_norm": 1.0351777114206293, + "learning_rate": 2.0246938044327913e-06, + "loss": 0.7012, + "step": 13032 + }, + { + "epoch": 0.8000859449338531, + "grad_norm": 0.6232908991288253, + "learning_rate": 2.0234944334828577e-06, + "loss": 0.7028, + "step": 13033 + }, + { + "epoch": 0.8001473341723196, + "grad_norm": 1.0666111652926349, + "learning_rate": 2.0222953778868483e-06, + "loss": 0.7615, + "step": 13034 + }, + { + "epoch": 0.8002087234107861, + "grad_norm": 0.9448639799349575, + "learning_rate": 2.0210966376921724e-06, + "loss": 0.7542, + "step": 13035 + }, + { + "epoch": 0.8002701126492526, + "grad_norm": 1.0429337051246996, + "learning_rate": 2.019898212946223e-06, + "loss": 0.7332, + "step": 13036 + }, + { + "epoch": 0.8003315018877191, + "grad_norm": 0.948563686948442, + "learning_rate": 2.0187001036963736e-06, + "loss": 0.6756, + "step": 13037 + }, + { + "epoch": 0.8003928911261856, + "grad_norm": 0.9979153517344892, + "learning_rate": 2.017502309989998e-06, + "loss": 0.712, + "step": 13038 + }, + { + "epoch": 0.800454280364652, + "grad_norm": 1.0807961931390184, + "learning_rate": 2.016304831874449e-06, + "loss": 0.7935, + "step": 13039 + }, + { + "epoch": 0.8005156696031186, + "grad_norm": 1.0199585185026125, + "learning_rate": 2.015107669397072e-06, + "loss": 0.8067, + "step": 13040 + }, + { + "epoch": 0.800577058841585, + "grad_norm": 1.0096425651570478, + "learning_rate": 2.0139108226051927e-06, + "loss": 0.7203, + "step": 13041 + }, + { + "epoch": 0.8006384480800516, + "grad_norm": 1.1058453841838634, + "learning_rate": 2.0127142915461318e-06, + "loss": 0.765, + "step": 13042 + }, + { + "epoch": 0.800699837318518, + "grad_norm": 1.0356444039437183, + "learning_rate": 2.011518076267195e-06, + "loss": 0.757, + "step": 13043 + }, + { + "epoch": 0.8007612265569846, + "grad_norm": 1.0373259032167959, + "learning_rate": 2.010322176815672e-06, + "loss": 0.7902, + "step": 13044 + }, + { + "epoch": 0.8008226157954511, + "grad_norm": 0.9579644071719168, + "learning_rate": 2.009126593238845e-06, + "loss": 0.7345, + "step": 13045 + }, + { + "epoch": 0.8008840050339175, + "grad_norm": 0.946849256984049, + "learning_rate": 2.007931325583985e-06, + "loss": 0.7236, + "step": 13046 + }, + { + "epoch": 0.8009453942723841, + "grad_norm": 1.0213109523000363, + "learning_rate": 2.0067363738983427e-06, + "loss": 0.7562, + "step": 13047 + }, + { + "epoch": 0.8010067835108505, + "grad_norm": 1.0130165999330931, + "learning_rate": 2.00554173822916e-06, + "loss": 0.731, + "step": 13048 + }, + { + "epoch": 0.8010681727493171, + "grad_norm": 1.012794497562153, + "learning_rate": 2.0043474186236723e-06, + "loss": 0.7511, + "step": 13049 + }, + { + "epoch": 0.8011295619877835, + "grad_norm": 1.0050036969014073, + "learning_rate": 2.0031534151290944e-06, + "loss": 0.6813, + "step": 13050 + }, + { + "epoch": 0.8011909512262501, + "grad_norm": 0.9764850480101952, + "learning_rate": 2.001959727792633e-06, + "loss": 0.7117, + "step": 13051 + }, + { + "epoch": 0.8012523404647165, + "grad_norm": 0.9244590426195568, + "learning_rate": 2.0007663566614797e-06, + "loss": 0.731, + "step": 13052 + }, + { + "epoch": 0.801313729703183, + "grad_norm": 1.0093931088418255, + "learning_rate": 1.9995733017828146e-06, + "loss": 0.745, + "step": 13053 + }, + { + "epoch": 0.8013751189416495, + "grad_norm": 1.071266385646159, + "learning_rate": 1.998380563203807e-06, + "loss": 0.6962, + "step": 13054 + }, + { + "epoch": 0.801436508180116, + "grad_norm": 0.993052925950188, + "learning_rate": 1.997188140971611e-06, + "loss": 0.7393, + "step": 13055 + }, + { + "epoch": 0.8014978974185826, + "grad_norm": 1.0283225171665034, + "learning_rate": 1.9959960351333706e-06, + "loss": 0.8008, + "step": 13056 + }, + { + "epoch": 0.801559286657049, + "grad_norm": 1.1250933583682354, + "learning_rate": 1.9948042457362148e-06, + "loss": 0.7375, + "step": 13057 + }, + { + "epoch": 0.8016206758955156, + "grad_norm": 1.071909883362814, + "learning_rate": 1.9936127728272615e-06, + "loss": 0.7565, + "step": 13058 + }, + { + "epoch": 0.801682065133982, + "grad_norm": 1.050478316318269, + "learning_rate": 1.9924216164536135e-06, + "loss": 0.7583, + "step": 13059 + }, + { + "epoch": 0.8017434543724485, + "grad_norm": 1.0549997552473303, + "learning_rate": 1.991230776662371e-06, + "loss": 0.7524, + "step": 13060 + }, + { + "epoch": 0.801804843610915, + "grad_norm": 1.1303149383997888, + "learning_rate": 1.9900402535006115e-06, + "loss": 0.7571, + "step": 13061 + }, + { + "epoch": 0.8018662328493815, + "grad_norm": 0.8891773536169607, + "learning_rate": 1.9888500470153947e-06, + "loss": 0.7137, + "step": 13062 + }, + { + "epoch": 0.801927622087848, + "grad_norm": 0.9077718917679112, + "learning_rate": 1.9876601572537857e-06, + "loss": 0.7471, + "step": 13063 + }, + { + "epoch": 0.8019890113263145, + "grad_norm": 0.9696190981974125, + "learning_rate": 1.986470584262824e-06, + "loss": 0.8257, + "step": 13064 + }, + { + "epoch": 0.8020504005647809, + "grad_norm": 0.9366444068396657, + "learning_rate": 1.985281328089539e-06, + "loss": 0.7238, + "step": 13065 + }, + { + "epoch": 0.8021117898032475, + "grad_norm": 1.0531131972243326, + "learning_rate": 1.9840923887809492e-06, + "loss": 0.7348, + "step": 13066 + }, + { + "epoch": 0.802173179041714, + "grad_norm": 1.0253967082375735, + "learning_rate": 1.9829037663840587e-06, + "loss": 0.6798, + "step": 13067 + }, + { + "epoch": 0.8022345682801805, + "grad_norm": 1.0258783560826468, + "learning_rate": 1.9817154609458624e-06, + "loss": 0.7817, + "step": 13068 + }, + { + "epoch": 0.802295957518647, + "grad_norm": 1.0559939521228692, + "learning_rate": 1.980527472513337e-06, + "loss": 0.7907, + "step": 13069 + }, + { + "epoch": 0.8023573467571135, + "grad_norm": 0.9833412067672038, + "learning_rate": 1.9793398011334497e-06, + "loss": 0.7152, + "step": 13070 + }, + { + "epoch": 0.80241873599558, + "grad_norm": 0.9416720319888027, + "learning_rate": 1.9781524468531634e-06, + "loss": 0.7542, + "step": 13071 + }, + { + "epoch": 0.8024801252340464, + "grad_norm": 1.1513440732364486, + "learning_rate": 1.9769654097194114e-06, + "loss": 0.7278, + "step": 13072 + }, + { + "epoch": 0.802541514472513, + "grad_norm": 1.128462124310145, + "learning_rate": 1.975778689779124e-06, + "loss": 0.7518, + "step": 13073 + }, + { + "epoch": 0.8026029037109794, + "grad_norm": 1.0041507609555165, + "learning_rate": 1.9745922870792245e-06, + "loss": 0.7701, + "step": 13074 + }, + { + "epoch": 0.802664292949446, + "grad_norm": 1.0432120937939195, + "learning_rate": 1.9734062016666145e-06, + "loss": 0.7075, + "step": 13075 + }, + { + "epoch": 0.8027256821879124, + "grad_norm": 0.9795916941265845, + "learning_rate": 1.972220433588188e-06, + "loss": 0.761, + "step": 13076 + }, + { + "epoch": 0.802787071426379, + "grad_norm": 1.0052599396265622, + "learning_rate": 1.9710349828908215e-06, + "loss": 0.7275, + "step": 13077 + }, + { + "epoch": 0.8028484606648455, + "grad_norm": 1.0046972604167925, + "learning_rate": 1.9698498496213847e-06, + "loss": 0.7586, + "step": 13078 + }, + { + "epoch": 0.8029098499033119, + "grad_norm": 1.0960688130869005, + "learning_rate": 1.968665033826732e-06, + "loss": 0.804, + "step": 13079 + }, + { + "epoch": 0.8029712391417785, + "grad_norm": 0.9472074100474817, + "learning_rate": 1.967480535553703e-06, + "loss": 0.7254, + "step": 13080 + }, + { + "epoch": 0.8030326283802449, + "grad_norm": 1.0509097608583093, + "learning_rate": 1.966296354849133e-06, + "loss": 0.7664, + "step": 13081 + }, + { + "epoch": 0.8030940176187115, + "grad_norm": 0.9328128766478485, + "learning_rate": 1.965112491759834e-06, + "loss": 0.7234, + "step": 13082 + }, + { + "epoch": 0.8031554068571779, + "grad_norm": 0.8948687036038256, + "learning_rate": 1.9639289463326118e-06, + "loss": 0.7589, + "step": 13083 + }, + { + "epoch": 0.8032167960956444, + "grad_norm": 1.058069564264892, + "learning_rate": 1.962745718614255e-06, + "loss": 0.7335, + "step": 13084 + }, + { + "epoch": 0.8032781853341109, + "grad_norm": 1.1354533582198636, + "learning_rate": 1.9615628086515494e-06, + "loss": 0.7348, + "step": 13085 + }, + { + "epoch": 0.8033395745725774, + "grad_norm": 1.1263865252102472, + "learning_rate": 1.960380216491261e-06, + "loss": 0.7195, + "step": 13086 + }, + { + "epoch": 0.803400963811044, + "grad_norm": 0.9555468904358928, + "learning_rate": 1.9591979421801353e-06, + "loss": 0.7482, + "step": 13087 + }, + { + "epoch": 0.8034623530495104, + "grad_norm": 0.9952742699223766, + "learning_rate": 1.958015985764924e-06, + "loss": 0.7658, + "step": 13088 + }, + { + "epoch": 0.803523742287977, + "grad_norm": 0.9551255388633179, + "learning_rate": 1.9568343472923524e-06, + "loss": 0.6841, + "step": 13089 + }, + { + "epoch": 0.8035851315264434, + "grad_norm": 0.9480248495600404, + "learning_rate": 1.9556530268091365e-06, + "loss": 0.6879, + "step": 13090 + }, + { + "epoch": 0.8036465207649099, + "grad_norm": 0.9765524371226247, + "learning_rate": 1.9544720243619806e-06, + "loss": 0.7096, + "step": 13091 + }, + { + "epoch": 0.8037079100033764, + "grad_norm": 1.0500630535569948, + "learning_rate": 1.953291339997576e-06, + "loss": 0.7234, + "step": 13092 + }, + { + "epoch": 0.8037692992418429, + "grad_norm": 0.568923393002938, + "learning_rate": 1.952110973762602e-06, + "loss": 0.6349, + "step": 13093 + }, + { + "epoch": 0.8038306884803094, + "grad_norm": 1.0450343371619486, + "learning_rate": 1.9509309257037244e-06, + "loss": 0.774, + "step": 13094 + }, + { + "epoch": 0.8038920777187759, + "grad_norm": 0.9796358956707599, + "learning_rate": 1.9497511958675943e-06, + "loss": 0.7247, + "step": 13095 + }, + { + "epoch": 0.8039534669572423, + "grad_norm": 1.0455217899521196, + "learning_rate": 1.948571784300859e-06, + "loss": 0.7319, + "step": 13096 + }, + { + "epoch": 0.8040148561957089, + "grad_norm": 1.10879775282886, + "learning_rate": 1.947392691050142e-06, + "loss": 0.753, + "step": 13097 + }, + { + "epoch": 0.8040762454341754, + "grad_norm": 0.9397618439966474, + "learning_rate": 1.9462139161620575e-06, + "loss": 0.7154, + "step": 13098 + }, + { + "epoch": 0.8041376346726419, + "grad_norm": 1.0576004863682296, + "learning_rate": 1.9450354596832134e-06, + "loss": 0.7435, + "step": 13099 + }, + { + "epoch": 0.8041990239111084, + "grad_norm": 1.0876474359953539, + "learning_rate": 1.943857321660202e-06, + "loss": 0.7454, + "step": 13100 + }, + { + "epoch": 0.8042604131495749, + "grad_norm": 1.0429890066864154, + "learning_rate": 1.9426795021395915e-06, + "loss": 0.7768, + "step": 13101 + }, + { + "epoch": 0.8043218023880414, + "grad_norm": 1.0796872701267612, + "learning_rate": 1.9415020011679577e-06, + "loss": 0.7289, + "step": 13102 + }, + { + "epoch": 0.8043831916265078, + "grad_norm": 1.092543410575548, + "learning_rate": 1.9403248187918487e-06, + "loss": 0.7886, + "step": 13103 + }, + { + "epoch": 0.8044445808649744, + "grad_norm": 1.0181468610866444, + "learning_rate": 1.9391479550578064e-06, + "loss": 0.7222, + "step": 13104 + }, + { + "epoch": 0.8045059701034408, + "grad_norm": 1.015755308337341, + "learning_rate": 1.937971410012358e-06, + "loss": 0.7558, + "step": 13105 + }, + { + "epoch": 0.8045673593419074, + "grad_norm": 0.9559282351552778, + "learning_rate": 1.936795183702018e-06, + "loss": 0.7556, + "step": 13106 + }, + { + "epoch": 0.8046287485803738, + "grad_norm": 0.9685435934888776, + "learning_rate": 1.9356192761732904e-06, + "loss": 0.7687, + "step": 13107 + }, + { + "epoch": 0.8046901378188404, + "grad_norm": 1.0700012398835717, + "learning_rate": 1.9344436874726637e-06, + "loss": 0.7219, + "step": 13108 + }, + { + "epoch": 0.8047515270573069, + "grad_norm": 1.0233880862660576, + "learning_rate": 1.9332684176466134e-06, + "loss": 0.7771, + "step": 13109 + }, + { + "epoch": 0.8048129162957733, + "grad_norm": 1.0473888226615085, + "learning_rate": 1.9320934667416103e-06, + "loss": 0.7249, + "step": 13110 + }, + { + "epoch": 0.8048743055342399, + "grad_norm": 1.0087979747447995, + "learning_rate": 1.930918834804102e-06, + "loss": 0.7483, + "step": 13111 + }, + { + "epoch": 0.8049356947727063, + "grad_norm": 0.975552558559491, + "learning_rate": 1.9297445218805246e-06, + "loss": 0.6934, + "step": 13112 + }, + { + "epoch": 0.8049970840111729, + "grad_norm": 0.9078875757747821, + "learning_rate": 1.9285705280173115e-06, + "loss": 0.7621, + "step": 13113 + }, + { + "epoch": 0.8050584732496393, + "grad_norm": 0.9989834784157726, + "learning_rate": 1.9273968532608754e-06, + "loss": 0.7939, + "step": 13114 + }, + { + "epoch": 0.8051198624881059, + "grad_norm": 0.9112280201583104, + "learning_rate": 1.9262234976576168e-06, + "loss": 0.7444, + "step": 13115 + }, + { + "epoch": 0.8051812517265723, + "grad_norm": 1.0571658962155783, + "learning_rate": 1.9250504612539246e-06, + "loss": 0.7955, + "step": 13116 + }, + { + "epoch": 0.8052426409650388, + "grad_norm": 0.9300163686430685, + "learning_rate": 1.923877744096175e-06, + "loss": 0.7297, + "step": 13117 + }, + { + "epoch": 0.8053040302035053, + "grad_norm": 0.9495959778652583, + "learning_rate": 1.9227053462307334e-06, + "loss": 0.7377, + "step": 13118 + }, + { + "epoch": 0.8053654194419718, + "grad_norm": 1.1323663499565362, + "learning_rate": 1.921533267703947e-06, + "loss": 0.7438, + "step": 13119 + }, + { + "epoch": 0.8054268086804384, + "grad_norm": 1.043449228162514, + "learning_rate": 1.9203615085621618e-06, + "loss": 0.7261, + "step": 13120 + }, + { + "epoch": 0.8054881979189048, + "grad_norm": 1.0500608403547445, + "learning_rate": 1.9191900688516973e-06, + "loss": 0.7553, + "step": 13121 + }, + { + "epoch": 0.8055495871573713, + "grad_norm": 0.8630125750169073, + "learning_rate": 1.9180189486188683e-06, + "loss": 0.7119, + "step": 13122 + }, + { + "epoch": 0.8056109763958378, + "grad_norm": 1.080786888650746, + "learning_rate": 1.9168481479099733e-06, + "loss": 0.7538, + "step": 13123 + }, + { + "epoch": 0.8056723656343043, + "grad_norm": 1.0099317991240915, + "learning_rate": 1.915677666771305e-06, + "loss": 0.7603, + "step": 13124 + }, + { + "epoch": 0.8057337548727708, + "grad_norm": 0.9543799480348886, + "learning_rate": 1.914507505249139e-06, + "loss": 0.6832, + "step": 13125 + }, + { + "epoch": 0.8057951441112373, + "grad_norm": 1.1448914351024189, + "learning_rate": 1.9133376633897303e-06, + "loss": 0.7783, + "step": 13126 + }, + { + "epoch": 0.8058565333497038, + "grad_norm": 1.0506977272441294, + "learning_rate": 1.9121681412393377e-06, + "loss": 0.7095, + "step": 13127 + }, + { + "epoch": 0.8059179225881703, + "grad_norm": 0.8980775953209793, + "learning_rate": 1.910998938844194e-06, + "loss": 0.7003, + "step": 13128 + }, + { + "epoch": 0.8059793118266367, + "grad_norm": 1.0687842475431337, + "learning_rate": 1.9098300562505266e-06, + "loss": 0.7259, + "step": 13129 + }, + { + "epoch": 0.8060407010651033, + "grad_norm": 0.6083592453071798, + "learning_rate": 1.9086614935045453e-06, + "loss": 0.664, + "step": 13130 + }, + { + "epoch": 0.8061020903035698, + "grad_norm": 1.0819904052103702, + "learning_rate": 1.907493250652451e-06, + "loss": 0.7605, + "step": 13131 + }, + { + "epoch": 0.8061634795420363, + "grad_norm": 0.901067125810709, + "learning_rate": 1.9063253277404304e-06, + "loss": 0.7326, + "step": 13132 + }, + { + "epoch": 0.8062248687805028, + "grad_norm": 0.8580503537232251, + "learning_rate": 1.905157724814658e-06, + "loss": 0.7333, + "step": 13133 + }, + { + "epoch": 0.8062862580189692, + "grad_norm": 1.068606024462578, + "learning_rate": 1.9039904419212917e-06, + "loss": 0.7658, + "step": 13134 + }, + { + "epoch": 0.8063476472574358, + "grad_norm": 1.0115106734984531, + "learning_rate": 1.9028234791064891e-06, + "loss": 0.7617, + "step": 13135 + }, + { + "epoch": 0.8064090364959022, + "grad_norm": 0.9404131350189544, + "learning_rate": 1.901656836416379e-06, + "loss": 0.7324, + "step": 13136 + }, + { + "epoch": 0.8064704257343688, + "grad_norm": 0.9699621241050986, + "learning_rate": 1.9004905138970842e-06, + "loss": 0.7668, + "step": 13137 + }, + { + "epoch": 0.8065318149728352, + "grad_norm": 0.9280491398656192, + "learning_rate": 1.8993245115947212e-06, + "loss": 0.7336, + "step": 13138 + }, + { + "epoch": 0.8065932042113018, + "grad_norm": 1.1355985492732452, + "learning_rate": 1.8981588295553855e-06, + "loss": 0.7515, + "step": 13139 + }, + { + "epoch": 0.8066545934497683, + "grad_norm": 0.9497395981947611, + "learning_rate": 1.8969934678251633e-06, + "loss": 0.6679, + "step": 13140 + }, + { + "epoch": 0.8067159826882347, + "grad_norm": 0.8942117779006938, + "learning_rate": 1.895828426450127e-06, + "loss": 0.7426, + "step": 13141 + }, + { + "epoch": 0.8067773719267013, + "grad_norm": 1.0643657122790822, + "learning_rate": 1.8946637054763372e-06, + "loss": 0.715, + "step": 13142 + }, + { + "epoch": 0.8068387611651677, + "grad_norm": 0.9994780594728088, + "learning_rate": 1.8934993049498418e-06, + "loss": 0.7465, + "step": 13143 + }, + { + "epoch": 0.8069001504036343, + "grad_norm": 1.1687214727072204, + "learning_rate": 1.8923352249166726e-06, + "loss": 0.7685, + "step": 13144 + }, + { + "epoch": 0.8069615396421007, + "grad_norm": 1.001521674718369, + "learning_rate": 1.8911714654228608e-06, + "loss": 0.7378, + "step": 13145 + }, + { + "epoch": 0.8070229288805673, + "grad_norm": 1.054448896702973, + "learning_rate": 1.890008026514406e-06, + "loss": 0.7358, + "step": 13146 + }, + { + "epoch": 0.8070843181190337, + "grad_norm": 0.9986448452744302, + "learning_rate": 1.8888449082373106e-06, + "loss": 0.8056, + "step": 13147 + }, + { + "epoch": 0.8071457073575002, + "grad_norm": 1.0778708507294819, + "learning_rate": 1.8876821106375543e-06, + "loss": 0.7157, + "step": 13148 + }, + { + "epoch": 0.8072070965959667, + "grad_norm": 1.0375357065391746, + "learning_rate": 1.8865196337611136e-06, + "loss": 0.6859, + "step": 13149 + }, + { + "epoch": 0.8072684858344332, + "grad_norm": 0.9623401529327144, + "learning_rate": 1.8853574776539497e-06, + "loss": 0.7004, + "step": 13150 + }, + { + "epoch": 0.8073298750728998, + "grad_norm": 1.1014444065640452, + "learning_rate": 1.884195642361999e-06, + "loss": 0.7525, + "step": 13151 + }, + { + "epoch": 0.8073912643113662, + "grad_norm": 1.0662111639742897, + "learning_rate": 1.8830341279312037e-06, + "loss": 0.7528, + "step": 13152 + }, + { + "epoch": 0.8074526535498328, + "grad_norm": 0.5546544280925123, + "learning_rate": 1.8818729344074815e-06, + "loss": 0.5901, + "step": 13153 + }, + { + "epoch": 0.8075140427882992, + "grad_norm": 1.0985493312957801, + "learning_rate": 1.8807120618367414e-06, + "loss": 0.7573, + "step": 13154 + }, + { + "epoch": 0.8075754320267657, + "grad_norm": 1.0357192030733946, + "learning_rate": 1.8795515102648787e-06, + "loss": 0.7459, + "step": 13155 + }, + { + "epoch": 0.8076368212652322, + "grad_norm": 1.0010998739057686, + "learning_rate": 1.8783912797377758e-06, + "loss": 0.7591, + "step": 13156 + }, + { + "epoch": 0.8076982105036987, + "grad_norm": 1.1674841312306499, + "learning_rate": 1.8772313703013024e-06, + "loss": 0.7832, + "step": 13157 + }, + { + "epoch": 0.8077595997421652, + "grad_norm": 1.008700133656309, + "learning_rate": 1.8760717820013142e-06, + "loss": 0.7516, + "step": 13158 + }, + { + "epoch": 0.8078209889806317, + "grad_norm": 1.0271281518338455, + "learning_rate": 1.874912514883661e-06, + "loss": 0.7388, + "step": 13159 + }, + { + "epoch": 0.8078823782190981, + "grad_norm": 0.9576965187441088, + "learning_rate": 1.8737535689941756e-06, + "loss": 0.7363, + "step": 13160 + }, + { + "epoch": 0.8079437674575647, + "grad_norm": 0.9777236447096324, + "learning_rate": 1.8725949443786707e-06, + "loss": 0.7138, + "step": 13161 + }, + { + "epoch": 0.8080051566960312, + "grad_norm": 0.9540006443342338, + "learning_rate": 1.8714366410829531e-06, + "loss": 0.7585, + "step": 13162 + }, + { + "epoch": 0.8080665459344977, + "grad_norm": 0.9919805943889429, + "learning_rate": 1.8702786591528222e-06, + "loss": 0.6886, + "step": 13163 + }, + { + "epoch": 0.8081279351729642, + "grad_norm": 0.9624145458045819, + "learning_rate": 1.8691209986340598e-06, + "loss": 0.7411, + "step": 13164 + }, + { + "epoch": 0.8081893244114307, + "grad_norm": 0.9862222532622522, + "learning_rate": 1.867963659572426e-06, + "loss": 0.7014, + "step": 13165 + }, + { + "epoch": 0.8082507136498972, + "grad_norm": 0.9717015275068092, + "learning_rate": 1.8668066420136843e-06, + "loss": 0.7237, + "step": 13166 + }, + { + "epoch": 0.8083121028883636, + "grad_norm": 0.9716245359751935, + "learning_rate": 1.865649946003576e-06, + "loss": 0.6997, + "step": 13167 + }, + { + "epoch": 0.8083734921268302, + "grad_norm": 0.9486907955115595, + "learning_rate": 1.8644935715878298e-06, + "loss": 0.7486, + "step": 13168 + }, + { + "epoch": 0.8084348813652966, + "grad_norm": 1.0362948878858629, + "learning_rate": 1.863337518812165e-06, + "loss": 0.7704, + "step": 13169 + }, + { + "epoch": 0.8084962706037632, + "grad_norm": 0.9408199225392252, + "learning_rate": 1.862181787722287e-06, + "loss": 0.7364, + "step": 13170 + }, + { + "epoch": 0.8085576598422296, + "grad_norm": 0.9798525430551893, + "learning_rate": 1.861026378363886e-06, + "loss": 0.7923, + "step": 13171 + }, + { + "epoch": 0.8086190490806962, + "grad_norm": 0.9248853082741031, + "learning_rate": 1.8598712907826421e-06, + "loss": 0.7478, + "step": 13172 + }, + { + "epoch": 0.8086804383191627, + "grad_norm": 1.0445497586743397, + "learning_rate": 1.8587165250242211e-06, + "loss": 0.7681, + "step": 13173 + }, + { + "epoch": 0.8087418275576291, + "grad_norm": 1.0158414254336656, + "learning_rate": 1.857562081134283e-06, + "loss": 0.7299, + "step": 13174 + }, + { + "epoch": 0.8088032167960957, + "grad_norm": 1.0232774158834104, + "learning_rate": 1.8564079591584628e-06, + "loss": 0.7152, + "step": 13175 + }, + { + "epoch": 0.8088646060345621, + "grad_norm": 0.9493882470301027, + "learning_rate": 1.8552541591423868e-06, + "loss": 0.7219, + "step": 13176 + }, + { + "epoch": 0.8089259952730287, + "grad_norm": 1.0034279158122963, + "learning_rate": 1.8541006811316787e-06, + "loss": 0.7295, + "step": 13177 + }, + { + "epoch": 0.8089873845114951, + "grad_norm": 0.9785687608652395, + "learning_rate": 1.8529475251719386e-06, + "loss": 0.7398, + "step": 13178 + }, + { + "epoch": 0.8090487737499616, + "grad_norm": 1.0734297792800553, + "learning_rate": 1.851794691308756e-06, + "loss": 0.7005, + "step": 13179 + }, + { + "epoch": 0.8091101629884281, + "grad_norm": 1.0620074939645672, + "learning_rate": 1.8506421795877082e-06, + "loss": 0.7462, + "step": 13180 + }, + { + "epoch": 0.8091715522268946, + "grad_norm": 0.9898146121253777, + "learning_rate": 1.8494899900543606e-06, + "loss": 0.7647, + "step": 13181 + }, + { + "epoch": 0.8092329414653612, + "grad_norm": 1.0821941628144847, + "learning_rate": 1.8483381227542663e-06, + "loss": 0.7411, + "step": 13182 + }, + { + "epoch": 0.8092943307038276, + "grad_norm": 1.0141089087080428, + "learning_rate": 1.8471865777329624e-06, + "loss": 0.7568, + "step": 13183 + }, + { + "epoch": 0.8093557199422942, + "grad_norm": 1.0123333257616924, + "learning_rate": 1.8460353550359811e-06, + "loss": 0.696, + "step": 13184 + }, + { + "epoch": 0.8094171091807606, + "grad_norm": 1.0221418151960528, + "learning_rate": 1.8448844547088307e-06, + "loss": 0.7402, + "step": 13185 + }, + { + "epoch": 0.8094784984192271, + "grad_norm": 1.0080614726153467, + "learning_rate": 1.8437338767970147e-06, + "loss": 0.6936, + "step": 13186 + }, + { + "epoch": 0.8095398876576936, + "grad_norm": 1.002977589406344, + "learning_rate": 1.842583621346019e-06, + "loss": 0.7739, + "step": 13187 + }, + { + "epoch": 0.8096012768961601, + "grad_norm": 1.1038410997360106, + "learning_rate": 1.8414336884013239e-06, + "loss": 0.772, + "step": 13188 + }, + { + "epoch": 0.8096626661346266, + "grad_norm": 0.8539537567419873, + "learning_rate": 1.840284078008393e-06, + "loss": 0.8044, + "step": 13189 + }, + { + "epoch": 0.8097240553730931, + "grad_norm": 1.0151626712512225, + "learning_rate": 1.8391347902126676e-06, + "loss": 0.7007, + "step": 13190 + }, + { + "epoch": 0.8097854446115595, + "grad_norm": 0.9883481222545244, + "learning_rate": 1.837985825059595e-06, + "loss": 0.7095, + "step": 13191 + }, + { + "epoch": 0.8098468338500261, + "grad_norm": 1.1202876245740787, + "learning_rate": 1.8368371825945952e-06, + "loss": 0.7626, + "step": 13192 + }, + { + "epoch": 0.8099082230884926, + "grad_norm": 1.054834498127289, + "learning_rate": 1.835688862863082e-06, + "loss": 0.7918, + "step": 13193 + }, + { + "epoch": 0.8099696123269591, + "grad_norm": 0.9487483024540143, + "learning_rate": 1.8345408659104536e-06, + "loss": 0.7797, + "step": 13194 + }, + { + "epoch": 0.8100310015654256, + "grad_norm": 0.8358685330418761, + "learning_rate": 1.833393191782097e-06, + "loss": 0.7336, + "step": 13195 + }, + { + "epoch": 0.8100923908038921, + "grad_norm": 1.0676289807754111, + "learning_rate": 1.8322458405233855e-06, + "loss": 0.7391, + "step": 13196 + }, + { + "epoch": 0.8101537800423586, + "grad_norm": 0.906324351001898, + "learning_rate": 1.8310988121796803e-06, + "loss": 0.7322, + "step": 13197 + }, + { + "epoch": 0.810215169280825, + "grad_norm": 0.5384723099250082, + "learning_rate": 1.8299521067963266e-06, + "loss": 0.5978, + "step": 13198 + }, + { + "epoch": 0.8102765585192916, + "grad_norm": 1.1256335586288808, + "learning_rate": 1.8288057244186674e-06, + "loss": 0.8039, + "step": 13199 + }, + { + "epoch": 0.810337947757758, + "grad_norm": 1.0828767309598923, + "learning_rate": 1.8276596650920187e-06, + "loss": 0.7832, + "step": 13200 + }, + { + "epoch": 0.8103993369962246, + "grad_norm": 1.0333171630897793, + "learning_rate": 1.8265139288616895e-06, + "loss": 0.7669, + "step": 13201 + }, + { + "epoch": 0.810460726234691, + "grad_norm": 1.0024757187039057, + "learning_rate": 1.8253685157729817e-06, + "loss": 0.7401, + "step": 13202 + }, + { + "epoch": 0.8105221154731576, + "grad_norm": 0.9498327207297709, + "learning_rate": 1.8242234258711778e-06, + "loss": 0.6947, + "step": 13203 + }, + { + "epoch": 0.8105835047116241, + "grad_norm": 0.9395167141632446, + "learning_rate": 1.823078659201548e-06, + "loss": 0.7657, + "step": 13204 + }, + { + "epoch": 0.8106448939500905, + "grad_norm": 1.0711038064706746, + "learning_rate": 1.8219342158093533e-06, + "loss": 0.7283, + "step": 13205 + }, + { + "epoch": 0.8107062831885571, + "grad_norm": 1.123463917779253, + "learning_rate": 1.8207900957398383e-06, + "loss": 0.7292, + "step": 13206 + }, + { + "epoch": 0.8107676724270235, + "grad_norm": 0.9836485293259106, + "learning_rate": 1.8196462990382357e-06, + "loss": 0.7263, + "step": 13207 + }, + { + "epoch": 0.8108290616654901, + "grad_norm": 1.0206949582783895, + "learning_rate": 1.818502825749764e-06, + "loss": 0.759, + "step": 13208 + }, + { + "epoch": 0.8108904509039565, + "grad_norm": 0.947984745858359, + "learning_rate": 1.8173596759196388e-06, + "loss": 0.7262, + "step": 13209 + }, + { + "epoch": 0.810951840142423, + "grad_norm": 0.8350243174239486, + "learning_rate": 1.8162168495930466e-06, + "loss": 0.719, + "step": 13210 + }, + { + "epoch": 0.8110132293808895, + "grad_norm": 1.0379855406971201, + "learning_rate": 1.8150743468151732e-06, + "loss": 0.7335, + "step": 13211 + }, + { + "epoch": 0.811074618619356, + "grad_norm": 0.9993316042767234, + "learning_rate": 1.8139321676311838e-06, + "loss": 0.7419, + "step": 13212 + }, + { + "epoch": 0.8111360078578225, + "grad_norm": 1.0551280762894495, + "learning_rate": 1.81279031208624e-06, + "loss": 0.7404, + "step": 13213 + }, + { + "epoch": 0.811197397096289, + "grad_norm": 1.0139433798816997, + "learning_rate": 1.8116487802254868e-06, + "loss": 0.7651, + "step": 13214 + }, + { + "epoch": 0.8112587863347556, + "grad_norm": 1.0115971303104694, + "learning_rate": 1.8105075720940457e-06, + "loss": 0.7523, + "step": 13215 + }, + { + "epoch": 0.811320175573222, + "grad_norm": 1.018496123116643, + "learning_rate": 1.8093666877370442e-06, + "loss": 0.7267, + "step": 13216 + }, + { + "epoch": 0.8113815648116885, + "grad_norm": 1.0873383596132058, + "learning_rate": 1.8082261271995837e-06, + "loss": 0.7699, + "step": 13217 + }, + { + "epoch": 0.811442954050155, + "grad_norm": 1.1983808928966961, + "learning_rate": 1.8070858905267563e-06, + "loss": 0.7336, + "step": 13218 + }, + { + "epoch": 0.8115043432886215, + "grad_norm": 1.0329981130920973, + "learning_rate": 1.8059459777636434e-06, + "loss": 0.7959, + "step": 13219 + }, + { + "epoch": 0.811565732527088, + "grad_norm": 1.0150089235741167, + "learning_rate": 1.8048063889553114e-06, + "loss": 0.7361, + "step": 13220 + }, + { + "epoch": 0.8116271217655545, + "grad_norm": 1.093023680981423, + "learning_rate": 1.803667124146813e-06, + "loss": 0.7302, + "step": 13221 + }, + { + "epoch": 0.811688511004021, + "grad_norm": 0.9904104236853917, + "learning_rate": 1.8025281833831875e-06, + "loss": 0.7801, + "step": 13222 + }, + { + "epoch": 0.8117499002424875, + "grad_norm": 1.0109033190009118, + "learning_rate": 1.8013895667094694e-06, + "loss": 0.7868, + "step": 13223 + }, + { + "epoch": 0.8118112894809539, + "grad_norm": 0.9578726086002121, + "learning_rate": 1.8002512741706723e-06, + "loss": 0.7159, + "step": 13224 + }, + { + "epoch": 0.8118726787194205, + "grad_norm": 1.0571331702497717, + "learning_rate": 1.7991133058117959e-06, + "loss": 0.7256, + "step": 13225 + }, + { + "epoch": 0.811934067957887, + "grad_norm": 1.0003150924502597, + "learning_rate": 1.79797566167783e-06, + "loss": 0.7215, + "step": 13226 + }, + { + "epoch": 0.8119954571963535, + "grad_norm": 0.987099988917419, + "learning_rate": 1.7968383418137557e-06, + "loss": 0.7002, + "step": 13227 + }, + { + "epoch": 0.81205684643482, + "grad_norm": 0.997264428952435, + "learning_rate": 1.795701346264538e-06, + "loss": 0.7589, + "step": 13228 + }, + { + "epoch": 0.8121182356732864, + "grad_norm": 1.079849992855289, + "learning_rate": 1.79456467507512e-06, + "loss": 0.7667, + "step": 13229 + }, + { + "epoch": 0.812179624911753, + "grad_norm": 0.9044302462580098, + "learning_rate": 1.7934283282904496e-06, + "loss": 0.7502, + "step": 13230 + }, + { + "epoch": 0.8122410141502194, + "grad_norm": 1.1152372912235096, + "learning_rate": 1.7922923059554486e-06, + "loss": 0.7489, + "step": 13231 + }, + { + "epoch": 0.812302403388686, + "grad_norm": 1.0405620628351224, + "learning_rate": 1.7911566081150311e-06, + "loss": 0.7193, + "step": 13232 + }, + { + "epoch": 0.8123637926271524, + "grad_norm": 0.5919611407910191, + "learning_rate": 1.7900212348140967e-06, + "loss": 0.6669, + "step": 13233 + }, + { + "epoch": 0.812425181865619, + "grad_norm": 1.0141971199678506, + "learning_rate": 1.7888861860975327e-06, + "loss": 0.7447, + "step": 13234 + }, + { + "epoch": 0.8124865711040855, + "grad_norm": 1.082960514337657, + "learning_rate": 1.7877514620102133e-06, + "loss": 0.7239, + "step": 13235 + }, + { + "epoch": 0.812547960342552, + "grad_norm": 1.0782460589451173, + "learning_rate": 1.7866170625970013e-06, + "loss": 0.8121, + "step": 13236 + }, + { + "epoch": 0.8126093495810185, + "grad_norm": 1.0395633844717416, + "learning_rate": 1.7854829879027435e-06, + "loss": 0.7309, + "step": 13237 + }, + { + "epoch": 0.8126707388194849, + "grad_norm": 0.9299484535612702, + "learning_rate": 1.7843492379722816e-06, + "loss": 0.7236, + "step": 13238 + }, + { + "epoch": 0.8127321280579515, + "grad_norm": 0.9576110595588434, + "learning_rate": 1.7832158128504328e-06, + "loss": 0.7284, + "step": 13239 + }, + { + "epoch": 0.8127935172964179, + "grad_norm": 1.0697142960113049, + "learning_rate": 1.782082712582006e-06, + "loss": 0.7788, + "step": 13240 + }, + { + "epoch": 0.8128549065348845, + "grad_norm": 0.9756837196845236, + "learning_rate": 1.7809499372118056e-06, + "loss": 0.7595, + "step": 13241 + }, + { + "epoch": 0.8129162957733509, + "grad_norm": 0.9453751121107151, + "learning_rate": 1.779817486784612e-06, + "loss": 0.7266, + "step": 13242 + }, + { + "epoch": 0.8129776850118174, + "grad_norm": 0.9892181945329221, + "learning_rate": 1.7786853613451983e-06, + "loss": 0.7579, + "step": 13243 + }, + { + "epoch": 0.8130390742502839, + "grad_norm": 1.0193782721753746, + "learning_rate": 1.7775535609383222e-06, + "loss": 0.7652, + "step": 13244 + }, + { + "epoch": 0.8131004634887504, + "grad_norm": 0.9275168163936834, + "learning_rate": 1.776422085608731e-06, + "loss": 0.7638, + "step": 13245 + }, + { + "epoch": 0.813161852727217, + "grad_norm": 1.0474646190431105, + "learning_rate": 1.7752909354011582e-06, + "loss": 0.7839, + "step": 13246 + }, + { + "epoch": 0.8132232419656834, + "grad_norm": 1.0825924731410856, + "learning_rate": 1.77416011036032e-06, + "loss": 0.733, + "step": 13247 + }, + { + "epoch": 0.81328463120415, + "grad_norm": 0.991161835771381, + "learning_rate": 1.773029610530933e-06, + "loss": 0.6843, + "step": 13248 + }, + { + "epoch": 0.8133460204426164, + "grad_norm": 0.953307733876448, + "learning_rate": 1.7718994359576835e-06, + "loss": 0.7165, + "step": 13249 + }, + { + "epoch": 0.8134074096810829, + "grad_norm": 1.0187461515371157, + "learning_rate": 1.770769586685257e-06, + "loss": 0.7232, + "step": 13250 + }, + { + "epoch": 0.8134687989195494, + "grad_norm": 1.1455813064614737, + "learning_rate": 1.7696400627583188e-06, + "loss": 0.7373, + "step": 13251 + }, + { + "epoch": 0.8135301881580159, + "grad_norm": 1.0234981933530247, + "learning_rate": 1.768510864221531e-06, + "loss": 0.8057, + "step": 13252 + }, + { + "epoch": 0.8135915773964824, + "grad_norm": 0.9330894267968142, + "learning_rate": 1.7673819911195356e-06, + "loss": 0.7409, + "step": 13253 + }, + { + "epoch": 0.8136529666349489, + "grad_norm": 1.0064197610172971, + "learning_rate": 1.766253443496957e-06, + "loss": 0.7245, + "step": 13254 + }, + { + "epoch": 0.8137143558734153, + "grad_norm": 0.9468920602707315, + "learning_rate": 1.7651252213984182e-06, + "loss": 0.7283, + "step": 13255 + }, + { + "epoch": 0.8137757451118819, + "grad_norm": 0.9851481616576285, + "learning_rate": 1.7639973248685239e-06, + "loss": 0.7422, + "step": 13256 + }, + { + "epoch": 0.8138371343503484, + "grad_norm": 1.033202728870353, + "learning_rate": 1.7628697539518647e-06, + "loss": 0.7695, + "step": 13257 + }, + { + "epoch": 0.8138985235888149, + "grad_norm": 1.0288410966074801, + "learning_rate": 1.7617425086930185e-06, + "loss": 0.753, + "step": 13258 + }, + { + "epoch": 0.8139599128272814, + "grad_norm": 1.0093719508283392, + "learning_rate": 1.7606155891365528e-06, + "loss": 0.7857, + "step": 13259 + }, + { + "epoch": 0.8140213020657479, + "grad_norm": 1.0427615196657853, + "learning_rate": 1.759488995327019e-06, + "loss": 0.7814, + "step": 13260 + }, + { + "epoch": 0.8140826913042144, + "grad_norm": 0.9957677281841402, + "learning_rate": 1.7583627273089576e-06, + "loss": 0.7308, + "step": 13261 + }, + { + "epoch": 0.8141440805426808, + "grad_norm": 0.9161087455567539, + "learning_rate": 1.7572367851268989e-06, + "loss": 0.73, + "step": 13262 + }, + { + "epoch": 0.8142054697811474, + "grad_norm": 1.041467437835011, + "learning_rate": 1.7561111688253574e-06, + "loss": 0.7802, + "step": 13263 + }, + { + "epoch": 0.8142668590196138, + "grad_norm": 0.9923978765679142, + "learning_rate": 1.7549858784488317e-06, + "loss": 0.7236, + "step": 13264 + }, + { + "epoch": 0.8143282482580804, + "grad_norm": 1.0524644900339115, + "learning_rate": 1.7538609140418072e-06, + "loss": 0.7376, + "step": 13265 + }, + { + "epoch": 0.8143896374965468, + "grad_norm": 1.1212032188193013, + "learning_rate": 1.7527362756487687e-06, + "loss": 0.7899, + "step": 13266 + }, + { + "epoch": 0.8144510267350134, + "grad_norm": 1.0065050321035423, + "learning_rate": 1.7516119633141738e-06, + "loss": 0.7797, + "step": 13267 + }, + { + "epoch": 0.8145124159734799, + "grad_norm": 0.9164165983529, + "learning_rate": 1.7504879770824734e-06, + "loss": 0.7333, + "step": 13268 + }, + { + "epoch": 0.8145738052119463, + "grad_norm": 1.1343501250348822, + "learning_rate": 1.7493643169981045e-06, + "loss": 0.8067, + "step": 13269 + }, + { + "epoch": 0.8146351944504129, + "grad_norm": 1.0343434892481431, + "learning_rate": 1.7482409831054924e-06, + "loss": 0.7169, + "step": 13270 + }, + { + "epoch": 0.8146965836888793, + "grad_norm": 0.9262580832856318, + "learning_rate": 1.7471179754490463e-06, + "loss": 0.7132, + "step": 13271 + }, + { + "epoch": 0.8147579729273459, + "grad_norm": 0.992226040560464, + "learning_rate": 1.745995294073165e-06, + "loss": 0.7487, + "step": 13272 + }, + { + "epoch": 0.8148193621658123, + "grad_norm": 0.9336204197813687, + "learning_rate": 1.7448729390222408e-06, + "loss": 0.7734, + "step": 13273 + }, + { + "epoch": 0.8148807514042788, + "grad_norm": 1.051250008297322, + "learning_rate": 1.743750910340637e-06, + "loss": 0.6911, + "step": 13274 + }, + { + "epoch": 0.8149421406427453, + "grad_norm": 1.0032828828879083, + "learning_rate": 1.7426292080727181e-06, + "loss": 0.7116, + "step": 13275 + }, + { + "epoch": 0.8150035298812118, + "grad_norm": 0.9182664644752674, + "learning_rate": 1.7415078322628265e-06, + "loss": 0.7377, + "step": 13276 + }, + { + "epoch": 0.8150649191196783, + "grad_norm": 0.864498753751645, + "learning_rate": 1.7403867829553035e-06, + "loss": 0.7452, + "step": 13277 + }, + { + "epoch": 0.8151263083581448, + "grad_norm": 0.9516246597211415, + "learning_rate": 1.739266060194469e-06, + "loss": 0.7579, + "step": 13278 + }, + { + "epoch": 0.8151876975966114, + "grad_norm": 1.102111202355404, + "learning_rate": 1.738145664024623e-06, + "loss": 0.7013, + "step": 13279 + }, + { + "epoch": 0.8152490868350778, + "grad_norm": 1.052938441838056, + "learning_rate": 1.7370255944900682e-06, + "loss": 0.7461, + "step": 13280 + }, + { + "epoch": 0.8153104760735443, + "grad_norm": 1.0651508958140126, + "learning_rate": 1.7359058516350868e-06, + "loss": 0.7523, + "step": 13281 + }, + { + "epoch": 0.8153718653120108, + "grad_norm": 1.103135910356648, + "learning_rate": 1.7347864355039456e-06, + "loss": 0.7876, + "step": 13282 + }, + { + "epoch": 0.8154332545504773, + "grad_norm": 0.9856516115879048, + "learning_rate": 1.7336673461409026e-06, + "loss": 0.7363, + "step": 13283 + }, + { + "epoch": 0.8154946437889438, + "grad_norm": 0.5767781452940596, + "learning_rate": 1.7325485835902002e-06, + "loss": 0.6665, + "step": 13284 + }, + { + "epoch": 0.8155560330274103, + "grad_norm": 1.0512561258305384, + "learning_rate": 1.7314301478960694e-06, + "loss": 0.708, + "step": 13285 + }, + { + "epoch": 0.8156174222658767, + "grad_norm": 1.0244297850946054, + "learning_rate": 1.7303120391027272e-06, + "loss": 0.686, + "step": 13286 + }, + { + "epoch": 0.8156788115043433, + "grad_norm": 1.0595395708358237, + "learning_rate": 1.7291942572543806e-06, + "loss": 0.7537, + "step": 13287 + }, + { + "epoch": 0.8157402007428098, + "grad_norm": 0.8932344720939692, + "learning_rate": 1.7280768023952245e-06, + "loss": 0.7126, + "step": 13288 + }, + { + "epoch": 0.8158015899812763, + "grad_norm": 1.1078200940436975, + "learning_rate": 1.7269596745694295e-06, + "loss": 0.7745, + "step": 13289 + }, + { + "epoch": 0.8158629792197428, + "grad_norm": 0.9844085067920422, + "learning_rate": 1.7258428738211642e-06, + "loss": 0.7073, + "step": 13290 + }, + { + "epoch": 0.8159243684582093, + "grad_norm": 1.0366391103059176, + "learning_rate": 1.7247264001945862e-06, + "loss": 0.7727, + "step": 13291 + }, + { + "epoch": 0.8159857576966758, + "grad_norm": 0.9334556229442569, + "learning_rate": 1.7236102537338328e-06, + "loss": 0.765, + "step": 13292 + }, + { + "epoch": 0.8160471469351422, + "grad_norm": 0.9976377402968308, + "learning_rate": 1.7224944344830309e-06, + "loss": 0.772, + "step": 13293 + }, + { + "epoch": 0.8161085361736088, + "grad_norm": 0.9940764305852432, + "learning_rate": 1.7213789424862947e-06, + "loss": 0.7687, + "step": 13294 + }, + { + "epoch": 0.8161699254120752, + "grad_norm": 0.9842655231474607, + "learning_rate": 1.7202637777877274e-06, + "loss": 0.7352, + "step": 13295 + }, + { + "epoch": 0.8162313146505418, + "grad_norm": 0.9961661151681601, + "learning_rate": 1.7191489404314155e-06, + "loss": 0.7095, + "step": 13296 + }, + { + "epoch": 0.8162927038890082, + "grad_norm": 1.0684711119601213, + "learning_rate": 1.7180344304614348e-06, + "loss": 0.7509, + "step": 13297 + }, + { + "epoch": 0.8163540931274748, + "grad_norm": 1.0627437841380085, + "learning_rate": 1.7169202479218483e-06, + "loss": 0.7363, + "step": 13298 + }, + { + "epoch": 0.8164154823659413, + "grad_norm": 1.0647276974070625, + "learning_rate": 1.715806392856706e-06, + "loss": 0.8047, + "step": 13299 + }, + { + "epoch": 0.8164768716044077, + "grad_norm": 1.0370722084922084, + "learning_rate": 1.7146928653100402e-06, + "loss": 0.6885, + "step": 13300 + }, + { + "epoch": 0.8165382608428743, + "grad_norm": 0.9933355586901809, + "learning_rate": 1.7135796653258818e-06, + "loss": 0.7295, + "step": 13301 + }, + { + "epoch": 0.8165996500813407, + "grad_norm": 0.9117866101828414, + "learning_rate": 1.7124667929482408e-06, + "loss": 0.6997, + "step": 13302 + }, + { + "epoch": 0.8166610393198073, + "grad_norm": 1.0201787449720103, + "learning_rate": 1.7113542482211098e-06, + "loss": 0.7621, + "step": 13303 + }, + { + "epoch": 0.8167224285582737, + "grad_norm": 0.9142402846679437, + "learning_rate": 1.7102420311884727e-06, + "loss": 0.7392, + "step": 13304 + }, + { + "epoch": 0.8167838177967403, + "grad_norm": 1.1095926205014917, + "learning_rate": 1.7091301418943084e-06, + "loss": 0.7434, + "step": 13305 + }, + { + "epoch": 0.8168452070352067, + "grad_norm": 1.0379569586753046, + "learning_rate": 1.7080185803825722e-06, + "loss": 0.7181, + "step": 13306 + }, + { + "epoch": 0.8169065962736732, + "grad_norm": 0.9773542758774297, + "learning_rate": 1.7069073466972096e-06, + "loss": 0.7238, + "step": 13307 + }, + { + "epoch": 0.8169679855121397, + "grad_norm": 1.0223801163686286, + "learning_rate": 1.7057964408821537e-06, + "loss": 0.7462, + "step": 13308 + }, + { + "epoch": 0.8170293747506062, + "grad_norm": 1.051076662252209, + "learning_rate": 1.7046858629813257e-06, + "loss": 0.7202, + "step": 13309 + }, + { + "epoch": 0.8170907639890728, + "grad_norm": 0.9170834173870476, + "learning_rate": 1.7035756130386328e-06, + "loss": 0.7379, + "step": 13310 + }, + { + "epoch": 0.8171521532275392, + "grad_norm": 1.0631386431827026, + "learning_rate": 1.7024656910979642e-06, + "loss": 0.7563, + "step": 13311 + }, + { + "epoch": 0.8172135424660057, + "grad_norm": 0.9880831801668952, + "learning_rate": 1.7013560972032117e-06, + "loss": 0.7438, + "step": 13312 + }, + { + "epoch": 0.8172749317044722, + "grad_norm": 1.0895709450848932, + "learning_rate": 1.7002468313982334e-06, + "loss": 0.6719, + "step": 13313 + }, + { + "epoch": 0.8173363209429387, + "grad_norm": 1.0168855199211932, + "learning_rate": 1.6991378937268888e-06, + "loss": 0.7508, + "step": 13314 + }, + { + "epoch": 0.8173977101814052, + "grad_norm": 1.060808231658346, + "learning_rate": 1.698029284233016e-06, + "loss": 0.751, + "step": 13315 + }, + { + "epoch": 0.8174590994198717, + "grad_norm": 0.9354734135878816, + "learning_rate": 1.696921002960451e-06, + "loss": 0.7471, + "step": 13316 + }, + { + "epoch": 0.8175204886583382, + "grad_norm": 1.016049295600617, + "learning_rate": 1.695813049953009e-06, + "loss": 0.7277, + "step": 13317 + }, + { + "epoch": 0.8175818778968047, + "grad_norm": 0.9388861478640596, + "learning_rate": 1.694705425254486e-06, + "loss": 0.7899, + "step": 13318 + }, + { + "epoch": 0.8176432671352711, + "grad_norm": 0.9876259170048253, + "learning_rate": 1.693598128908679e-06, + "loss": 0.7365, + "step": 13319 + }, + { + "epoch": 0.8177046563737377, + "grad_norm": 1.0505410284386438, + "learning_rate": 1.6924911609593652e-06, + "loss": 0.7461, + "step": 13320 + }, + { + "epoch": 0.8177660456122042, + "grad_norm": 0.9956094103351394, + "learning_rate": 1.6913845214503065e-06, + "loss": 0.7243, + "step": 13321 + }, + { + "epoch": 0.8178274348506707, + "grad_norm": 1.1656845325263752, + "learning_rate": 1.6902782104252557e-06, + "loss": 0.7608, + "step": 13322 + }, + { + "epoch": 0.8178888240891372, + "grad_norm": 0.9934426811571327, + "learning_rate": 1.6891722279279498e-06, + "loss": 0.7357, + "step": 13323 + }, + { + "epoch": 0.8179502133276036, + "grad_norm": 1.046679143528713, + "learning_rate": 1.6880665740021162e-06, + "loss": 0.7367, + "step": 13324 + }, + { + "epoch": 0.8180116025660702, + "grad_norm": 0.9280322447618321, + "learning_rate": 1.6869612486914645e-06, + "loss": 0.6885, + "step": 13325 + }, + { + "epoch": 0.8180729918045366, + "grad_norm": 1.0059040115128652, + "learning_rate": 1.685856252039697e-06, + "loss": 0.7703, + "step": 13326 + }, + { + "epoch": 0.8181343810430032, + "grad_norm": 0.9994760724732775, + "learning_rate": 1.6847515840905015e-06, + "loss": 0.7943, + "step": 13327 + }, + { + "epoch": 0.8181957702814696, + "grad_norm": 1.1796516461713344, + "learning_rate": 1.6836472448875473e-06, + "loss": 0.7297, + "step": 13328 + }, + { + "epoch": 0.8182571595199362, + "grad_norm": 0.9244305780601285, + "learning_rate": 1.682543234474494e-06, + "loss": 0.7189, + "step": 13329 + }, + { + "epoch": 0.8183185487584026, + "grad_norm": 1.1008902237233487, + "learning_rate": 1.6814395528949935e-06, + "loss": 0.7333, + "step": 13330 + }, + { + "epoch": 0.8183799379968691, + "grad_norm": 0.950968645438772, + "learning_rate": 1.6803362001926782e-06, + "loss": 0.7641, + "step": 13331 + }, + { + "epoch": 0.8184413272353357, + "grad_norm": 1.1396654176392869, + "learning_rate": 1.6792331764111701e-06, + "loss": 0.7746, + "step": 13332 + }, + { + "epoch": 0.8185027164738021, + "grad_norm": 1.0359794491014163, + "learning_rate": 1.678130481594077e-06, + "loss": 0.7285, + "step": 13333 + }, + { + "epoch": 0.8185641057122687, + "grad_norm": 0.9903317291292886, + "learning_rate": 1.6770281157849944e-06, + "loss": 0.7284, + "step": 13334 + }, + { + "epoch": 0.8186254949507351, + "grad_norm": 1.1413380311359966, + "learning_rate": 1.6759260790275044e-06, + "loss": 0.7669, + "step": 13335 + }, + { + "epoch": 0.8186868841892017, + "grad_norm": 1.072217831781072, + "learning_rate": 1.6748243713651746e-06, + "loss": 0.7392, + "step": 13336 + }, + { + "epoch": 0.8187482734276681, + "grad_norm": 1.0524447415318308, + "learning_rate": 1.6737229928415676e-06, + "loss": 0.753, + "step": 13337 + }, + { + "epoch": 0.8188096626661346, + "grad_norm": 1.1961317142741499, + "learning_rate": 1.6726219435002223e-06, + "loss": 0.732, + "step": 13338 + }, + { + "epoch": 0.8188710519046011, + "grad_norm": 0.9823168693064702, + "learning_rate": 1.6715212233846656e-06, + "loss": 0.7802, + "step": 13339 + }, + { + "epoch": 0.8189324411430676, + "grad_norm": 1.0871032662558957, + "learning_rate": 1.6704208325384208e-06, + "loss": 0.7326, + "step": 13340 + }, + { + "epoch": 0.8189938303815342, + "grad_norm": 0.997398962493452, + "learning_rate": 1.669320771004992e-06, + "loss": 0.8108, + "step": 13341 + }, + { + "epoch": 0.8190552196200006, + "grad_norm": 1.0804492678686153, + "learning_rate": 1.6682210388278697e-06, + "loss": 0.7679, + "step": 13342 + }, + { + "epoch": 0.8191166088584672, + "grad_norm": 1.1433711995530542, + "learning_rate": 1.6671216360505272e-06, + "loss": 0.7277, + "step": 13343 + }, + { + "epoch": 0.8191779980969336, + "grad_norm": 0.8799989937046783, + "learning_rate": 1.666022562716435e-06, + "loss": 0.7467, + "step": 13344 + }, + { + "epoch": 0.8192393873354001, + "grad_norm": 1.0285372420257233, + "learning_rate": 1.6649238188690454e-06, + "loss": 0.7251, + "step": 13345 + }, + { + "epoch": 0.8193007765738666, + "grad_norm": 0.9825793220779018, + "learning_rate": 1.6638254045517955e-06, + "loss": 0.748, + "step": 13346 + }, + { + "epoch": 0.8193621658123331, + "grad_norm": 0.9522522713915428, + "learning_rate": 1.662727319808113e-06, + "loss": 0.7275, + "step": 13347 + }, + { + "epoch": 0.8194235550507996, + "grad_norm": 0.918503097002765, + "learning_rate": 1.6616295646814096e-06, + "loss": 0.7498, + "step": 13348 + }, + { + "epoch": 0.8194849442892661, + "grad_norm": 0.892289538603166, + "learning_rate": 1.6605321392150875e-06, + "loss": 0.7405, + "step": 13349 + }, + { + "epoch": 0.8195463335277325, + "grad_norm": 1.0100778908750354, + "learning_rate": 1.6594350434525298e-06, + "loss": 0.7544, + "step": 13350 + }, + { + "epoch": 0.8196077227661991, + "grad_norm": 1.043066329403579, + "learning_rate": 1.6583382774371149e-06, + "loss": 0.7339, + "step": 13351 + }, + { + "epoch": 0.8196691120046656, + "grad_norm": 1.0863086226819587, + "learning_rate": 1.6572418412122049e-06, + "loss": 0.7381, + "step": 13352 + }, + { + "epoch": 0.8197305012431321, + "grad_norm": 1.1128667318869736, + "learning_rate": 1.656145734821143e-06, + "loss": 0.7779, + "step": 13353 + }, + { + "epoch": 0.8197918904815986, + "grad_norm": 1.0564397676383896, + "learning_rate": 1.6550499583072644e-06, + "loss": 0.7227, + "step": 13354 + }, + { + "epoch": 0.819853279720065, + "grad_norm": 1.068318819541589, + "learning_rate": 1.6539545117138944e-06, + "loss": 0.7021, + "step": 13355 + }, + { + "epoch": 0.8199146689585316, + "grad_norm": 1.1765839250143149, + "learning_rate": 1.6528593950843408e-06, + "loss": 0.7262, + "step": 13356 + }, + { + "epoch": 0.819976058196998, + "grad_norm": 1.0192568862013676, + "learning_rate": 1.6517646084618989e-06, + "loss": 0.7016, + "step": 13357 + }, + { + "epoch": 0.8200374474354646, + "grad_norm": 1.1797465434483985, + "learning_rate": 1.6506701518898504e-06, + "loss": 0.7655, + "step": 13358 + }, + { + "epoch": 0.820098836673931, + "grad_norm": 1.0673472742775063, + "learning_rate": 1.6495760254114679e-06, + "loss": 0.8075, + "step": 13359 + }, + { + "epoch": 0.8201602259123976, + "grad_norm": 1.0232592261214648, + "learning_rate": 1.6484822290700054e-06, + "loss": 0.7774, + "step": 13360 + }, + { + "epoch": 0.820221615150864, + "grad_norm": 1.0260200001724935, + "learning_rate": 1.647388762908707e-06, + "loss": 0.8114, + "step": 13361 + }, + { + "epoch": 0.8202830043893306, + "grad_norm": 1.1232992421976922, + "learning_rate": 1.6462956269708052e-06, + "loss": 0.7037, + "step": 13362 + }, + { + "epoch": 0.8203443936277971, + "grad_norm": 1.1142133515234642, + "learning_rate": 1.6452028212995152e-06, + "loss": 0.7931, + "step": 13363 + }, + { + "epoch": 0.8204057828662635, + "grad_norm": 1.013874376769988, + "learning_rate": 1.6441103459380392e-06, + "loss": 0.7753, + "step": 13364 + }, + { + "epoch": 0.8204671721047301, + "grad_norm": 1.1802734820211, + "learning_rate": 1.6430182009295748e-06, + "loss": 0.7457, + "step": 13365 + }, + { + "epoch": 0.8205285613431965, + "grad_norm": 0.8975035464274057, + "learning_rate": 1.6419263863172997e-06, + "loss": 0.7413, + "step": 13366 + }, + { + "epoch": 0.8205899505816631, + "grad_norm": 1.0947024871013928, + "learning_rate": 1.6408349021443736e-06, + "loss": 0.7406, + "step": 13367 + }, + { + "epoch": 0.8206513398201295, + "grad_norm": 1.0272794557050355, + "learning_rate": 1.6397437484539502e-06, + "loss": 0.7424, + "step": 13368 + }, + { + "epoch": 0.820712729058596, + "grad_norm": 1.0175077008640259, + "learning_rate": 1.6386529252891725e-06, + "loss": 0.7152, + "step": 13369 + }, + { + "epoch": 0.8207741182970625, + "grad_norm": 0.9759798112065089, + "learning_rate": 1.6375624326931638e-06, + "loss": 0.7274, + "step": 13370 + }, + { + "epoch": 0.820835507535529, + "grad_norm": 1.020893739667823, + "learning_rate": 1.6364722707090374e-06, + "loss": 0.7024, + "step": 13371 + }, + { + "epoch": 0.8208968967739955, + "grad_norm": 1.023425692754284, + "learning_rate": 1.6353824393798945e-06, + "loss": 0.78, + "step": 13372 + }, + { + "epoch": 0.820958286012462, + "grad_norm": 1.1401265405880172, + "learning_rate": 1.6342929387488205e-06, + "loss": 0.7618, + "step": 13373 + }, + { + "epoch": 0.8210196752509286, + "grad_norm": 0.9670297196026247, + "learning_rate": 1.6332037688588887e-06, + "loss": 0.7279, + "step": 13374 + }, + { + "epoch": 0.821081064489395, + "grad_norm": 1.0492490384144155, + "learning_rate": 1.632114929753159e-06, + "loss": 0.7079, + "step": 13375 + }, + { + "epoch": 0.8211424537278615, + "grad_norm": 0.9968291165392804, + "learning_rate": 1.631026421474685e-06, + "loss": 0.7414, + "step": 13376 + }, + { + "epoch": 0.821203842966328, + "grad_norm": 1.145734060909856, + "learning_rate": 1.6299382440664958e-06, + "loss": 0.7301, + "step": 13377 + }, + { + "epoch": 0.8212652322047945, + "grad_norm": 1.114856263991154, + "learning_rate": 1.6288503975716108e-06, + "loss": 0.7348, + "step": 13378 + }, + { + "epoch": 0.821326621443261, + "grad_norm": 1.0812383893529893, + "learning_rate": 1.6277628820330437e-06, + "loss": 0.7542, + "step": 13379 + }, + { + "epoch": 0.8213880106817275, + "grad_norm": 0.9817676668384796, + "learning_rate": 1.626675697493788e-06, + "loss": 0.692, + "step": 13380 + }, + { + "epoch": 0.821449399920194, + "grad_norm": 1.0034784242405337, + "learning_rate": 1.6255888439968282e-06, + "loss": 0.7241, + "step": 13381 + }, + { + "epoch": 0.8215107891586605, + "grad_norm": 0.9717147400524011, + "learning_rate": 1.6245023215851263e-06, + "loss": 0.7314, + "step": 13382 + }, + { + "epoch": 0.8215721783971269, + "grad_norm": 0.9964212710031137, + "learning_rate": 1.623416130301645e-06, + "loss": 0.7239, + "step": 13383 + }, + { + "epoch": 0.8216335676355935, + "grad_norm": 1.028892738285302, + "learning_rate": 1.622330270189325e-06, + "loss": 0.7181, + "step": 13384 + }, + { + "epoch": 0.82169495687406, + "grad_norm": 1.1102337019323325, + "learning_rate": 1.621244741291097e-06, + "loss": 0.7842, + "step": 13385 + }, + { + "epoch": 0.8217563461125265, + "grad_norm": 1.0567944213352563, + "learning_rate": 1.6201595436498774e-06, + "loss": 0.7567, + "step": 13386 + }, + { + "epoch": 0.821817735350993, + "grad_norm": 1.0307503924145027, + "learning_rate": 1.6190746773085686e-06, + "loss": 0.7402, + "step": 13387 + }, + { + "epoch": 0.8218791245894594, + "grad_norm": 0.9783103449214134, + "learning_rate": 1.617990142310062e-06, + "loss": 0.7606, + "step": 13388 + }, + { + "epoch": 0.821940513827926, + "grad_norm": 1.110112491896161, + "learning_rate": 1.6169059386972342e-06, + "loss": 0.7847, + "step": 13389 + }, + { + "epoch": 0.8220019030663924, + "grad_norm": 1.082630010106575, + "learning_rate": 1.615822066512952e-06, + "loss": 0.7527, + "step": 13390 + }, + { + "epoch": 0.822063292304859, + "grad_norm": 0.6141396779610718, + "learning_rate": 1.614738525800067e-06, + "loss": 0.6704, + "step": 13391 + }, + { + "epoch": 0.8221246815433254, + "grad_norm": 0.9367504111851714, + "learning_rate": 1.6136553166014146e-06, + "loss": 0.7189, + "step": 13392 + }, + { + "epoch": 0.822186070781792, + "grad_norm": 0.9224354701346864, + "learning_rate": 1.6125724389598175e-06, + "loss": 0.7255, + "step": 13393 + }, + { + "epoch": 0.8222474600202585, + "grad_norm": 0.9893926214009063, + "learning_rate": 1.6114898929180934e-06, + "loss": 0.7503, + "step": 13394 + }, + { + "epoch": 0.8223088492587249, + "grad_norm": 0.9679660982570667, + "learning_rate": 1.6104076785190393e-06, + "loss": 0.7639, + "step": 13395 + }, + { + "epoch": 0.8223702384971915, + "grad_norm": 0.9978924243570405, + "learning_rate": 1.6093257958054399e-06, + "loss": 0.7399, + "step": 13396 + }, + { + "epoch": 0.8224316277356579, + "grad_norm": 1.0598299914035156, + "learning_rate": 1.6082442448200686e-06, + "loss": 0.7648, + "step": 13397 + }, + { + "epoch": 0.8224930169741245, + "grad_norm": 0.9829375642398878, + "learning_rate": 1.6071630256056847e-06, + "loss": 0.727, + "step": 13398 + }, + { + "epoch": 0.8225544062125909, + "grad_norm": 0.9777848634214474, + "learning_rate": 1.606082138205034e-06, + "loss": 0.6944, + "step": 13399 + }, + { + "epoch": 0.8226157954510575, + "grad_norm": 1.0743026689042625, + "learning_rate": 1.6050015826608478e-06, + "loss": 0.7544, + "step": 13400 + }, + { + "epoch": 0.8226771846895239, + "grad_norm": 1.0096204614483528, + "learning_rate": 1.6039213590158542e-06, + "loss": 0.7481, + "step": 13401 + }, + { + "epoch": 0.8227385739279904, + "grad_norm": 1.037957930107394, + "learning_rate": 1.6028414673127514e-06, + "loss": 0.7735, + "step": 13402 + }, + { + "epoch": 0.8227999631664569, + "grad_norm": 0.9802324292863733, + "learning_rate": 1.6017619075942347e-06, + "loss": 0.7516, + "step": 13403 + }, + { + "epoch": 0.8228613524049234, + "grad_norm": 1.0972671785079446, + "learning_rate": 1.6006826799029885e-06, + "loss": 0.7779, + "step": 13404 + }, + { + "epoch": 0.82292274164339, + "grad_norm": 0.9499500836702273, + "learning_rate": 1.5996037842816792e-06, + "loss": 0.7639, + "step": 13405 + }, + { + "epoch": 0.8229841308818564, + "grad_norm": 0.9883706914896458, + "learning_rate": 1.598525220772963e-06, + "loss": 0.7389, + "step": 13406 + }, + { + "epoch": 0.823045520120323, + "grad_norm": 1.0662495264135006, + "learning_rate": 1.5974469894194745e-06, + "loss": 0.7831, + "step": 13407 + }, + { + "epoch": 0.8231069093587894, + "grad_norm": 1.0526714853655887, + "learning_rate": 1.5963690902638484e-06, + "loss": 0.7463, + "step": 13408 + }, + { + "epoch": 0.8231682985972559, + "grad_norm": 1.1175385791589214, + "learning_rate": 1.5952915233486987e-06, + "loss": 0.747, + "step": 13409 + }, + { + "epoch": 0.8232296878357224, + "grad_norm": 1.062117521372893, + "learning_rate": 1.5942142887166268e-06, + "loss": 0.753, + "step": 13410 + }, + { + "epoch": 0.8232910770741889, + "grad_norm": 1.0600910249201814, + "learning_rate": 1.5931373864102207e-06, + "loss": 0.7134, + "step": 13411 + }, + { + "epoch": 0.8233524663126554, + "grad_norm": 0.9786803652399498, + "learning_rate": 1.5920608164720563e-06, + "loss": 0.7583, + "step": 13412 + }, + { + "epoch": 0.8234138555511219, + "grad_norm": 1.0075104182733954, + "learning_rate": 1.5909845789446976e-06, + "loss": 0.7392, + "step": 13413 + }, + { + "epoch": 0.8234752447895883, + "grad_norm": 1.0235447591976088, + "learning_rate": 1.5899086738706904e-06, + "loss": 0.7244, + "step": 13414 + }, + { + "epoch": 0.8235366340280549, + "grad_norm": 0.9268259102033841, + "learning_rate": 1.5888331012925762e-06, + "loss": 0.735, + "step": 13415 + }, + { + "epoch": 0.8235980232665214, + "grad_norm": 0.9003112290764335, + "learning_rate": 1.5877578612528777e-06, + "loss": 0.7337, + "step": 13416 + }, + { + "epoch": 0.8236594125049879, + "grad_norm": 1.0323367306102886, + "learning_rate": 1.5866829537940975e-06, + "loss": 0.7735, + "step": 13417 + }, + { + "epoch": 0.8237208017434544, + "grad_norm": 1.0644139780449104, + "learning_rate": 1.5856083789587407e-06, + "loss": 0.7064, + "step": 13418 + }, + { + "epoch": 0.8237821909819208, + "grad_norm": 1.0528861941987653, + "learning_rate": 1.5845341367892875e-06, + "loss": 0.753, + "step": 13419 + }, + { + "epoch": 0.8238435802203874, + "grad_norm": 1.009491571871034, + "learning_rate": 1.5834602273282096e-06, + "loss": 0.7051, + "step": 13420 + }, + { + "epoch": 0.8239049694588538, + "grad_norm": 0.9521029886806472, + "learning_rate": 1.582386650617963e-06, + "loss": 0.7685, + "step": 13421 + }, + { + "epoch": 0.8239663586973204, + "grad_norm": 1.04179262923348, + "learning_rate": 1.5813134067009938e-06, + "loss": 0.7402, + "step": 13422 + }, + { + "epoch": 0.8240277479357868, + "grad_norm": 0.9525994650275684, + "learning_rate": 1.5802404956197314e-06, + "loss": 0.7446, + "step": 13423 + }, + { + "epoch": 0.8240891371742534, + "grad_norm": 1.0539722997053769, + "learning_rate": 1.5791679174165941e-06, + "loss": 0.7447, + "step": 13424 + }, + { + "epoch": 0.8241505264127198, + "grad_norm": 1.0871111738332715, + "learning_rate": 1.5780956721339847e-06, + "loss": 0.7727, + "step": 13425 + }, + { + "epoch": 0.8242119156511863, + "grad_norm": 1.0635732402959395, + "learning_rate": 1.5770237598143013e-06, + "loss": 0.7774, + "step": 13426 + }, + { + "epoch": 0.8242733048896529, + "grad_norm": 0.9713248045746083, + "learning_rate": 1.5759521804999157e-06, + "loss": 0.7641, + "step": 13427 + }, + { + "epoch": 0.8243346941281193, + "grad_norm": 0.981757904262295, + "learning_rate": 1.5748809342331929e-06, + "loss": 0.7451, + "step": 13428 + }, + { + "epoch": 0.8243960833665859, + "grad_norm": 1.021682959395642, + "learning_rate": 1.57381002105649e-06, + "loss": 0.7782, + "step": 13429 + }, + { + "epoch": 0.8244574726050523, + "grad_norm": 1.1432311413032847, + "learning_rate": 1.5727394410121454e-06, + "loss": 0.7326, + "step": 13430 + }, + { + "epoch": 0.8245188618435189, + "grad_norm": 1.1232295386273858, + "learning_rate": 1.571669194142481e-06, + "loss": 0.7101, + "step": 13431 + }, + { + "epoch": 0.8245802510819853, + "grad_norm": 1.1114902826881734, + "learning_rate": 1.5705992804898084e-06, + "loss": 0.7891, + "step": 13432 + }, + { + "epoch": 0.8246416403204518, + "grad_norm": 1.033273596227923, + "learning_rate": 1.5695297000964327e-06, + "loss": 0.7375, + "step": 13433 + }, + { + "epoch": 0.8247030295589183, + "grad_norm": 0.9971016133136821, + "learning_rate": 1.5684604530046366e-06, + "loss": 0.7662, + "step": 13434 + }, + { + "epoch": 0.8247644187973848, + "grad_norm": 0.9360240794317204, + "learning_rate": 1.5673915392566941e-06, + "loss": 0.7131, + "step": 13435 + }, + { + "epoch": 0.8248258080358513, + "grad_norm": 1.0595004918974589, + "learning_rate": 1.5663229588948647e-06, + "loss": 0.7205, + "step": 13436 + }, + { + "epoch": 0.8248871972743178, + "grad_norm": 1.0664948498236502, + "learning_rate": 1.565254711961396e-06, + "loss": 0.7337, + "step": 13437 + }, + { + "epoch": 0.8249485865127844, + "grad_norm": 1.0060197324328846, + "learning_rate": 1.5641867984985204e-06, + "loss": 0.7193, + "step": 13438 + }, + { + "epoch": 0.8250099757512508, + "grad_norm": 0.9950284371542429, + "learning_rate": 1.5631192185484557e-06, + "loss": 0.755, + "step": 13439 + }, + { + "epoch": 0.8250713649897173, + "grad_norm": 0.8963602709941768, + "learning_rate": 1.5620519721534166e-06, + "loss": 0.7341, + "step": 13440 + }, + { + "epoch": 0.8251327542281838, + "grad_norm": 1.036457167607381, + "learning_rate": 1.5609850593555909e-06, + "loss": 0.7195, + "step": 13441 + }, + { + "epoch": 0.8251941434666503, + "grad_norm": 1.0456244281358165, + "learning_rate": 1.559918480197158e-06, + "loss": 0.7839, + "step": 13442 + }, + { + "epoch": 0.8252555327051168, + "grad_norm": 1.0909087108931126, + "learning_rate": 1.5588522347202905e-06, + "loss": 0.7532, + "step": 13443 + }, + { + "epoch": 0.8253169219435833, + "grad_norm": 1.0704002431041217, + "learning_rate": 1.5577863229671408e-06, + "loss": 0.7359, + "step": 13444 + }, + { + "epoch": 0.8253783111820497, + "grad_norm": 0.8684440022885245, + "learning_rate": 1.5567207449798517e-06, + "loss": 0.6992, + "step": 13445 + }, + { + "epoch": 0.8254397004205163, + "grad_norm": 0.9023855710283828, + "learning_rate": 1.5556555008005447e-06, + "loss": 0.7513, + "step": 13446 + }, + { + "epoch": 0.8255010896589828, + "grad_norm": 1.021693336303724, + "learning_rate": 1.5545905904713421e-06, + "loss": 0.696, + "step": 13447 + }, + { + "epoch": 0.8255624788974493, + "grad_norm": 1.0194116571254088, + "learning_rate": 1.5535260140343433e-06, + "loss": 0.7029, + "step": 13448 + }, + { + "epoch": 0.8256238681359158, + "grad_norm": 1.0192542007331322, + "learning_rate": 1.5524617715316348e-06, + "loss": 0.7817, + "step": 13449 + }, + { + "epoch": 0.8256852573743823, + "grad_norm": 0.9796103649715413, + "learning_rate": 1.551397863005294e-06, + "loss": 0.7707, + "step": 13450 + }, + { + "epoch": 0.8257466466128488, + "grad_norm": 0.9769827072234646, + "learning_rate": 1.5503342884973816e-06, + "loss": 0.7493, + "step": 13451 + }, + { + "epoch": 0.8258080358513152, + "grad_norm": 0.9586161861030021, + "learning_rate": 1.5492710480499463e-06, + "loss": 0.7276, + "step": 13452 + }, + { + "epoch": 0.8258694250897818, + "grad_norm": 0.9872820337278974, + "learning_rate": 1.548208141705022e-06, + "loss": 0.7601, + "step": 13453 + }, + { + "epoch": 0.8259308143282482, + "grad_norm": 1.0618363492803526, + "learning_rate": 1.5471455695046366e-06, + "loss": 0.732, + "step": 13454 + }, + { + "epoch": 0.8259922035667148, + "grad_norm": 1.0362895234581095, + "learning_rate": 1.5460833314907975e-06, + "loss": 0.7493, + "step": 13455 + }, + { + "epoch": 0.8260535928051812, + "grad_norm": 0.9771118106464722, + "learning_rate": 1.5450214277054943e-06, + "loss": 0.7191, + "step": 13456 + }, + { + "epoch": 0.8261149820436477, + "grad_norm": 1.10850789156796, + "learning_rate": 1.5439598581907167e-06, + "loss": 0.7656, + "step": 13457 + }, + { + "epoch": 0.8261763712821143, + "grad_norm": 0.901712076711061, + "learning_rate": 1.5428986229884323e-06, + "loss": 0.7345, + "step": 13458 + }, + { + "epoch": 0.8262377605205807, + "grad_norm": 0.9998552257699873, + "learning_rate": 1.5418377221405967e-06, + "loss": 0.7886, + "step": 13459 + }, + { + "epoch": 0.8262991497590473, + "grad_norm": 1.0100419471806785, + "learning_rate": 1.5407771556891538e-06, + "loss": 0.7428, + "step": 13460 + }, + { + "epoch": 0.8263605389975137, + "grad_norm": 0.9778422300363374, + "learning_rate": 1.5397169236760324e-06, + "loss": 0.7611, + "step": 13461 + }, + { + "epoch": 0.8264219282359803, + "grad_norm": 1.138964836418063, + "learning_rate": 1.538657026143151e-06, + "loss": 0.7319, + "step": 13462 + }, + { + "epoch": 0.8264833174744467, + "grad_norm": 0.9630352999073549, + "learning_rate": 1.5375974631324108e-06, + "loss": 0.7291, + "step": 13463 + }, + { + "epoch": 0.8265447067129132, + "grad_norm": 0.9753535646845346, + "learning_rate": 1.5365382346857005e-06, + "loss": 0.6995, + "step": 13464 + }, + { + "epoch": 0.8266060959513797, + "grad_norm": 1.0582043596424404, + "learning_rate": 1.5354793408449043e-06, + "loss": 0.7146, + "step": 13465 + }, + { + "epoch": 0.8266674851898462, + "grad_norm": 1.0723141769909441, + "learning_rate": 1.5344207816518797e-06, + "loss": 0.7694, + "step": 13466 + }, + { + "epoch": 0.8267288744283127, + "grad_norm": 1.0565985249896932, + "learning_rate": 1.5333625571484756e-06, + "loss": 0.7443, + "step": 13467 + }, + { + "epoch": 0.8267902636667792, + "grad_norm": 0.9283380691720935, + "learning_rate": 1.5323046673765352e-06, + "loss": 0.7504, + "step": 13468 + }, + { + "epoch": 0.8268516529052458, + "grad_norm": 1.0287430652885041, + "learning_rate": 1.5312471123778795e-06, + "loss": 0.7594, + "step": 13469 + }, + { + "epoch": 0.8269130421437122, + "grad_norm": 1.0162923913099209, + "learning_rate": 1.5301898921943214e-06, + "loss": 0.7762, + "step": 13470 + }, + { + "epoch": 0.8269744313821787, + "grad_norm": 1.0938368773904175, + "learning_rate": 1.5291330068676525e-06, + "loss": 0.7726, + "step": 13471 + }, + { + "epoch": 0.8270358206206452, + "grad_norm": 1.171048695478072, + "learning_rate": 1.5280764564396632e-06, + "loss": 0.7515, + "step": 13472 + }, + { + "epoch": 0.8270972098591117, + "grad_norm": 1.0554683517426662, + "learning_rate": 1.527020240952123e-06, + "loss": 0.7305, + "step": 13473 + }, + { + "epoch": 0.8271585990975782, + "grad_norm": 1.1155133554986543, + "learning_rate": 1.5259643604467889e-06, + "loss": 0.7743, + "step": 13474 + }, + { + "epoch": 0.8272199883360447, + "grad_norm": 0.9760580993408922, + "learning_rate": 1.5249088149654069e-06, + "loss": 0.7644, + "step": 13475 + }, + { + "epoch": 0.8272813775745111, + "grad_norm": 1.154186575917734, + "learning_rate": 1.5238536045497066e-06, + "loss": 0.7155, + "step": 13476 + }, + { + "epoch": 0.8273427668129777, + "grad_norm": 1.0918109915015088, + "learning_rate": 1.5227987292414071e-06, + "loss": 0.7262, + "step": 13477 + }, + { + "epoch": 0.8274041560514441, + "grad_norm": 0.9461285463979259, + "learning_rate": 1.5217441890822103e-06, + "loss": 0.7417, + "step": 13478 + }, + { + "epoch": 0.8274655452899107, + "grad_norm": 0.9621980786955323, + "learning_rate": 1.5206899841138135e-06, + "loss": 0.7252, + "step": 13479 + }, + { + "epoch": 0.8275269345283772, + "grad_norm": 0.9677165882878003, + "learning_rate": 1.5196361143778937e-06, + "loss": 0.785, + "step": 13480 + }, + { + "epoch": 0.8275883237668437, + "grad_norm": 0.9336014634882304, + "learning_rate": 1.5185825799161114e-06, + "loss": 0.7604, + "step": 13481 + }, + { + "epoch": 0.8276497130053102, + "grad_norm": 0.9270533867602634, + "learning_rate": 1.5175293807701219e-06, + "loss": 0.7618, + "step": 13482 + }, + { + "epoch": 0.8277111022437766, + "grad_norm": 0.9637306728006207, + "learning_rate": 1.5164765169815654e-06, + "loss": 0.7094, + "step": 13483 + }, + { + "epoch": 0.8277724914822432, + "grad_norm": 1.1447854457936086, + "learning_rate": 1.515423988592064e-06, + "loss": 0.7189, + "step": 13484 + }, + { + "epoch": 0.8278338807207096, + "grad_norm": 1.0787538460195556, + "learning_rate": 1.5143717956432312e-06, + "loss": 0.7276, + "step": 13485 + }, + { + "epoch": 0.8278952699591762, + "grad_norm": 0.9440246039290079, + "learning_rate": 1.5133199381766662e-06, + "loss": 0.7284, + "step": 13486 + }, + { + "epoch": 0.8279566591976426, + "grad_norm": 1.0603601171782193, + "learning_rate": 1.512268416233953e-06, + "loss": 0.7837, + "step": 13487 + }, + { + "epoch": 0.8280180484361092, + "grad_norm": 1.0529195752719467, + "learning_rate": 1.5112172298566652e-06, + "loss": 0.7603, + "step": 13488 + }, + { + "epoch": 0.8280794376745757, + "grad_norm": 1.020709809111792, + "learning_rate": 1.5101663790863597e-06, + "loss": 0.7036, + "step": 13489 + }, + { + "epoch": 0.8281408269130421, + "grad_norm": 0.9218192264331754, + "learning_rate": 1.5091158639645886e-06, + "loss": 0.7444, + "step": 13490 + }, + { + "epoch": 0.8282022161515087, + "grad_norm": 0.9547709677137057, + "learning_rate": 1.5080656845328778e-06, + "loss": 0.7295, + "step": 13491 + }, + { + "epoch": 0.8282636053899751, + "grad_norm": 1.0992639224083833, + "learning_rate": 1.5070158408327452e-06, + "loss": 0.7525, + "step": 13492 + }, + { + "epoch": 0.8283249946284417, + "grad_norm": 0.9784961891593231, + "learning_rate": 1.5059663329057028e-06, + "loss": 0.7576, + "step": 13493 + }, + { + "epoch": 0.8283863838669081, + "grad_norm": 1.0034293173533122, + "learning_rate": 1.5049171607932434e-06, + "loss": 0.6805, + "step": 13494 + }, + { + "epoch": 0.8284477731053747, + "grad_norm": 1.0729640866597991, + "learning_rate": 1.5038683245368412e-06, + "loss": 0.8028, + "step": 13495 + }, + { + "epoch": 0.8285091623438411, + "grad_norm": 1.1808232229108497, + "learning_rate": 1.5028198241779611e-06, + "loss": 0.7362, + "step": 13496 + }, + { + "epoch": 0.8285705515823076, + "grad_norm": 0.9456479640691805, + "learning_rate": 1.5017716597580633e-06, + "loss": 0.736, + "step": 13497 + }, + { + "epoch": 0.8286319408207741, + "grad_norm": 1.124458160706348, + "learning_rate": 1.5007238313185823e-06, + "loss": 0.7826, + "step": 13498 + }, + { + "epoch": 0.8286933300592406, + "grad_norm": 1.0690921490248382, + "learning_rate": 1.4996763389009461e-06, + "loss": 0.7418, + "step": 13499 + }, + { + "epoch": 0.8287547192977072, + "grad_norm": 0.96440140693749, + "learning_rate": 1.4986291825465682e-06, + "loss": 0.7473, + "step": 13500 + }, + { + "epoch": 0.8288161085361736, + "grad_norm": 1.071124115491158, + "learning_rate": 1.4975823622968455e-06, + "loss": 0.7019, + "step": 13501 + }, + { + "epoch": 0.8288774977746401, + "grad_norm": 0.8942496131126234, + "learning_rate": 1.4965358781931672e-06, + "loss": 0.7328, + "step": 13502 + }, + { + "epoch": 0.8289388870131066, + "grad_norm": 0.9827558363848449, + "learning_rate": 1.4954897302769022e-06, + "loss": 0.7161, + "step": 13503 + }, + { + "epoch": 0.8290002762515731, + "grad_norm": 1.0517832240490876, + "learning_rate": 1.4944439185894188e-06, + "loss": 0.7093, + "step": 13504 + }, + { + "epoch": 0.8290616654900396, + "grad_norm": 1.1333632747375921, + "learning_rate": 1.493398443172056e-06, + "loss": 0.7661, + "step": 13505 + }, + { + "epoch": 0.8291230547285061, + "grad_norm": 0.9952841518823206, + "learning_rate": 1.4923533040661464e-06, + "loss": 0.7587, + "step": 13506 + }, + { + "epoch": 0.8291844439669726, + "grad_norm": 1.0096443608172332, + "learning_rate": 1.4913085013130158e-06, + "loss": 0.747, + "step": 13507 + }, + { + "epoch": 0.8292458332054391, + "grad_norm": 0.9544886644242782, + "learning_rate": 1.4902640349539676e-06, + "loss": 0.7381, + "step": 13508 + }, + { + "epoch": 0.8293072224439055, + "grad_norm": 1.0658497571319234, + "learning_rate": 1.4892199050302968e-06, + "loss": 0.762, + "step": 13509 + }, + { + "epoch": 0.8293686116823721, + "grad_norm": 1.0604464403519032, + "learning_rate": 1.4881761115832782e-06, + "loss": 0.7087, + "step": 13510 + }, + { + "epoch": 0.8294300009208386, + "grad_norm": 1.0239558222171883, + "learning_rate": 1.4871326546541843e-06, + "loss": 0.7477, + "step": 13511 + }, + { + "epoch": 0.8294913901593051, + "grad_norm": 0.9343642452300778, + "learning_rate": 1.4860895342842674e-06, + "loss": 0.7841, + "step": 13512 + }, + { + "epoch": 0.8295527793977716, + "grad_norm": 1.011253258750002, + "learning_rate": 1.4850467505147658e-06, + "loss": 0.7288, + "step": 13513 + }, + { + "epoch": 0.829614168636238, + "grad_norm": 0.9702032442841831, + "learning_rate": 1.4840043033869079e-06, + "loss": 0.7982, + "step": 13514 + }, + { + "epoch": 0.8296755578747046, + "grad_norm": 0.967070168621538, + "learning_rate": 1.4829621929419069e-06, + "loss": 0.7665, + "step": 13515 + }, + { + "epoch": 0.829736947113171, + "grad_norm": 1.0456239322145056, + "learning_rate": 1.4819204192209613e-06, + "loss": 0.7329, + "step": 13516 + }, + { + "epoch": 0.8297983363516376, + "grad_norm": 0.9174193449116611, + "learning_rate": 1.480878982265258e-06, + "loss": 0.7408, + "step": 13517 + }, + { + "epoch": 0.829859725590104, + "grad_norm": 1.0941034973417605, + "learning_rate": 1.4798378821159753e-06, + "loss": 0.7447, + "step": 13518 + }, + { + "epoch": 0.8299211148285706, + "grad_norm": 1.0299508331787723, + "learning_rate": 1.4787971188142713e-06, + "loss": 0.7243, + "step": 13519 + }, + { + "epoch": 0.829982504067037, + "grad_norm": 1.0650316168671758, + "learning_rate": 1.4777566924012877e-06, + "loss": 0.7461, + "step": 13520 + }, + { + "epoch": 0.8300438933055035, + "grad_norm": 1.1067318161324453, + "learning_rate": 1.4767166029181635e-06, + "loss": 0.7488, + "step": 13521 + }, + { + "epoch": 0.8301052825439701, + "grad_norm": 0.9364495343842689, + "learning_rate": 1.4756768504060193e-06, + "loss": 0.726, + "step": 13522 + }, + { + "epoch": 0.8301666717824365, + "grad_norm": 1.1949082231219084, + "learning_rate": 1.474637434905959e-06, + "loss": 0.7999, + "step": 13523 + }, + { + "epoch": 0.8302280610209031, + "grad_norm": 1.03791132306055, + "learning_rate": 1.4735983564590784e-06, + "loss": 0.7292, + "step": 13524 + }, + { + "epoch": 0.8302894502593695, + "grad_norm": 1.0111018190534797, + "learning_rate": 1.472559615106457e-06, + "loss": 0.7243, + "step": 13525 + }, + { + "epoch": 0.8303508394978361, + "grad_norm": 1.0603323081920786, + "learning_rate": 1.471521210889162e-06, + "loss": 0.7579, + "step": 13526 + }, + { + "epoch": 0.8304122287363025, + "grad_norm": 1.1454013027617034, + "learning_rate": 1.470483143848247e-06, + "loss": 0.7074, + "step": 13527 + }, + { + "epoch": 0.830473617974769, + "grad_norm": 1.0760050705452353, + "learning_rate": 1.4694454140247506e-06, + "loss": 0.7286, + "step": 13528 + }, + { + "epoch": 0.8305350072132355, + "grad_norm": 0.9947668825484757, + "learning_rate": 1.4684080214597064e-06, + "loss": 0.8107, + "step": 13529 + }, + { + "epoch": 0.830596396451702, + "grad_norm": 1.1718136073630758, + "learning_rate": 1.4673709661941205e-06, + "loss": 0.7677, + "step": 13530 + }, + { + "epoch": 0.8306577856901685, + "grad_norm": 0.9009009218900255, + "learning_rate": 1.4663342482689935e-06, + "loss": 0.7287, + "step": 13531 + }, + { + "epoch": 0.830719174928635, + "grad_norm": 1.043268988129527, + "learning_rate": 1.465297867725317e-06, + "loss": 0.7249, + "step": 13532 + }, + { + "epoch": 0.8307805641671016, + "grad_norm": 1.0605103559136002, + "learning_rate": 1.464261824604063e-06, + "loss": 0.748, + "step": 13533 + }, + { + "epoch": 0.830841953405568, + "grad_norm": 1.0130211561468698, + "learning_rate": 1.4632261189461937e-06, + "loss": 0.7644, + "step": 13534 + }, + { + "epoch": 0.8309033426440345, + "grad_norm": 1.1080150467733707, + "learning_rate": 1.4621907507926493e-06, + "loss": 0.7359, + "step": 13535 + }, + { + "epoch": 0.830964731882501, + "grad_norm": 0.9732263961705279, + "learning_rate": 1.4611557201843696e-06, + "loss": 0.7404, + "step": 13536 + }, + { + "epoch": 0.8310261211209675, + "grad_norm": 1.1770531520657939, + "learning_rate": 1.4601210271622735e-06, + "loss": 0.7252, + "step": 13537 + }, + { + "epoch": 0.831087510359434, + "grad_norm": 0.98545118840753, + "learning_rate": 1.459086671767268e-06, + "loss": 0.7646, + "step": 13538 + }, + { + "epoch": 0.8311488995979005, + "grad_norm": 1.136507719669205, + "learning_rate": 1.4580526540402462e-06, + "loss": 0.7005, + "step": 13539 + }, + { + "epoch": 0.8312102888363669, + "grad_norm": 1.0084420798058147, + "learning_rate": 1.4570189740220885e-06, + "loss": 0.793, + "step": 13540 + }, + { + "epoch": 0.8312716780748335, + "grad_norm": 0.9056006963335627, + "learning_rate": 1.4559856317536624e-06, + "loss": 0.7376, + "step": 13541 + }, + { + "epoch": 0.8313330673133, + "grad_norm": 0.9861148375930194, + "learning_rate": 1.4549526272758185e-06, + "loss": 0.7504, + "step": 13542 + }, + { + "epoch": 0.8313944565517665, + "grad_norm": 0.9863304650733492, + "learning_rate": 1.4539199606294007e-06, + "loss": 0.7569, + "step": 13543 + }, + { + "epoch": 0.831455845790233, + "grad_norm": 0.9949732113504697, + "learning_rate": 1.4528876318552375e-06, + "loss": 0.7521, + "step": 13544 + }, + { + "epoch": 0.8315172350286995, + "grad_norm": 1.0017079057632319, + "learning_rate": 1.4518556409941342e-06, + "loss": 0.7616, + "step": 13545 + }, + { + "epoch": 0.831578624267166, + "grad_norm": 1.052060496298701, + "learning_rate": 1.4508239880868992e-06, + "loss": 0.7998, + "step": 13546 + }, + { + "epoch": 0.8316400135056324, + "grad_norm": 1.1132880037206785, + "learning_rate": 1.449792673174316e-06, + "loss": 0.739, + "step": 13547 + }, + { + "epoch": 0.831701402744099, + "grad_norm": 0.9555046996367134, + "learning_rate": 1.4487616962971573e-06, + "loss": 0.6798, + "step": 13548 + }, + { + "epoch": 0.8317627919825654, + "grad_norm": 1.0790626459590937, + "learning_rate": 1.4477310574961856e-06, + "loss": 0.699, + "step": 13549 + }, + { + "epoch": 0.831824181221032, + "grad_norm": 0.5888891981833742, + "learning_rate": 1.446700756812145e-06, + "loss": 0.6519, + "step": 13550 + }, + { + "epoch": 0.8318855704594984, + "grad_norm": 0.9330447022055721, + "learning_rate": 1.4456707942857696e-06, + "loss": 0.7458, + "step": 13551 + }, + { + "epoch": 0.831946959697965, + "grad_norm": 1.1142040235853996, + "learning_rate": 1.444641169957779e-06, + "loss": 0.6994, + "step": 13552 + }, + { + "epoch": 0.8320083489364315, + "grad_norm": 1.0030216615378893, + "learning_rate": 1.4436118838688795e-06, + "loss": 0.7425, + "step": 13553 + }, + { + "epoch": 0.8320697381748979, + "grad_norm": 1.0458696098063274, + "learning_rate": 1.4425829360597676e-06, + "loss": 0.7127, + "step": 13554 + }, + { + "epoch": 0.8321311274133645, + "grad_norm": 1.0835267797943557, + "learning_rate": 1.4415543265711196e-06, + "loss": 0.7603, + "step": 13555 + }, + { + "epoch": 0.8321925166518309, + "grad_norm": 1.167626352634458, + "learning_rate": 1.4405260554436007e-06, + "loss": 0.8082, + "step": 13556 + }, + { + "epoch": 0.8322539058902975, + "grad_norm": 1.0248457652407699, + "learning_rate": 1.4394981227178673e-06, + "loss": 0.7125, + "step": 13557 + }, + { + "epoch": 0.8323152951287639, + "grad_norm": 1.0420923192239708, + "learning_rate": 1.4384705284345613e-06, + "loss": 0.7293, + "step": 13558 + }, + { + "epoch": 0.8323766843672304, + "grad_norm": 1.1367176663151222, + "learning_rate": 1.4374432726343002e-06, + "loss": 0.7099, + "step": 13559 + }, + { + "epoch": 0.8324380736056969, + "grad_norm": 0.9848590363325459, + "learning_rate": 1.4364163553577048e-06, + "loss": 0.6996, + "step": 13560 + }, + { + "epoch": 0.8324994628441634, + "grad_norm": 1.047436118262556, + "learning_rate": 1.4353897766453729e-06, + "loss": 0.6753, + "step": 13561 + }, + { + "epoch": 0.8325608520826299, + "grad_norm": 0.9487301995449526, + "learning_rate": 1.4343635365378895e-06, + "loss": 0.6943, + "step": 13562 + }, + { + "epoch": 0.8326222413210964, + "grad_norm": 1.130376376406256, + "learning_rate": 1.4333376350758265e-06, + "loss": 0.7288, + "step": 13563 + }, + { + "epoch": 0.832683630559563, + "grad_norm": 1.0854648144852774, + "learning_rate": 1.4323120722997463e-06, + "loss": 0.7151, + "step": 13564 + }, + { + "epoch": 0.8327450197980294, + "grad_norm": 1.0309403741080037, + "learning_rate": 1.4312868482501918e-06, + "loss": 0.6618, + "step": 13565 + }, + { + "epoch": 0.8328064090364959, + "grad_norm": 1.0671386326933008, + "learning_rate": 1.4302619629676972e-06, + "loss": 0.7432, + "step": 13566 + }, + { + "epoch": 0.8328677982749624, + "grad_norm": 1.059735556844931, + "learning_rate": 1.4292374164927803e-06, + "loss": 0.7141, + "step": 13567 + }, + { + "epoch": 0.8329291875134289, + "grad_norm": 1.1409076781553509, + "learning_rate": 1.4282132088659506e-06, + "loss": 0.732, + "step": 13568 + }, + { + "epoch": 0.8329905767518954, + "grad_norm": 1.200099691987759, + "learning_rate": 1.4271893401276972e-06, + "loss": 0.7575, + "step": 13569 + }, + { + "epoch": 0.8330519659903619, + "grad_norm": 1.1436429818635876, + "learning_rate": 1.426165810318496e-06, + "loss": 0.7474, + "step": 13570 + }, + { + "epoch": 0.8331133552288283, + "grad_norm": 0.9719688537487121, + "learning_rate": 1.4251426194788197e-06, + "loss": 0.7145, + "step": 13571 + }, + { + "epoch": 0.8331747444672949, + "grad_norm": 1.0294743865300613, + "learning_rate": 1.424119767649118e-06, + "loss": 0.7071, + "step": 13572 + }, + { + "epoch": 0.8332361337057613, + "grad_norm": 0.6202191022055926, + "learning_rate": 1.4230972548698295e-06, + "loss": 0.6911, + "step": 13573 + }, + { + "epoch": 0.8332975229442279, + "grad_norm": 1.0622842780288733, + "learning_rate": 1.4220750811813754e-06, + "loss": 0.6991, + "step": 13574 + }, + { + "epoch": 0.8333589121826944, + "grad_norm": 1.0770612939949578, + "learning_rate": 1.4210532466241733e-06, + "loss": 0.7202, + "step": 13575 + }, + { + "epoch": 0.8334203014211609, + "grad_norm": 1.0313967748644612, + "learning_rate": 1.4200317512386196e-06, + "loss": 0.7152, + "step": 13576 + }, + { + "epoch": 0.8334816906596274, + "grad_norm": 1.0080226783126536, + "learning_rate": 1.4190105950651e-06, + "loss": 0.7271, + "step": 13577 + }, + { + "epoch": 0.8335430798980938, + "grad_norm": 1.0272294278299345, + "learning_rate": 1.4179897781439867e-06, + "loss": 0.7149, + "step": 13578 + }, + { + "epoch": 0.8336044691365604, + "grad_norm": 1.15368790474462, + "learning_rate": 1.416969300515636e-06, + "loss": 0.7398, + "step": 13579 + }, + { + "epoch": 0.8336658583750268, + "grad_norm": 1.0317725141664567, + "learning_rate": 1.4159491622203947e-06, + "loss": 0.7643, + "step": 13580 + }, + { + "epoch": 0.8337272476134934, + "grad_norm": 1.101909958065358, + "learning_rate": 1.4149293632985917e-06, + "loss": 0.7414, + "step": 13581 + }, + { + "epoch": 0.8337886368519598, + "grad_norm": 1.1168725789022063, + "learning_rate": 1.4139099037905491e-06, + "loss": 0.7014, + "step": 13582 + }, + { + "epoch": 0.8338500260904264, + "grad_norm": 1.0007811391084396, + "learning_rate": 1.4128907837365724e-06, + "loss": 0.7441, + "step": 13583 + }, + { + "epoch": 0.8339114153288928, + "grad_norm": 1.0581338956111754, + "learning_rate": 1.4118720031769451e-06, + "loss": 0.7557, + "step": 13584 + }, + { + "epoch": 0.8339728045673593, + "grad_norm": 1.080873180792526, + "learning_rate": 1.4108535621519514e-06, + "loss": 0.7419, + "step": 13585 + }, + { + "epoch": 0.8340341938058259, + "grad_norm": 1.0087732676042631, + "learning_rate": 1.409835460701856e-06, + "loss": 0.7314, + "step": 13586 + }, + { + "epoch": 0.8340955830442923, + "grad_norm": 0.9874116397393137, + "learning_rate": 1.4088176988669077e-06, + "loss": 0.7601, + "step": 13587 + }, + { + "epoch": 0.8341569722827589, + "grad_norm": 1.1019286732168698, + "learning_rate": 1.4078002766873444e-06, + "loss": 0.6927, + "step": 13588 + }, + { + "epoch": 0.8342183615212253, + "grad_norm": 0.9465878130443689, + "learning_rate": 1.4067831942033904e-06, + "loss": 0.7304, + "step": 13589 + }, + { + "epoch": 0.8342797507596919, + "grad_norm": 1.025760975885889, + "learning_rate": 1.4057664514552572e-06, + "loss": 0.7165, + "step": 13590 + }, + { + "epoch": 0.8343411399981583, + "grad_norm": 1.045841263184649, + "learning_rate": 1.40475004848314e-06, + "loss": 0.7225, + "step": 13591 + }, + { + "epoch": 0.8344025292366248, + "grad_norm": 1.0414148079757997, + "learning_rate": 1.4037339853272225e-06, + "loss": 0.8054, + "step": 13592 + }, + { + "epoch": 0.8344639184750913, + "grad_norm": 1.0500991930639396, + "learning_rate": 1.4027182620276814e-06, + "loss": 0.7167, + "step": 13593 + }, + { + "epoch": 0.8345253077135578, + "grad_norm": 0.9417032724929869, + "learning_rate": 1.4017028786246666e-06, + "loss": 0.7234, + "step": 13594 + }, + { + "epoch": 0.8345866969520244, + "grad_norm": 1.0275678357021607, + "learning_rate": 1.400687835158322e-06, + "loss": 0.6883, + "step": 13595 + }, + { + "epoch": 0.8346480861904908, + "grad_norm": 1.1039288018845421, + "learning_rate": 1.3996731316687805e-06, + "loss": 0.7301, + "step": 13596 + }, + { + "epoch": 0.8347094754289573, + "grad_norm": 0.9706139917075967, + "learning_rate": 1.3986587681961595e-06, + "loss": 0.7224, + "step": 13597 + }, + { + "epoch": 0.8347708646674238, + "grad_norm": 1.0844013963986454, + "learning_rate": 1.3976447447805596e-06, + "loss": 0.7248, + "step": 13598 + }, + { + "epoch": 0.8348322539058903, + "grad_norm": 1.0648528543125955, + "learning_rate": 1.3966310614620726e-06, + "loss": 0.7343, + "step": 13599 + }, + { + "epoch": 0.8348936431443568, + "grad_norm": 1.0153116620739833, + "learning_rate": 1.395617718280773e-06, + "loss": 0.6904, + "step": 13600 + }, + { + "epoch": 0.8349550323828233, + "grad_norm": 1.042985012403505, + "learning_rate": 1.394604715276724e-06, + "loss": 0.7164, + "step": 13601 + }, + { + "epoch": 0.8350164216212898, + "grad_norm": 1.036495771697524, + "learning_rate": 1.393592052489976e-06, + "loss": 0.7165, + "step": 13602 + }, + { + "epoch": 0.8350778108597563, + "grad_norm": 0.9564334829416932, + "learning_rate": 1.3925797299605649e-06, + "loss": 0.7301, + "step": 13603 + }, + { + "epoch": 0.8351392000982227, + "grad_norm": 0.950295672179549, + "learning_rate": 1.3915677477285129e-06, + "loss": 0.7537, + "step": 13604 + }, + { + "epoch": 0.8352005893366893, + "grad_norm": 1.0444377275636139, + "learning_rate": 1.390556105833828e-06, + "loss": 0.7262, + "step": 13605 + }, + { + "epoch": 0.8352619785751558, + "grad_norm": 0.9625036269111743, + "learning_rate": 1.389544804316505e-06, + "loss": 0.784, + "step": 13606 + }, + { + "epoch": 0.8353233678136223, + "grad_norm": 0.9550499054386512, + "learning_rate": 1.3885338432165295e-06, + "loss": 0.7406, + "step": 13607 + }, + { + "epoch": 0.8353847570520888, + "grad_norm": 0.9801737594281533, + "learning_rate": 1.3875232225738722e-06, + "loss": 0.7248, + "step": 13608 + }, + { + "epoch": 0.8354461462905552, + "grad_norm": 1.1045730558845004, + "learning_rate": 1.3865129424284785e-06, + "loss": 0.7183, + "step": 13609 + }, + { + "epoch": 0.8355075355290218, + "grad_norm": 0.9755912361247557, + "learning_rate": 1.3855030028202997e-06, + "loss": 0.7492, + "step": 13610 + }, + { + "epoch": 0.8355689247674882, + "grad_norm": 1.006367485313034, + "learning_rate": 1.384493403789261e-06, + "loss": 0.7433, + "step": 13611 + }, + { + "epoch": 0.8356303140059548, + "grad_norm": 0.9506043554627466, + "learning_rate": 1.3834841453752768e-06, + "loss": 0.7516, + "step": 13612 + }, + { + "epoch": 0.8356917032444212, + "grad_norm": 1.0382779908559105, + "learning_rate": 1.3824752276182474e-06, + "loss": 0.7201, + "step": 13613 + }, + { + "epoch": 0.8357530924828878, + "grad_norm": 1.0662293426944063, + "learning_rate": 1.3814666505580632e-06, + "loss": 0.7207, + "step": 13614 + }, + { + "epoch": 0.8358144817213542, + "grad_norm": 1.0581333971501443, + "learning_rate": 1.3804584142345977e-06, + "loss": 0.7218, + "step": 13615 + }, + { + "epoch": 0.8358758709598207, + "grad_norm": 1.0061904798229353, + "learning_rate": 1.3794505186877117e-06, + "loss": 0.7789, + "step": 13616 + }, + { + "epoch": 0.8359372601982873, + "grad_norm": 0.9592394014854063, + "learning_rate": 1.3784429639572494e-06, + "loss": 0.6707, + "step": 13617 + }, + { + "epoch": 0.8359986494367537, + "grad_norm": 1.0231397680602592, + "learning_rate": 1.3774357500830527e-06, + "loss": 0.6985, + "step": 13618 + }, + { + "epoch": 0.8360600386752203, + "grad_norm": 0.61711703852891, + "learning_rate": 1.376428877104936e-06, + "loss": 0.6805, + "step": 13619 + }, + { + "epoch": 0.8361214279136867, + "grad_norm": 0.9378649078866743, + "learning_rate": 1.3754223450627057e-06, + "loss": 0.7049, + "step": 13620 + }, + { + "epoch": 0.8361828171521533, + "grad_norm": 0.9793553766628277, + "learning_rate": 1.3744161539961588e-06, + "loss": 0.759, + "step": 13621 + }, + { + "epoch": 0.8362442063906197, + "grad_norm": 0.9462662115864576, + "learning_rate": 1.3734103039450752e-06, + "loss": 0.7438, + "step": 13622 + }, + { + "epoch": 0.8363055956290862, + "grad_norm": 1.0795238568611984, + "learning_rate": 1.3724047949492203e-06, + "loss": 0.7462, + "step": 13623 + }, + { + "epoch": 0.8363669848675527, + "grad_norm": 1.1195674144158865, + "learning_rate": 1.3713996270483475e-06, + "loss": 0.7209, + "step": 13624 + }, + { + "epoch": 0.8364283741060192, + "grad_norm": 0.9898425069025069, + "learning_rate": 1.3703948002821954e-06, + "loss": 0.7005, + "step": 13625 + }, + { + "epoch": 0.8364897633444857, + "grad_norm": 0.9649565792233655, + "learning_rate": 1.369390314690493e-06, + "loss": 0.6929, + "step": 13626 + }, + { + "epoch": 0.8365511525829522, + "grad_norm": 0.9661153512702257, + "learning_rate": 1.3683861703129498e-06, + "loss": 0.716, + "step": 13627 + }, + { + "epoch": 0.8366125418214188, + "grad_norm": 1.0166549687856694, + "learning_rate": 1.3673823671892673e-06, + "loss": 0.7198, + "step": 13628 + }, + { + "epoch": 0.8366739310598852, + "grad_norm": 1.1075727052679238, + "learning_rate": 1.3663789053591292e-06, + "loss": 0.7602, + "step": 13629 + }, + { + "epoch": 0.8367353202983517, + "grad_norm": 1.0683084530695481, + "learning_rate": 1.3653757848622096e-06, + "loss": 0.6948, + "step": 13630 + }, + { + "epoch": 0.8367967095368182, + "grad_norm": 1.1385906050568895, + "learning_rate": 1.3643730057381643e-06, + "loss": 0.7726, + "step": 13631 + }, + { + "epoch": 0.8368580987752847, + "grad_norm": 1.0480031024370695, + "learning_rate": 1.3633705680266452e-06, + "loss": 0.737, + "step": 13632 + }, + { + "epoch": 0.8369194880137512, + "grad_norm": 1.0491147950371462, + "learning_rate": 1.362368471767277e-06, + "loss": 0.7433, + "step": 13633 + }, + { + "epoch": 0.8369808772522177, + "grad_norm": 0.9136415937813773, + "learning_rate": 1.361366716999678e-06, + "loss": 0.7645, + "step": 13634 + }, + { + "epoch": 0.8370422664906841, + "grad_norm": 1.127702852628579, + "learning_rate": 1.3603653037634579e-06, + "loss": 0.7267, + "step": 13635 + }, + { + "epoch": 0.8371036557291507, + "grad_norm": 0.9839765024727751, + "learning_rate": 1.3593642320982047e-06, + "loss": 0.7275, + "step": 13636 + }, + { + "epoch": 0.8371650449676171, + "grad_norm": 1.119367610194913, + "learning_rate": 1.3583635020434983e-06, + "loss": 0.724, + "step": 13637 + }, + { + "epoch": 0.8372264342060837, + "grad_norm": 1.084019774150591, + "learning_rate": 1.3573631136388998e-06, + "loss": 0.7127, + "step": 13638 + }, + { + "epoch": 0.8372878234445502, + "grad_norm": 1.0420066533341479, + "learning_rate": 1.3563630669239625e-06, + "loss": 0.6718, + "step": 13639 + }, + { + "epoch": 0.8373492126830167, + "grad_norm": 1.037664345403291, + "learning_rate": 1.3553633619382223e-06, + "loss": 0.7069, + "step": 13640 + }, + { + "epoch": 0.8374106019214832, + "grad_norm": 1.0913700651204756, + "learning_rate": 1.3543639987212032e-06, + "loss": 0.6869, + "step": 13641 + }, + { + "epoch": 0.8374719911599496, + "grad_norm": 1.0738030037147432, + "learning_rate": 1.3533649773124147e-06, + "loss": 0.7356, + "step": 13642 + }, + { + "epoch": 0.8375333803984162, + "grad_norm": 1.009077552503112, + "learning_rate": 1.352366297751354e-06, + "loss": 0.7582, + "step": 13643 + }, + { + "epoch": 0.8375947696368826, + "grad_norm": 1.0760236961735876, + "learning_rate": 1.3513679600775053e-06, + "loss": 0.7541, + "step": 13644 + }, + { + "epoch": 0.8376561588753492, + "grad_norm": 0.9600414540082063, + "learning_rate": 1.3503699643303347e-06, + "loss": 0.7162, + "step": 13645 + }, + { + "epoch": 0.8377175481138156, + "grad_norm": 1.0381138364635065, + "learning_rate": 1.3493723105493029e-06, + "loss": 0.7071, + "step": 13646 + }, + { + "epoch": 0.8377789373522821, + "grad_norm": 0.9757679934974346, + "learning_rate": 1.3483749987738525e-06, + "loss": 0.7038, + "step": 13647 + }, + { + "epoch": 0.8378403265907487, + "grad_norm": 0.9986968377408271, + "learning_rate": 1.3473780290434069e-06, + "loss": 0.7498, + "step": 13648 + }, + { + "epoch": 0.8379017158292151, + "grad_norm": 1.1193783381338351, + "learning_rate": 1.3463814013973875e-06, + "loss": 0.7505, + "step": 13649 + }, + { + "epoch": 0.8379631050676817, + "grad_norm": 1.0633783766422233, + "learning_rate": 1.345385115875193e-06, + "loss": 0.7189, + "step": 13650 + }, + { + "epoch": 0.8380244943061481, + "grad_norm": 1.0878238453108473, + "learning_rate": 1.344389172516214e-06, + "loss": 0.762, + "step": 13651 + }, + { + "epoch": 0.8380858835446147, + "grad_norm": 1.0342230368140262, + "learning_rate": 1.3433935713598245e-06, + "loss": 0.733, + "step": 13652 + }, + { + "epoch": 0.8381472727830811, + "grad_norm": 1.1120269759842223, + "learning_rate": 1.3423983124453855e-06, + "loss": 0.7629, + "step": 13653 + }, + { + "epoch": 0.8382086620215476, + "grad_norm": 1.0821612048838423, + "learning_rate": 1.3414033958122452e-06, + "loss": 0.7647, + "step": 13654 + }, + { + "epoch": 0.8382700512600141, + "grad_norm": 1.050099782585406, + "learning_rate": 1.340408821499738e-06, + "loss": 0.7452, + "step": 13655 + }, + { + "epoch": 0.8383314404984806, + "grad_norm": 0.947952276620062, + "learning_rate": 1.3394145895471832e-06, + "loss": 0.7586, + "step": 13656 + }, + { + "epoch": 0.8383928297369471, + "grad_norm": 1.0040038001157034, + "learning_rate": 1.3384206999938943e-06, + "loss": 0.7209, + "step": 13657 + }, + { + "epoch": 0.8384542189754136, + "grad_norm": 1.0058819116631887, + "learning_rate": 1.3374271528791572e-06, + "loss": 0.7293, + "step": 13658 + }, + { + "epoch": 0.8385156082138802, + "grad_norm": 1.0107557529646067, + "learning_rate": 1.336433948242254e-06, + "loss": 0.7294, + "step": 13659 + }, + { + "epoch": 0.8385769974523466, + "grad_norm": 0.9617347498745468, + "learning_rate": 1.3354410861224555e-06, + "loss": 0.7423, + "step": 13660 + }, + { + "epoch": 0.8386383866908131, + "grad_norm": 1.1090185661346503, + "learning_rate": 1.3344485665590113e-06, + "loss": 0.7913, + "step": 13661 + }, + { + "epoch": 0.8386997759292796, + "grad_norm": 1.037619663230858, + "learning_rate": 1.3334563895911624e-06, + "loss": 0.6808, + "step": 13662 + }, + { + "epoch": 0.8387611651677461, + "grad_norm": 0.9889937489659959, + "learning_rate": 1.332464555258134e-06, + "loss": 0.7112, + "step": 13663 + }, + { + "epoch": 0.8388225544062126, + "grad_norm": 1.0421280681998677, + "learning_rate": 1.3314730635991391e-06, + "loss": 0.7342, + "step": 13664 + }, + { + "epoch": 0.8388839436446791, + "grad_norm": 1.007246457807137, + "learning_rate": 1.3304819146533765e-06, + "loss": 0.7571, + "step": 13665 + }, + { + "epoch": 0.8389453328831455, + "grad_norm": 1.0356386568208655, + "learning_rate": 1.3294911084600315e-06, + "loss": 0.7492, + "step": 13666 + }, + { + "epoch": 0.8390067221216121, + "grad_norm": 1.0254241396475703, + "learning_rate": 1.3285006450582771e-06, + "loss": 0.7393, + "step": 13667 + }, + { + "epoch": 0.8390681113600785, + "grad_norm": 0.9320616579851811, + "learning_rate": 1.32751052448727e-06, + "loss": 0.7267, + "step": 13668 + }, + { + "epoch": 0.8391295005985451, + "grad_norm": 0.5976379087379583, + "learning_rate": 1.3265207467861552e-06, + "loss": 0.6757, + "step": 13669 + }, + { + "epoch": 0.8391908898370116, + "grad_norm": 1.0414775387165902, + "learning_rate": 1.3255313119940626e-06, + "loss": 0.711, + "step": 13670 + }, + { + "epoch": 0.8392522790754781, + "grad_norm": 0.989290818044115, + "learning_rate": 1.3245422201501135e-06, + "loss": 0.7542, + "step": 13671 + }, + { + "epoch": 0.8393136683139446, + "grad_norm": 0.9996688162577263, + "learning_rate": 1.3235534712934118e-06, + "loss": 0.7086, + "step": 13672 + }, + { + "epoch": 0.839375057552411, + "grad_norm": 1.0520072259186748, + "learning_rate": 1.322565065463043e-06, + "loss": 0.7307, + "step": 13673 + }, + { + "epoch": 0.8394364467908776, + "grad_norm": 1.1401059915723057, + "learning_rate": 1.321577002698089e-06, + "loss": 0.7895, + "step": 13674 + }, + { + "epoch": 0.839497836029344, + "grad_norm": 0.973818435006207, + "learning_rate": 1.3205892830376111e-06, + "loss": 0.7123, + "step": 13675 + }, + { + "epoch": 0.8395592252678106, + "grad_norm": 1.0222432115945965, + "learning_rate": 1.31960190652066e-06, + "loss": 0.7208, + "step": 13676 + }, + { + "epoch": 0.839620614506277, + "grad_norm": 1.104677320928059, + "learning_rate": 1.3186148731862712e-06, + "loss": 0.7531, + "step": 13677 + }, + { + "epoch": 0.8396820037447436, + "grad_norm": 0.9918606749497585, + "learning_rate": 1.3176281830734682e-06, + "loss": 0.7497, + "step": 13678 + }, + { + "epoch": 0.83974339298321, + "grad_norm": 1.1205452548997112, + "learning_rate": 1.3166418362212596e-06, + "loss": 0.7654, + "step": 13679 + }, + { + "epoch": 0.8398047822216765, + "grad_norm": 0.965380576087947, + "learning_rate": 1.3156558326686409e-06, + "loss": 0.7508, + "step": 13680 + }, + { + "epoch": 0.8398661714601431, + "grad_norm": 1.0082870727216513, + "learning_rate": 1.314670172454593e-06, + "loss": 0.7553, + "step": 13681 + }, + { + "epoch": 0.8399275606986095, + "grad_norm": 0.8792638083445787, + "learning_rate": 1.3136848556180893e-06, + "loss": 0.7725, + "step": 13682 + }, + { + "epoch": 0.8399889499370761, + "grad_norm": 0.9738413364401862, + "learning_rate": 1.3126998821980786e-06, + "loss": 0.7298, + "step": 13683 + }, + { + "epoch": 0.8400503391755425, + "grad_norm": 1.092558163112394, + "learning_rate": 1.311715252233502e-06, + "loss": 0.7199, + "step": 13684 + }, + { + "epoch": 0.840111728414009, + "grad_norm": 1.0270985262115613, + "learning_rate": 1.3107309657632927e-06, + "loss": 0.7591, + "step": 13685 + }, + { + "epoch": 0.8401731176524755, + "grad_norm": 0.8866112476977327, + "learning_rate": 1.309747022826361e-06, + "loss": 0.7026, + "step": 13686 + }, + { + "epoch": 0.840234506890942, + "grad_norm": 1.0937886947884772, + "learning_rate": 1.3087634234616087e-06, + "loss": 0.7143, + "step": 13687 + }, + { + "epoch": 0.8402958961294085, + "grad_norm": 1.0823997639439062, + "learning_rate": 1.3077801677079228e-06, + "loss": 0.7608, + "step": 13688 + }, + { + "epoch": 0.840357285367875, + "grad_norm": 1.1542494536665053, + "learning_rate": 1.3067972556041753e-06, + "loss": 0.756, + "step": 13689 + }, + { + "epoch": 0.8404186746063415, + "grad_norm": 1.0838394359665209, + "learning_rate": 1.3058146871892275e-06, + "loss": 0.7405, + "step": 13690 + }, + { + "epoch": 0.840480063844808, + "grad_norm": 1.0362217324870315, + "learning_rate": 1.3048324625019238e-06, + "loss": 0.726, + "step": 13691 + }, + { + "epoch": 0.8405414530832745, + "grad_norm": 1.0635416133298958, + "learning_rate": 1.3038505815810986e-06, + "loss": 0.7872, + "step": 13692 + }, + { + "epoch": 0.840602842321741, + "grad_norm": 1.056168308888812, + "learning_rate": 1.30286904446557e-06, + "loss": 0.7552, + "step": 13693 + }, + { + "epoch": 0.8406642315602075, + "grad_norm": 1.0998503037542091, + "learning_rate": 1.3018878511941436e-06, + "loss": 0.7109, + "step": 13694 + }, + { + "epoch": 0.840725620798674, + "grad_norm": 1.0485259041574997, + "learning_rate": 1.3009070018056092e-06, + "loss": 0.7043, + "step": 13695 + }, + { + "epoch": 0.8407870100371405, + "grad_norm": 1.0213751851912567, + "learning_rate": 1.2999264963387514e-06, + "loss": 0.7287, + "step": 13696 + }, + { + "epoch": 0.840848399275607, + "grad_norm": 1.0820930221962166, + "learning_rate": 1.2989463348323284e-06, + "loss": 0.7699, + "step": 13697 + }, + { + "epoch": 0.8409097885140735, + "grad_norm": 0.9699400834231722, + "learning_rate": 1.2979665173250911e-06, + "loss": 0.6984, + "step": 13698 + }, + { + "epoch": 0.8409711777525399, + "grad_norm": 1.010903187015985, + "learning_rate": 1.2969870438557808e-06, + "loss": 0.7174, + "step": 13699 + }, + { + "epoch": 0.8410325669910065, + "grad_norm": 1.1152008161533726, + "learning_rate": 1.29600791446312e-06, + "loss": 0.748, + "step": 13700 + }, + { + "epoch": 0.841093956229473, + "grad_norm": 1.0466725730617057, + "learning_rate": 1.2950291291858185e-06, + "loss": 0.7555, + "step": 13701 + }, + { + "epoch": 0.8411553454679395, + "grad_norm": 0.606741748623621, + "learning_rate": 1.2940506880625725e-06, + "loss": 0.7011, + "step": 13702 + }, + { + "epoch": 0.841216734706406, + "grad_norm": 0.9715006749795737, + "learning_rate": 1.2930725911320664e-06, + "loss": 0.7256, + "step": 13703 + }, + { + "epoch": 0.8412781239448724, + "grad_norm": 1.133980315332391, + "learning_rate": 1.2920948384329679e-06, + "loss": 0.7491, + "step": 13704 + }, + { + "epoch": 0.841339513183339, + "grad_norm": 1.0271940750551702, + "learning_rate": 1.2911174300039342e-06, + "loss": 0.7117, + "step": 13705 + }, + { + "epoch": 0.8414009024218054, + "grad_norm": 1.117211064238621, + "learning_rate": 1.2901403658836065e-06, + "loss": 0.7311, + "step": 13706 + }, + { + "epoch": 0.841462291660272, + "grad_norm": 1.119879674037831, + "learning_rate": 1.2891636461106137e-06, + "loss": 0.7442, + "step": 13707 + }, + { + "epoch": 0.8415236808987384, + "grad_norm": 1.0342950455834448, + "learning_rate": 1.2881872707235722e-06, + "loss": 0.7705, + "step": 13708 + }, + { + "epoch": 0.841585070137205, + "grad_norm": 1.1852388278838448, + "learning_rate": 1.287211239761078e-06, + "loss": 0.7248, + "step": 13709 + }, + { + "epoch": 0.8416464593756714, + "grad_norm": 0.685843726931394, + "learning_rate": 1.2862355532617255e-06, + "loss": 0.7365, + "step": 13710 + }, + { + "epoch": 0.8417078486141379, + "grad_norm": 1.0880855933139137, + "learning_rate": 1.2852602112640877e-06, + "loss": 0.7668, + "step": 13711 + }, + { + "epoch": 0.8417692378526045, + "grad_norm": 0.9869067055802423, + "learning_rate": 1.2842852138067197e-06, + "loss": 0.7407, + "step": 13712 + }, + { + "epoch": 0.8418306270910709, + "grad_norm": 0.9868089596975991, + "learning_rate": 1.283310560928175e-06, + "loss": 0.6604, + "step": 13713 + }, + { + "epoch": 0.8418920163295375, + "grad_norm": 1.0380579475438785, + "learning_rate": 1.2823362526669825e-06, + "loss": 0.7338, + "step": 13714 + }, + { + "epoch": 0.8419534055680039, + "grad_norm": 1.0864982008686235, + "learning_rate": 1.281362289061664e-06, + "loss": 0.7571, + "step": 13715 + }, + { + "epoch": 0.8420147948064705, + "grad_norm": 0.9895455651059386, + "learning_rate": 1.280388670150725e-06, + "loss": 0.7569, + "step": 13716 + }, + { + "epoch": 0.8420761840449369, + "grad_norm": 0.6294243782756024, + "learning_rate": 1.2794153959726575e-06, + "loss": 0.6839, + "step": 13717 + }, + { + "epoch": 0.8421375732834034, + "grad_norm": 0.9767146687125478, + "learning_rate": 1.27844246656594e-06, + "loss": 0.7184, + "step": 13718 + }, + { + "epoch": 0.8421989625218699, + "grad_norm": 0.9565533818672617, + "learning_rate": 1.2774698819690378e-06, + "loss": 0.7547, + "step": 13719 + }, + { + "epoch": 0.8422603517603364, + "grad_norm": 0.9783671149489745, + "learning_rate": 1.2764976422204013e-06, + "loss": 0.7442, + "step": 13720 + }, + { + "epoch": 0.8423217409988029, + "grad_norm": 1.0400760622996483, + "learning_rate": 1.2755257473584737e-06, + "loss": 0.7685, + "step": 13721 + }, + { + "epoch": 0.8423831302372694, + "grad_norm": 1.017201293191641, + "learning_rate": 1.2745541974216725e-06, + "loss": 0.8158, + "step": 13722 + }, + { + "epoch": 0.842444519475736, + "grad_norm": 1.0799244455031132, + "learning_rate": 1.2735829924484077e-06, + "loss": 0.7336, + "step": 13723 + }, + { + "epoch": 0.8425059087142024, + "grad_norm": 0.9217769062638687, + "learning_rate": 1.2726121324770835e-06, + "loss": 0.7707, + "step": 13724 + }, + { + "epoch": 0.8425672979526689, + "grad_norm": 0.9380228731189865, + "learning_rate": 1.2716416175460778e-06, + "loss": 0.7228, + "step": 13725 + }, + { + "epoch": 0.8426286871911354, + "grad_norm": 0.9273486344284886, + "learning_rate": 1.270671447693762e-06, + "loss": 0.7887, + "step": 13726 + }, + { + "epoch": 0.8426900764296019, + "grad_norm": 1.0448349284497063, + "learning_rate": 1.2697016229584913e-06, + "loss": 0.7029, + "step": 13727 + }, + { + "epoch": 0.8427514656680684, + "grad_norm": 1.144257278041735, + "learning_rate": 1.2687321433786081e-06, + "loss": 0.723, + "step": 13728 + }, + { + "epoch": 0.8428128549065349, + "grad_norm": 1.079835659125282, + "learning_rate": 1.267763008992442e-06, + "loss": 0.7079, + "step": 13729 + }, + { + "epoch": 0.8428742441450013, + "grad_norm": 1.038981307552512, + "learning_rate": 1.2667942198383053e-06, + "loss": 0.7271, + "step": 13730 + }, + { + "epoch": 0.8429356333834679, + "grad_norm": 1.1051982915786371, + "learning_rate": 1.2658257759545056e-06, + "loss": 0.7788, + "step": 13731 + }, + { + "epoch": 0.8429970226219343, + "grad_norm": 1.053360338320554, + "learning_rate": 1.2648576773793243e-06, + "loss": 0.7032, + "step": 13732 + }, + { + "epoch": 0.8430584118604009, + "grad_norm": 1.010086446601731, + "learning_rate": 1.2638899241510382e-06, + "loss": 0.736, + "step": 13733 + }, + { + "epoch": 0.8431198010988674, + "grad_norm": 1.0228738224247684, + "learning_rate": 1.2629225163079051e-06, + "loss": 0.7283, + "step": 13734 + }, + { + "epoch": 0.8431811903373339, + "grad_norm": 1.0976539719803802, + "learning_rate": 1.2619554538881761e-06, + "loss": 0.7236, + "step": 13735 + }, + { + "epoch": 0.8432425795758004, + "grad_norm": 1.0063012564948886, + "learning_rate": 1.2609887369300844e-06, + "loss": 0.7266, + "step": 13736 + }, + { + "epoch": 0.8433039688142668, + "grad_norm": 1.0025433067892435, + "learning_rate": 1.2600223654718434e-06, + "loss": 0.7109, + "step": 13737 + }, + { + "epoch": 0.8433653580527334, + "grad_norm": 0.5855890099199551, + "learning_rate": 1.2590563395516652e-06, + "loss": 0.6421, + "step": 13738 + }, + { + "epoch": 0.8434267472911998, + "grad_norm": 1.0382505563632498, + "learning_rate": 1.2580906592077403e-06, + "loss": 0.7602, + "step": 13739 + }, + { + "epoch": 0.8434881365296664, + "grad_norm": 1.1143407094724456, + "learning_rate": 1.2571253244782456e-06, + "loss": 0.7187, + "step": 13740 + }, + { + "epoch": 0.8435495257681328, + "grad_norm": 1.1737684111001916, + "learning_rate": 1.2561603354013474e-06, + "loss": 0.7251, + "step": 13741 + }, + { + "epoch": 0.8436109150065993, + "grad_norm": 0.9188475315337353, + "learning_rate": 1.2551956920151965e-06, + "loss": 0.744, + "step": 13742 + }, + { + "epoch": 0.8436723042450658, + "grad_norm": 0.9869567685436575, + "learning_rate": 1.2542313943579309e-06, + "loss": 0.7393, + "step": 13743 + }, + { + "epoch": 0.8437336934835323, + "grad_norm": 0.9276552426437348, + "learning_rate": 1.2532674424676727e-06, + "loss": 0.7033, + "step": 13744 + }, + { + "epoch": 0.8437950827219989, + "grad_norm": 1.068655933980098, + "learning_rate": 1.2523038363825324e-06, + "loss": 0.7065, + "step": 13745 + }, + { + "epoch": 0.8438564719604653, + "grad_norm": 1.1311239010317578, + "learning_rate": 1.2513405761406107e-06, + "loss": 0.7267, + "step": 13746 + }, + { + "epoch": 0.8439178611989319, + "grad_norm": 1.0908347018219862, + "learning_rate": 1.2503776617799857e-06, + "loss": 0.7035, + "step": 13747 + }, + { + "epoch": 0.8439792504373983, + "grad_norm": 1.0928905105571556, + "learning_rate": 1.2494150933387262e-06, + "loss": 0.7432, + "step": 13748 + }, + { + "epoch": 0.8440406396758648, + "grad_norm": 1.0268610058922338, + "learning_rate": 1.2484528708548904e-06, + "loss": 0.6813, + "step": 13749 + }, + { + "epoch": 0.8441020289143313, + "grad_norm": 0.9158595441151671, + "learning_rate": 1.2474909943665203e-06, + "loss": 0.6943, + "step": 13750 + }, + { + "epoch": 0.8441634181527978, + "grad_norm": 0.9922793751039733, + "learning_rate": 1.2465294639116422e-06, + "loss": 0.711, + "step": 13751 + }, + { + "epoch": 0.8442248073912643, + "grad_norm": 1.1103724144341842, + "learning_rate": 1.245568279528272e-06, + "loss": 0.7417, + "step": 13752 + }, + { + "epoch": 0.8442861966297308, + "grad_norm": 1.0063719461494613, + "learning_rate": 1.2446074412544084e-06, + "loss": 0.722, + "step": 13753 + }, + { + "epoch": 0.8443475858681974, + "grad_norm": 1.070719984370803, + "learning_rate": 1.243646949128041e-06, + "loss": 0.8001, + "step": 13754 + }, + { + "epoch": 0.8444089751066638, + "grad_norm": 0.9020868543414254, + "learning_rate": 1.242686803187142e-06, + "loss": 0.6907, + "step": 13755 + }, + { + "epoch": 0.8444703643451303, + "grad_norm": 1.1085273392942843, + "learning_rate": 1.2417270034696704e-06, + "loss": 0.7486, + "step": 13756 + }, + { + "epoch": 0.8445317535835968, + "grad_norm": 1.0987361322264944, + "learning_rate": 1.240767550013573e-06, + "loss": 0.7147, + "step": 13757 + }, + { + "epoch": 0.8445931428220633, + "grad_norm": 1.0721750301384778, + "learning_rate": 1.2398084428567824e-06, + "loss": 0.7286, + "step": 13758 + }, + { + "epoch": 0.8446545320605298, + "grad_norm": 0.8711018576601716, + "learning_rate": 1.2388496820372143e-06, + "loss": 0.7009, + "step": 13759 + }, + { + "epoch": 0.8447159212989963, + "grad_norm": 0.981173355900124, + "learning_rate": 1.2378912675927801e-06, + "loss": 0.7263, + "step": 13760 + }, + { + "epoch": 0.8447773105374627, + "grad_norm": 1.0400155016840997, + "learning_rate": 1.2369331995613664e-06, + "loss": 0.7346, + "step": 13761 + }, + { + "epoch": 0.8448386997759293, + "grad_norm": 0.9956554355402774, + "learning_rate": 1.2359754779808487e-06, + "loss": 0.6766, + "step": 13762 + }, + { + "epoch": 0.8449000890143957, + "grad_norm": 0.9508468614047185, + "learning_rate": 1.2350181028890952e-06, + "loss": 0.7374, + "step": 13763 + }, + { + "epoch": 0.8449614782528623, + "grad_norm": 0.9980036648718272, + "learning_rate": 1.2340610743239545e-06, + "loss": 0.7568, + "step": 13764 + }, + { + "epoch": 0.8450228674913288, + "grad_norm": 0.9153939917085151, + "learning_rate": 1.2331043923232633e-06, + "loss": 0.7281, + "step": 13765 + }, + { + "epoch": 0.8450842567297953, + "grad_norm": 1.0909291817398756, + "learning_rate": 1.2321480569248444e-06, + "loss": 0.745, + "step": 13766 + }, + { + "epoch": 0.8451456459682618, + "grad_norm": 0.9628413133175544, + "learning_rate": 1.2311920681665068e-06, + "loss": 0.7196, + "step": 13767 + }, + { + "epoch": 0.8452070352067282, + "grad_norm": 1.0907127135187666, + "learning_rate": 1.2302364260860455e-06, + "loss": 0.7192, + "step": 13768 + }, + { + "epoch": 0.8452684244451948, + "grad_norm": 1.0073056691533706, + "learning_rate": 1.2292811307212415e-06, + "loss": 0.7509, + "step": 13769 + }, + { + "epoch": 0.8453298136836612, + "grad_norm": 1.0325329105694638, + "learning_rate": 1.2283261821098647e-06, + "loss": 0.7088, + "step": 13770 + }, + { + "epoch": 0.8453912029221278, + "grad_norm": 1.1601944999402731, + "learning_rate": 1.2273715802896668e-06, + "loss": 0.7732, + "step": 13771 + }, + { + "epoch": 0.8454525921605942, + "grad_norm": 1.162235229456926, + "learning_rate": 1.22641732529839e-06, + "loss": 0.8017, + "step": 13772 + }, + { + "epoch": 0.8455139813990608, + "grad_norm": 1.0069277597272, + "learning_rate": 1.22546341717376e-06, + "loss": 0.7452, + "step": 13773 + }, + { + "epoch": 0.8455753706375272, + "grad_norm": 1.2296516781154885, + "learning_rate": 1.2245098559534918e-06, + "loss": 0.7117, + "step": 13774 + }, + { + "epoch": 0.8456367598759937, + "grad_norm": 1.0911596233493075, + "learning_rate": 1.2235566416752853e-06, + "loss": 0.7466, + "step": 13775 + }, + { + "epoch": 0.8456981491144603, + "grad_norm": 1.0485557264113612, + "learning_rate": 1.2226037743768205e-06, + "loss": 0.7708, + "step": 13776 + }, + { + "epoch": 0.8457595383529267, + "grad_norm": 0.9868084350885216, + "learning_rate": 1.2216512540957758e-06, + "loss": 0.7437, + "step": 13777 + }, + { + "epoch": 0.8458209275913933, + "grad_norm": 0.8683962827152332, + "learning_rate": 1.2206990808698061e-06, + "loss": 0.7218, + "step": 13778 + }, + { + "epoch": 0.8458823168298597, + "grad_norm": 0.978923243619547, + "learning_rate": 1.2197472547365574e-06, + "loss": 0.6925, + "step": 13779 + }, + { + "epoch": 0.8459437060683263, + "grad_norm": 0.8973938719306613, + "learning_rate": 1.21879577573366e-06, + "loss": 0.6919, + "step": 13780 + }, + { + "epoch": 0.8460050953067927, + "grad_norm": 1.020984875031296, + "learning_rate": 1.2178446438987302e-06, + "loss": 0.7109, + "step": 13781 + }, + { + "epoch": 0.8460664845452592, + "grad_norm": 1.1052007699694493, + "learning_rate": 1.2168938592693724e-06, + "loss": 0.7255, + "step": 13782 + }, + { + "epoch": 0.8461278737837257, + "grad_norm": 0.8991792552115451, + "learning_rate": 1.2159434218831756e-06, + "loss": 0.7015, + "step": 13783 + }, + { + "epoch": 0.8461892630221922, + "grad_norm": 1.0407923258857834, + "learning_rate": 1.214993331777714e-06, + "loss": 0.6858, + "step": 13784 + }, + { + "epoch": 0.8462506522606587, + "grad_norm": 1.0007345822652727, + "learning_rate": 1.2140435889905545e-06, + "loss": 0.7146, + "step": 13785 + }, + { + "epoch": 0.8463120414991252, + "grad_norm": 1.1819377958712118, + "learning_rate": 1.213094193559241e-06, + "loss": 0.6971, + "step": 13786 + }, + { + "epoch": 0.8463734307375917, + "grad_norm": 1.1085897456681157, + "learning_rate": 1.2121451455213085e-06, + "loss": 0.7277, + "step": 13787 + }, + { + "epoch": 0.8464348199760582, + "grad_norm": 1.1103239759441714, + "learning_rate": 1.21119644491428e-06, + "loss": 0.7349, + "step": 13788 + }, + { + "epoch": 0.8464962092145247, + "grad_norm": 1.0980292410052244, + "learning_rate": 1.2102480917756632e-06, + "loss": 0.7458, + "step": 13789 + }, + { + "epoch": 0.8465575984529912, + "grad_norm": 1.0970751498919666, + "learning_rate": 1.2093000861429494e-06, + "loss": 0.7189, + "step": 13790 + }, + { + "epoch": 0.8466189876914577, + "grad_norm": 1.0318684209990951, + "learning_rate": 1.2083524280536186e-06, + "loss": 0.6889, + "step": 13791 + }, + { + "epoch": 0.8466803769299241, + "grad_norm": 0.9678535425132458, + "learning_rate": 1.2074051175451384e-06, + "loss": 0.707, + "step": 13792 + }, + { + "epoch": 0.8467417661683907, + "grad_norm": 0.9514980256385267, + "learning_rate": 1.2064581546549592e-06, + "loss": 0.7442, + "step": 13793 + }, + { + "epoch": 0.8468031554068571, + "grad_norm": 0.9766606209850291, + "learning_rate": 1.2055115394205186e-06, + "loss": 0.685, + "step": 13794 + }, + { + "epoch": 0.8468645446453237, + "grad_norm": 1.0044270784553235, + "learning_rate": 1.2045652718792477e-06, + "loss": 0.7371, + "step": 13795 + }, + { + "epoch": 0.8469259338837901, + "grad_norm": 1.2013043878736525, + "learning_rate": 1.2036193520685503e-06, + "loss": 0.7687, + "step": 13796 + }, + { + "epoch": 0.8469873231222567, + "grad_norm": 0.9735223921556151, + "learning_rate": 1.202673780025826e-06, + "loss": 0.7029, + "step": 13797 + }, + { + "epoch": 0.8470487123607232, + "grad_norm": 1.0239044727284492, + "learning_rate": 1.2017285557884572e-06, + "loss": 0.7577, + "step": 13798 + }, + { + "epoch": 0.8471101015991896, + "grad_norm": 1.0342440023874246, + "learning_rate": 1.2007836793938165e-06, + "loss": 0.7362, + "step": 13799 + }, + { + "epoch": 0.8471714908376562, + "grad_norm": 1.1642660086405976, + "learning_rate": 1.1998391508792607e-06, + "loss": 0.7606, + "step": 13800 + }, + { + "epoch": 0.8472328800761226, + "grad_norm": 1.091788058138577, + "learning_rate": 1.1988949702821251e-06, + "loss": 0.7821, + "step": 13801 + }, + { + "epoch": 0.8472942693145892, + "grad_norm": 0.9852112463750731, + "learning_rate": 1.1979511376397457e-06, + "loss": 0.7716, + "step": 13802 + }, + { + "epoch": 0.8473556585530556, + "grad_norm": 1.0694159758872792, + "learning_rate": 1.1970076529894348e-06, + "loss": 0.7615, + "step": 13803 + }, + { + "epoch": 0.8474170477915222, + "grad_norm": 0.974493649159562, + "learning_rate": 1.1960645163684925e-06, + "loss": 0.7296, + "step": 13804 + }, + { + "epoch": 0.8474784370299886, + "grad_norm": 1.1221058262638335, + "learning_rate": 1.195121727814207e-06, + "loss": 0.7265, + "step": 13805 + }, + { + "epoch": 0.8475398262684551, + "grad_norm": 1.0091183557082468, + "learning_rate": 1.1941792873638513e-06, + "loss": 0.7269, + "step": 13806 + }, + { + "epoch": 0.8476012155069217, + "grad_norm": 0.966469761968287, + "learning_rate": 1.193237195054685e-06, + "loss": 0.7005, + "step": 13807 + }, + { + "epoch": 0.8476626047453881, + "grad_norm": 0.9830936986072619, + "learning_rate": 1.1922954509239548e-06, + "loss": 0.7657, + "step": 13808 + }, + { + "epoch": 0.8477239939838547, + "grad_norm": 0.9037225922736735, + "learning_rate": 1.1913540550088899e-06, + "loss": 0.6999, + "step": 13809 + }, + { + "epoch": 0.8477853832223211, + "grad_norm": 1.0977246549277535, + "learning_rate": 1.1904130073467157e-06, + "loss": 0.7762, + "step": 13810 + }, + { + "epoch": 0.8478467724607877, + "grad_norm": 1.0865463799587063, + "learning_rate": 1.1894723079746296e-06, + "loss": 0.7186, + "step": 13811 + }, + { + "epoch": 0.8479081616992541, + "grad_norm": 1.0354762923683551, + "learning_rate": 1.1885319569298237e-06, + "loss": 0.7445, + "step": 13812 + }, + { + "epoch": 0.8479695509377206, + "grad_norm": 0.9283694097753865, + "learning_rate": 1.1875919542494784e-06, + "loss": 0.7466, + "step": 13813 + }, + { + "epoch": 0.8480309401761871, + "grad_norm": 0.903839353147365, + "learning_rate": 1.1866522999707553e-06, + "loss": 0.7351, + "step": 13814 + }, + { + "epoch": 0.8480923294146536, + "grad_norm": 0.9686829707692681, + "learning_rate": 1.1857129941308031e-06, + "loss": 0.6991, + "step": 13815 + }, + { + "epoch": 0.8481537186531201, + "grad_norm": 0.8465439298746811, + "learning_rate": 1.1847740367667593e-06, + "loss": 0.7029, + "step": 13816 + }, + { + "epoch": 0.8482151078915866, + "grad_norm": 1.0472002856726492, + "learning_rate": 1.183835427915745e-06, + "loss": 0.749, + "step": 13817 + }, + { + "epoch": 0.8482764971300532, + "grad_norm": 0.968816521278679, + "learning_rate": 1.1828971676148681e-06, + "loss": 0.6667, + "step": 13818 + }, + { + "epoch": 0.8483378863685196, + "grad_norm": 1.0510781428705585, + "learning_rate": 1.1819592559012206e-06, + "loss": 0.7494, + "step": 13819 + }, + { + "epoch": 0.8483992756069861, + "grad_norm": 1.1052012351060154, + "learning_rate": 1.1810216928118912e-06, + "loss": 0.7572, + "step": 13820 + }, + { + "epoch": 0.8484606648454526, + "grad_norm": 1.026031179566851, + "learning_rate": 1.1800844783839382e-06, + "loss": 0.6894, + "step": 13821 + }, + { + "epoch": 0.8485220540839191, + "grad_norm": 0.9883446776013461, + "learning_rate": 1.1791476126544187e-06, + "loss": 0.7581, + "step": 13822 + }, + { + "epoch": 0.8485834433223856, + "grad_norm": 1.0175906912662922, + "learning_rate": 1.1782110956603699e-06, + "loss": 0.7186, + "step": 13823 + }, + { + "epoch": 0.8486448325608521, + "grad_norm": 1.0759178855724127, + "learning_rate": 1.1772749274388219e-06, + "loss": 0.7026, + "step": 13824 + }, + { + "epoch": 0.8487062217993185, + "grad_norm": 1.088077790143703, + "learning_rate": 1.1763391080267815e-06, + "loss": 0.7527, + "step": 13825 + }, + { + "epoch": 0.8487676110377851, + "grad_norm": 0.9616924843462853, + "learning_rate": 1.1754036374612465e-06, + "loss": 0.7395, + "step": 13826 + }, + { + "epoch": 0.8488290002762515, + "grad_norm": 1.0404744804621484, + "learning_rate": 1.1744685157792046e-06, + "loss": 0.7473, + "step": 13827 + }, + { + "epoch": 0.8488903895147181, + "grad_norm": 0.8974392524719386, + "learning_rate": 1.1735337430176252e-06, + "loss": 0.7492, + "step": 13828 + }, + { + "epoch": 0.8489517787531846, + "grad_norm": 1.0342053459972573, + "learning_rate": 1.1725993192134633e-06, + "loss": 0.7692, + "step": 13829 + }, + { + "epoch": 0.849013167991651, + "grad_norm": 1.1083274150907538, + "learning_rate": 1.1716652444036636e-06, + "loss": 0.755, + "step": 13830 + }, + { + "epoch": 0.8490745572301176, + "grad_norm": 1.160983844625953, + "learning_rate": 1.1707315186251534e-06, + "loss": 0.7583, + "step": 13831 + }, + { + "epoch": 0.849135946468584, + "grad_norm": 0.921154492217504, + "learning_rate": 1.1697981419148485e-06, + "loss": 0.722, + "step": 13832 + }, + { + "epoch": 0.8491973357070506, + "grad_norm": 1.079731419373012, + "learning_rate": 1.1688651143096486e-06, + "loss": 0.7435, + "step": 13833 + }, + { + "epoch": 0.849258724945517, + "grad_norm": 1.0474985669404542, + "learning_rate": 1.1679324358464473e-06, + "loss": 0.7303, + "step": 13834 + }, + { + "epoch": 0.8493201141839836, + "grad_norm": 0.946024821303254, + "learning_rate": 1.1670001065621105e-06, + "loss": 0.7642, + "step": 13835 + }, + { + "epoch": 0.84938150342245, + "grad_norm": 0.9588855495638925, + "learning_rate": 1.1660681264935036e-06, + "loss": 0.7326, + "step": 13836 + }, + { + "epoch": 0.8494428926609165, + "grad_norm": 1.1548518904941125, + "learning_rate": 1.165136495677468e-06, + "loss": 0.7549, + "step": 13837 + }, + { + "epoch": 0.849504281899383, + "grad_norm": 1.0452451781758703, + "learning_rate": 1.1642052141508408e-06, + "loss": 0.7154, + "step": 13838 + }, + { + "epoch": 0.8495656711378495, + "grad_norm": 0.9811477995186928, + "learning_rate": 1.1632742819504406e-06, + "loss": 0.7178, + "step": 13839 + }, + { + "epoch": 0.8496270603763161, + "grad_norm": 0.9338336524863855, + "learning_rate": 1.1623436991130654e-06, + "loss": 0.7115, + "step": 13840 + }, + { + "epoch": 0.8496884496147825, + "grad_norm": 1.0615910170021603, + "learning_rate": 1.161413465675514e-06, + "loss": 0.7421, + "step": 13841 + }, + { + "epoch": 0.8497498388532491, + "grad_norm": 0.9314144099971728, + "learning_rate": 1.1604835816745607e-06, + "loss": 0.7613, + "step": 13842 + }, + { + "epoch": 0.8498112280917155, + "grad_norm": 1.1083571905546212, + "learning_rate": 1.159554047146968e-06, + "loss": 0.753, + "step": 13843 + }, + { + "epoch": 0.849872617330182, + "grad_norm": 1.0485794521720415, + "learning_rate": 1.1586248621294849e-06, + "loss": 0.7301, + "step": 13844 + }, + { + "epoch": 0.8499340065686485, + "grad_norm": 1.0392114319370216, + "learning_rate": 1.1576960266588488e-06, + "loss": 0.742, + "step": 13845 + }, + { + "epoch": 0.849995395807115, + "grad_norm": 0.9758266476509538, + "learning_rate": 1.1567675407717816e-06, + "loss": 0.7414, + "step": 13846 + }, + { + "epoch": 0.8500567850455815, + "grad_norm": 0.9137220912246052, + "learning_rate": 1.1558394045049892e-06, + "loss": 0.7195, + "step": 13847 + }, + { + "epoch": 0.850118174284048, + "grad_norm": 1.0587044923286861, + "learning_rate": 1.1549116178951659e-06, + "loss": 0.7911, + "step": 13848 + }, + { + "epoch": 0.8501795635225146, + "grad_norm": 0.9916797633477672, + "learning_rate": 1.1539841809789965e-06, + "loss": 0.7378, + "step": 13849 + }, + { + "epoch": 0.850240952760981, + "grad_norm": 1.022316586255117, + "learning_rate": 1.153057093793143e-06, + "loss": 0.7239, + "step": 13850 + }, + { + "epoch": 0.8503023419994475, + "grad_norm": 0.9628658292848975, + "learning_rate": 1.152130356374256e-06, + "loss": 0.7367, + "step": 13851 + }, + { + "epoch": 0.850363731237914, + "grad_norm": 1.0273980248551278, + "learning_rate": 1.1512039687589804e-06, + "loss": 0.7005, + "step": 13852 + }, + { + "epoch": 0.8504251204763805, + "grad_norm": 0.97189044161548, + "learning_rate": 1.1502779309839395e-06, + "loss": 0.7015, + "step": 13853 + }, + { + "epoch": 0.850486509714847, + "grad_norm": 1.0525502772711919, + "learning_rate": 1.1493522430857429e-06, + "loss": 0.6785, + "step": 13854 + }, + { + "epoch": 0.8505478989533135, + "grad_norm": 1.072475697532318, + "learning_rate": 1.148426905100989e-06, + "loss": 0.737, + "step": 13855 + }, + { + "epoch": 0.8506092881917799, + "grad_norm": 0.9918320278146813, + "learning_rate": 1.1475019170662605e-06, + "loss": 0.7288, + "step": 13856 + }, + { + "epoch": 0.8506706774302465, + "grad_norm": 0.9625239859033999, + "learning_rate": 1.1465772790181284e-06, + "loss": 0.7499, + "step": 13857 + }, + { + "epoch": 0.8507320666687129, + "grad_norm": 1.0165139057663737, + "learning_rate": 1.1456529909931447e-06, + "loss": 0.782, + "step": 13858 + }, + { + "epoch": 0.8507934559071795, + "grad_norm": 1.0481966974317778, + "learning_rate": 1.1447290530278598e-06, + "loss": 0.7256, + "step": 13859 + }, + { + "epoch": 0.850854845145646, + "grad_norm": 1.0403244436281216, + "learning_rate": 1.143805465158795e-06, + "loss": 0.7127, + "step": 13860 + }, + { + "epoch": 0.8509162343841125, + "grad_norm": 0.9645334329931258, + "learning_rate": 1.142882227422466e-06, + "loss": 0.7397, + "step": 13861 + }, + { + "epoch": 0.850977623622579, + "grad_norm": 1.0712792129773003, + "learning_rate": 1.1419593398553707e-06, + "loss": 0.7365, + "step": 13862 + }, + { + "epoch": 0.8510390128610454, + "grad_norm": 1.1054316361908954, + "learning_rate": 1.1410368024940022e-06, + "loss": 0.7443, + "step": 13863 + }, + { + "epoch": 0.851100402099512, + "grad_norm": 0.9146188274429885, + "learning_rate": 1.140114615374831e-06, + "loss": 0.78, + "step": 13864 + }, + { + "epoch": 0.8511617913379784, + "grad_norm": 1.0298251966143586, + "learning_rate": 1.1391927785343114e-06, + "loss": 0.6845, + "step": 13865 + }, + { + "epoch": 0.851223180576445, + "grad_norm": 0.9689614249765913, + "learning_rate": 1.1382712920088945e-06, + "loss": 0.7205, + "step": 13866 + }, + { + "epoch": 0.8512845698149114, + "grad_norm": 1.041352678704761, + "learning_rate": 1.1373501558350098e-06, + "loss": 0.7248, + "step": 13867 + }, + { + "epoch": 0.851345959053378, + "grad_norm": 1.0189242596881165, + "learning_rate": 1.1364293700490736e-06, + "loss": 0.7582, + "step": 13868 + }, + { + "epoch": 0.8514073482918444, + "grad_norm": 1.048201605253515, + "learning_rate": 1.1355089346874902e-06, + "loss": 0.6807, + "step": 13869 + }, + { + "epoch": 0.8514687375303109, + "grad_norm": 1.0476263990942885, + "learning_rate": 1.1345888497866486e-06, + "loss": 0.7525, + "step": 13870 + }, + { + "epoch": 0.8515301267687775, + "grad_norm": 1.131084316426722, + "learning_rate": 1.133669115382926e-06, + "loss": 0.7167, + "step": 13871 + }, + { + "epoch": 0.8515915160072439, + "grad_norm": 1.0574807134408821, + "learning_rate": 1.1327497315126811e-06, + "loss": 0.7453, + "step": 13872 + }, + { + "epoch": 0.8516529052457105, + "grad_norm": 1.052642856250664, + "learning_rate": 1.1318306982122674e-06, + "loss": 0.7801, + "step": 13873 + }, + { + "epoch": 0.8517142944841769, + "grad_norm": 0.5728651173109762, + "learning_rate": 1.1309120155180186e-06, + "loss": 0.5878, + "step": 13874 + }, + { + "epoch": 0.8517756837226435, + "grad_norm": 0.9905106921391806, + "learning_rate": 1.1299936834662506e-06, + "loss": 0.7129, + "step": 13875 + }, + { + "epoch": 0.8518370729611099, + "grad_norm": 0.9581882436400844, + "learning_rate": 1.1290757020932707e-06, + "loss": 0.72, + "step": 13876 + }, + { + "epoch": 0.8518984621995764, + "grad_norm": 1.1875497799853254, + "learning_rate": 1.1281580714353746e-06, + "loss": 0.7469, + "step": 13877 + }, + { + "epoch": 0.8519598514380429, + "grad_norm": 1.103182038535754, + "learning_rate": 1.1272407915288408e-06, + "loss": 0.7067, + "step": 13878 + }, + { + "epoch": 0.8520212406765094, + "grad_norm": 1.0429382354210515, + "learning_rate": 1.1263238624099327e-06, + "loss": 0.7534, + "step": 13879 + }, + { + "epoch": 0.8520826299149759, + "grad_norm": 0.6118134582793183, + "learning_rate": 1.1254072841149021e-06, + "loss": 0.6864, + "step": 13880 + }, + { + "epoch": 0.8521440191534424, + "grad_norm": 1.1608237766642713, + "learning_rate": 1.1244910566799872e-06, + "loss": 0.7235, + "step": 13881 + }, + { + "epoch": 0.852205408391909, + "grad_norm": 0.6000643433214014, + "learning_rate": 1.1235751801414097e-06, + "loss": 0.6594, + "step": 13882 + }, + { + "epoch": 0.8522667976303754, + "grad_norm": 0.9721199251152615, + "learning_rate": 1.1226596545353774e-06, + "loss": 0.7443, + "step": 13883 + }, + { + "epoch": 0.8523281868688419, + "grad_norm": 1.0371724563994835, + "learning_rate": 1.1217444798980926e-06, + "loss": 0.7649, + "step": 13884 + }, + { + "epoch": 0.8523895761073084, + "grad_norm": 1.1094185772347873, + "learning_rate": 1.1208296562657317e-06, + "loss": 0.7043, + "step": 13885 + }, + { + "epoch": 0.8524509653457749, + "grad_norm": 1.0848964748962677, + "learning_rate": 1.1199151836744627e-06, + "loss": 0.7011, + "step": 13886 + }, + { + "epoch": 0.8525123545842413, + "grad_norm": 1.0355720599617078, + "learning_rate": 1.1190010621604387e-06, + "loss": 0.7311, + "step": 13887 + }, + { + "epoch": 0.8525737438227079, + "grad_norm": 0.8393445414911517, + "learning_rate": 1.1180872917598052e-06, + "loss": 0.704, + "step": 13888 + }, + { + "epoch": 0.8526351330611743, + "grad_norm": 1.0017075322322055, + "learning_rate": 1.1171738725086833e-06, + "loss": 0.7656, + "step": 13889 + }, + { + "epoch": 0.8526965222996409, + "grad_norm": 1.0517990246258702, + "learning_rate": 1.1162608044431845e-06, + "loss": 0.694, + "step": 13890 + }, + { + "epoch": 0.8527579115381073, + "grad_norm": 1.1232366769986148, + "learning_rate": 1.1153480875994115e-06, + "loss": 0.7659, + "step": 13891 + }, + { + "epoch": 0.8528193007765739, + "grad_norm": 1.0663629256807152, + "learning_rate": 1.1144357220134482e-06, + "loss": 0.7366, + "step": 13892 + }, + { + "epoch": 0.8528806900150404, + "grad_norm": 1.0049363130475097, + "learning_rate": 1.1135237077213635e-06, + "loss": 0.7257, + "step": 13893 + }, + { + "epoch": 0.8529420792535068, + "grad_norm": 1.0746285376410687, + "learning_rate": 1.1126120447592147e-06, + "loss": 0.7143, + "step": 13894 + }, + { + "epoch": 0.8530034684919734, + "grad_norm": 1.0647201052637354, + "learning_rate": 1.1117007331630446e-06, + "loss": 0.7547, + "step": 13895 + }, + { + "epoch": 0.8530648577304398, + "grad_norm": 0.996911633360219, + "learning_rate": 1.1107897729688833e-06, + "loss": 0.7143, + "step": 13896 + }, + { + "epoch": 0.8531262469689064, + "grad_norm": 1.002925190222727, + "learning_rate": 1.1098791642127427e-06, + "loss": 0.7363, + "step": 13897 + }, + { + "epoch": 0.8531876362073728, + "grad_norm": 1.0533468337462113, + "learning_rate": 1.1089689069306308e-06, + "loss": 0.7425, + "step": 13898 + }, + { + "epoch": 0.8532490254458394, + "grad_norm": 1.0124491853370063, + "learning_rate": 1.108059001158528e-06, + "loss": 0.6845, + "step": 13899 + }, + { + "epoch": 0.8533104146843058, + "grad_norm": 1.0380307768675552, + "learning_rate": 1.1071494469324107e-06, + "loss": 0.7395, + "step": 13900 + }, + { + "epoch": 0.8533718039227723, + "grad_norm": 1.0492654093211866, + "learning_rate": 1.1062402442882358e-06, + "loss": 0.7463, + "step": 13901 + }, + { + "epoch": 0.8534331931612389, + "grad_norm": 1.028688150356557, + "learning_rate": 1.1053313932619535e-06, + "loss": 0.7351, + "step": 13902 + }, + { + "epoch": 0.8534945823997053, + "grad_norm": 0.9413780259448414, + "learning_rate": 1.1044228938894952e-06, + "loss": 0.7224, + "step": 13903 + }, + { + "epoch": 0.8535559716381719, + "grad_norm": 0.999052368755178, + "learning_rate": 1.103514746206772e-06, + "loss": 0.7043, + "step": 13904 + }, + { + "epoch": 0.8536173608766383, + "grad_norm": 0.9762573215547633, + "learning_rate": 1.102606950249696e-06, + "loss": 0.7322, + "step": 13905 + }, + { + "epoch": 0.8536787501151049, + "grad_norm": 0.9154138206935795, + "learning_rate": 1.1016995060541524e-06, + "loss": 0.6979, + "step": 13906 + }, + { + "epoch": 0.8537401393535713, + "grad_norm": 1.0833312882366164, + "learning_rate": 1.10079241365602e-06, + "loss": 0.7141, + "step": 13907 + }, + { + "epoch": 0.8538015285920378, + "grad_norm": 0.9832557718993307, + "learning_rate": 1.0998856730911588e-06, + "loss": 0.7127, + "step": 13908 + }, + { + "epoch": 0.8538629178305043, + "grad_norm": 1.067021903302017, + "learning_rate": 1.0989792843954196e-06, + "loss": 0.7156, + "step": 13909 + }, + { + "epoch": 0.8539243070689708, + "grad_norm": 1.0634703775029895, + "learning_rate": 1.098073247604634e-06, + "loss": 0.7598, + "step": 13910 + }, + { + "epoch": 0.8539856963074373, + "grad_norm": 0.935236608217437, + "learning_rate": 1.0971675627546218e-06, + "loss": 0.7185, + "step": 13911 + }, + { + "epoch": 0.8540470855459038, + "grad_norm": 1.087843872133209, + "learning_rate": 1.0962622298811943e-06, + "loss": 0.7365, + "step": 13912 + }, + { + "epoch": 0.8541084747843704, + "grad_norm": 1.0646565237026528, + "learning_rate": 1.0953572490201426e-06, + "loss": 0.7398, + "step": 13913 + }, + { + "epoch": 0.8541698640228368, + "grad_norm": 1.0706963583778757, + "learning_rate": 1.0944526202072424e-06, + "loss": 0.6784, + "step": 13914 + }, + { + "epoch": 0.8542312532613033, + "grad_norm": 0.9701542157308899, + "learning_rate": 1.093548343478259e-06, + "loss": 0.7062, + "step": 13915 + }, + { + "epoch": 0.8542926424997698, + "grad_norm": 1.1526299914799412, + "learning_rate": 1.0926444188689467e-06, + "loss": 0.7102, + "step": 13916 + }, + { + "epoch": 0.8543540317382363, + "grad_norm": 1.0313943750636152, + "learning_rate": 1.0917408464150392e-06, + "loss": 0.7768, + "step": 13917 + }, + { + "epoch": 0.8544154209767028, + "grad_norm": 1.0872620713574257, + "learning_rate": 1.0908376261522613e-06, + "loss": 0.7762, + "step": 13918 + }, + { + "epoch": 0.8544768102151693, + "grad_norm": 1.0083931324669613, + "learning_rate": 1.0899347581163222e-06, + "loss": 0.694, + "step": 13919 + }, + { + "epoch": 0.8545381994536357, + "grad_norm": 1.152099910676843, + "learning_rate": 1.0890322423429155e-06, + "loss": 0.7396, + "step": 13920 + }, + { + "epoch": 0.8545995886921023, + "grad_norm": 1.1112455635016596, + "learning_rate": 1.0881300788677241e-06, + "loss": 0.7147, + "step": 13921 + }, + { + "epoch": 0.8546609779305687, + "grad_norm": 1.076381906146552, + "learning_rate": 1.0872282677264124e-06, + "loss": 0.7585, + "step": 13922 + }, + { + "epoch": 0.8547223671690353, + "grad_norm": 0.9060877492985975, + "learning_rate": 1.0863268089546408e-06, + "loss": 0.6575, + "step": 13923 + }, + { + "epoch": 0.8547837564075018, + "grad_norm": 1.0791410422755894, + "learning_rate": 1.085425702588041e-06, + "loss": 0.7251, + "step": 13924 + }, + { + "epoch": 0.8548451456459683, + "grad_norm": 1.1779887993545193, + "learning_rate": 1.0845249486622422e-06, + "loss": 0.8207, + "step": 13925 + }, + { + "epoch": 0.8549065348844348, + "grad_norm": 0.9835598233142558, + "learning_rate": 1.0836245472128538e-06, + "loss": 0.7953, + "step": 13926 + }, + { + "epoch": 0.8549679241229012, + "grad_norm": 1.0409334296935278, + "learning_rate": 1.082724498275477e-06, + "loss": 0.72, + "step": 13927 + }, + { + "epoch": 0.8550293133613678, + "grad_norm": 1.118614082878782, + "learning_rate": 1.0818248018856958e-06, + "loss": 0.7926, + "step": 13928 + }, + { + "epoch": 0.8550907025998342, + "grad_norm": 1.1624678655263374, + "learning_rate": 1.080925458079074e-06, + "loss": 0.7725, + "step": 13929 + }, + { + "epoch": 0.8551520918383008, + "grad_norm": 0.994337240751814, + "learning_rate": 1.080026466891173e-06, + "loss": 0.7227, + "step": 13930 + }, + { + "epoch": 0.8552134810767672, + "grad_norm": 1.0683115300363755, + "learning_rate": 1.0791278283575336e-06, + "loss": 0.7688, + "step": 13931 + }, + { + "epoch": 0.8552748703152337, + "grad_norm": 1.131315245801429, + "learning_rate": 1.0782295425136835e-06, + "loss": 0.7449, + "step": 13932 + }, + { + "epoch": 0.8553362595537002, + "grad_norm": 0.9500301964633976, + "learning_rate": 1.0773316093951358e-06, + "loss": 0.7436, + "step": 13933 + }, + { + "epoch": 0.8553976487921667, + "grad_norm": 0.9651824841766915, + "learning_rate": 1.0764340290373921e-06, + "loss": 0.77, + "step": 13934 + }, + { + "epoch": 0.8554590380306333, + "grad_norm": 0.6038050678759996, + "learning_rate": 1.0755368014759371e-06, + "loss": 0.6875, + "step": 13935 + }, + { + "epoch": 0.8555204272690997, + "grad_norm": 1.072586394813946, + "learning_rate": 1.0746399267462416e-06, + "loss": 0.8052, + "step": 13936 + }, + { + "epoch": 0.8555818165075663, + "grad_norm": 1.12232463387015, + "learning_rate": 1.073743404883769e-06, + "loss": 0.7547, + "step": 13937 + }, + { + "epoch": 0.8556432057460327, + "grad_norm": 0.9602734710031305, + "learning_rate": 1.0728472359239616e-06, + "loss": 0.7066, + "step": 13938 + }, + { + "epoch": 0.8557045949844992, + "grad_norm": 1.0036562203192771, + "learning_rate": 1.0719514199022473e-06, + "loss": 0.7725, + "step": 13939 + }, + { + "epoch": 0.8557659842229657, + "grad_norm": 1.0700251717291462, + "learning_rate": 1.0710559568540425e-06, + "loss": 0.6846, + "step": 13940 + }, + { + "epoch": 0.8558273734614322, + "grad_norm": 0.6245490894711454, + "learning_rate": 1.0701608468147517e-06, + "loss": 0.6369, + "step": 13941 + }, + { + "epoch": 0.8558887626998987, + "grad_norm": 1.010119795695953, + "learning_rate": 1.0692660898197638e-06, + "loss": 0.7541, + "step": 13942 + }, + { + "epoch": 0.8559501519383652, + "grad_norm": 1.0412728430994602, + "learning_rate": 1.0683716859044513e-06, + "loss": 0.729, + "step": 13943 + }, + { + "epoch": 0.8560115411768316, + "grad_norm": 1.0959463895090629, + "learning_rate": 1.067477635104177e-06, + "loss": 0.7589, + "step": 13944 + }, + { + "epoch": 0.8560729304152982, + "grad_norm": 1.1043540255363133, + "learning_rate": 1.0665839374542853e-06, + "loss": 0.7225, + "step": 13945 + }, + { + "epoch": 0.8561343196537647, + "grad_norm": 1.0138607361261738, + "learning_rate": 1.0656905929901108e-06, + "loss": 0.7453, + "step": 13946 + }, + { + "epoch": 0.8561957088922312, + "grad_norm": 1.0133736998489187, + "learning_rate": 1.0647976017469685e-06, + "loss": 0.7725, + "step": 13947 + }, + { + "epoch": 0.8562570981306977, + "grad_norm": 1.0057601659272022, + "learning_rate": 1.0639049637601695e-06, + "loss": 0.677, + "step": 13948 + }, + { + "epoch": 0.8563184873691642, + "grad_norm": 1.0092354470338287, + "learning_rate": 1.0630126790649998e-06, + "loss": 0.8185, + "step": 13949 + }, + { + "epoch": 0.8563798766076307, + "grad_norm": 1.0338445582641846, + "learning_rate": 1.0621207476967343e-06, + "loss": 0.7162, + "step": 13950 + }, + { + "epoch": 0.8564412658460971, + "grad_norm": 0.9397971992294987, + "learning_rate": 1.0612291696906407e-06, + "loss": 0.7644, + "step": 13951 + }, + { + "epoch": 0.8565026550845637, + "grad_norm": 1.0566300915329199, + "learning_rate": 1.0603379450819684e-06, + "loss": 0.7612, + "step": 13952 + }, + { + "epoch": 0.8565640443230301, + "grad_norm": 0.9519195671102216, + "learning_rate": 1.059447073905948e-06, + "loss": 0.7987, + "step": 13953 + }, + { + "epoch": 0.8566254335614967, + "grad_norm": 1.035069640592164, + "learning_rate": 1.0585565561978007e-06, + "loss": 0.7478, + "step": 13954 + }, + { + "epoch": 0.8566868227999632, + "grad_norm": 1.1794379922046196, + "learning_rate": 1.0576663919927366e-06, + "loss": 0.7424, + "step": 13955 + }, + { + "epoch": 0.8567482120384297, + "grad_norm": 0.9854376143024125, + "learning_rate": 1.0567765813259455e-06, + "loss": 0.7316, + "step": 13956 + }, + { + "epoch": 0.8568096012768962, + "grad_norm": 1.1291497440690195, + "learning_rate": 1.0558871242326097e-06, + "loss": 0.7112, + "step": 13957 + }, + { + "epoch": 0.8568709905153626, + "grad_norm": 0.9988892828385099, + "learning_rate": 1.0549980207478916e-06, + "loss": 0.7391, + "step": 13958 + }, + { + "epoch": 0.8569323797538292, + "grad_norm": 1.0377341544013103, + "learning_rate": 1.0541092709069433e-06, + "loss": 0.6931, + "step": 13959 + }, + { + "epoch": 0.8569937689922956, + "grad_norm": 1.1195494101549823, + "learning_rate": 1.0532208747449014e-06, + "loss": 0.714, + "step": 13960 + }, + { + "epoch": 0.8570551582307622, + "grad_norm": 0.961015884541432, + "learning_rate": 1.0523328322968863e-06, + "loss": 0.6971, + "step": 13961 + }, + { + "epoch": 0.8571165474692286, + "grad_norm": 1.0490028788017594, + "learning_rate": 1.0514451435980143e-06, + "loss": 0.7203, + "step": 13962 + }, + { + "epoch": 0.8571779367076952, + "grad_norm": 1.0287134325696061, + "learning_rate": 1.0505578086833745e-06, + "loss": 0.7583, + "step": 13963 + }, + { + "epoch": 0.8572393259461616, + "grad_norm": 0.905018333667196, + "learning_rate": 1.0496708275880497e-06, + "loss": 0.7413, + "step": 13964 + }, + { + "epoch": 0.8573007151846281, + "grad_norm": 0.9957728055182715, + "learning_rate": 1.0487842003471038e-06, + "loss": 0.7402, + "step": 13965 + }, + { + "epoch": 0.8573621044230947, + "grad_norm": 1.0327031089384062, + "learning_rate": 1.0478979269955958e-06, + "loss": 0.699, + "step": 13966 + }, + { + "epoch": 0.8574234936615611, + "grad_norm": 1.1734377154566205, + "learning_rate": 1.047012007568563e-06, + "loss": 0.7474, + "step": 13967 + }, + { + "epoch": 0.8574848829000277, + "grad_norm": 1.0541343370778267, + "learning_rate": 1.0461264421010265e-06, + "loss": 0.7415, + "step": 13968 + }, + { + "epoch": 0.8575462721384941, + "grad_norm": 1.0737533353941042, + "learning_rate": 1.0452412306280023e-06, + "loss": 0.7762, + "step": 13969 + }, + { + "epoch": 0.8576076613769607, + "grad_norm": 1.031535336688933, + "learning_rate": 1.0443563731844852e-06, + "loss": 0.7362, + "step": 13970 + }, + { + "epoch": 0.8576690506154271, + "grad_norm": 1.0049615608184022, + "learning_rate": 1.043471869805459e-06, + "loss": 0.7152, + "step": 13971 + }, + { + "epoch": 0.8577304398538936, + "grad_norm": 0.8694058126045593, + "learning_rate": 1.0425877205258928e-06, + "loss": 0.7513, + "step": 13972 + }, + { + "epoch": 0.8577918290923601, + "grad_norm": 1.0848599023993053, + "learning_rate": 1.0417039253807416e-06, + "loss": 0.7067, + "step": 13973 + }, + { + "epoch": 0.8578532183308266, + "grad_norm": 1.0322052549561662, + "learning_rate": 1.0408204844049464e-06, + "loss": 0.6992, + "step": 13974 + }, + { + "epoch": 0.857914607569293, + "grad_norm": 0.665347517277208, + "learning_rate": 1.0399373976334326e-06, + "loss": 0.6554, + "step": 13975 + }, + { + "epoch": 0.8579759968077596, + "grad_norm": 1.0797943317693275, + "learning_rate": 1.0390546651011168e-06, + "loss": 0.7218, + "step": 13976 + }, + { + "epoch": 0.8580373860462261, + "grad_norm": 1.1169664882732273, + "learning_rate": 1.038172286842899e-06, + "loss": 0.7375, + "step": 13977 + }, + { + "epoch": 0.8580987752846926, + "grad_norm": 1.0449554313576614, + "learning_rate": 1.0372902628936598e-06, + "loss": 0.7041, + "step": 13978 + }, + { + "epoch": 0.8581601645231591, + "grad_norm": 1.0047470922203168, + "learning_rate": 1.0364085932882706e-06, + "loss": 0.8097, + "step": 13979 + }, + { + "epoch": 0.8582215537616256, + "grad_norm": 1.1361308643963823, + "learning_rate": 1.0355272780615921e-06, + "loss": 0.7608, + "step": 13980 + }, + { + "epoch": 0.8582829430000921, + "grad_norm": 1.0550519851761773, + "learning_rate": 1.0346463172484667e-06, + "loss": 0.7355, + "step": 13981 + }, + { + "epoch": 0.8583443322385585, + "grad_norm": 1.0803459677422218, + "learning_rate": 1.0337657108837208e-06, + "loss": 0.7399, + "step": 13982 + }, + { + "epoch": 0.8584057214770251, + "grad_norm": 1.125609285406093, + "learning_rate": 1.032885459002172e-06, + "loss": 0.7484, + "step": 13983 + }, + { + "epoch": 0.8584671107154915, + "grad_norm": 1.099789778034862, + "learning_rate": 1.0320055616386205e-06, + "loss": 0.7295, + "step": 13984 + }, + { + "epoch": 0.8585284999539581, + "grad_norm": 1.0151229075475654, + "learning_rate": 1.0311260188278537e-06, + "loss": 0.7178, + "step": 13985 + }, + { + "epoch": 0.8585898891924245, + "grad_norm": 1.215633999397172, + "learning_rate": 1.0302468306046421e-06, + "loss": 0.7551, + "step": 13986 + }, + { + "epoch": 0.8586512784308911, + "grad_norm": 1.161798733823467, + "learning_rate": 1.0293679970037508e-06, + "loss": 0.7564, + "step": 13987 + }, + { + "epoch": 0.8587126676693576, + "grad_norm": 1.2512633811979266, + "learning_rate": 1.0284895180599185e-06, + "loss": 0.6991, + "step": 13988 + }, + { + "epoch": 0.858774056907824, + "grad_norm": 0.9387554318845404, + "learning_rate": 1.0276113938078768e-06, + "loss": 0.7105, + "step": 13989 + }, + { + "epoch": 0.8588354461462906, + "grad_norm": 1.1145974413968593, + "learning_rate": 1.0267336242823466e-06, + "loss": 0.734, + "step": 13990 + }, + { + "epoch": 0.858896835384757, + "grad_norm": 1.0432867317404955, + "learning_rate": 1.0258562095180291e-06, + "loss": 0.7329, + "step": 13991 + }, + { + "epoch": 0.8589582246232236, + "grad_norm": 1.0049683677393477, + "learning_rate": 1.0249791495496143e-06, + "loss": 0.7295, + "step": 13992 + }, + { + "epoch": 0.85901961386169, + "grad_norm": 1.1234953613690202, + "learning_rate": 1.024102444411771e-06, + "loss": 0.7428, + "step": 13993 + }, + { + "epoch": 0.8590810031001566, + "grad_norm": 0.9300746295091119, + "learning_rate": 1.0232260941391669e-06, + "loss": 0.7591, + "step": 13994 + }, + { + "epoch": 0.859142392338623, + "grad_norm": 1.0037732499200285, + "learning_rate": 1.0223500987664458e-06, + "loss": 0.766, + "step": 13995 + }, + { + "epoch": 0.8592037815770895, + "grad_norm": 0.965647786712698, + "learning_rate": 1.0214744583282422e-06, + "loss": 0.7022, + "step": 13996 + }, + { + "epoch": 0.859265170815556, + "grad_norm": 0.9627296899127077, + "learning_rate": 1.0205991728591735e-06, + "loss": 0.7303, + "step": 13997 + }, + { + "epoch": 0.8593265600540225, + "grad_norm": 1.1088166564713127, + "learning_rate": 1.0197242423938447e-06, + "loss": 0.7669, + "step": 13998 + }, + { + "epoch": 0.8593879492924891, + "grad_norm": 0.9513595974730954, + "learning_rate": 1.0188496669668469e-06, + "loss": 0.735, + "step": 13999 + }, + { + "epoch": 0.8594493385309555, + "grad_norm": 1.2321037715123526, + "learning_rate": 1.0179754466127533e-06, + "loss": 0.7253, + "step": 14000 + }, + { + "epoch": 0.8595107277694221, + "grad_norm": 1.1023635573157373, + "learning_rate": 1.0171015813661322e-06, + "loss": 0.7081, + "step": 14001 + }, + { + "epoch": 0.8595721170078885, + "grad_norm": 1.0357327212169718, + "learning_rate": 1.0162280712615314e-06, + "loss": 0.7375, + "step": 14002 + }, + { + "epoch": 0.859633506246355, + "grad_norm": 1.041158879699981, + "learning_rate": 1.0153549163334809e-06, + "loss": 0.7557, + "step": 14003 + }, + { + "epoch": 0.8596948954848215, + "grad_norm": 1.0795118472246108, + "learning_rate": 1.014482116616503e-06, + "loss": 0.686, + "step": 14004 + }, + { + "epoch": 0.859756284723288, + "grad_norm": 1.1799614231020132, + "learning_rate": 1.0136096721451061e-06, + "loss": 0.7502, + "step": 14005 + }, + { + "epoch": 0.8598176739617545, + "grad_norm": 1.0900493029138871, + "learning_rate": 1.0127375829537822e-06, + "loss": 0.7458, + "step": 14006 + }, + { + "epoch": 0.859879063200221, + "grad_norm": 1.0331857743640664, + "learning_rate": 1.0118658490770083e-06, + "loss": 0.7275, + "step": 14007 + }, + { + "epoch": 0.8599404524386876, + "grad_norm": 1.051162779562178, + "learning_rate": 1.0109944705492492e-06, + "loss": 0.7461, + "step": 14008 + }, + { + "epoch": 0.860001841677154, + "grad_norm": 1.0998801846268014, + "learning_rate": 1.010123447404956e-06, + "loss": 0.7436, + "step": 14009 + }, + { + "epoch": 0.8600632309156205, + "grad_norm": 1.0043633147832474, + "learning_rate": 1.0092527796785633e-06, + "loss": 0.6989, + "step": 14010 + }, + { + "epoch": 0.860124620154087, + "grad_norm": 1.2236719945933028, + "learning_rate": 1.008382467404493e-06, + "loss": 0.7277, + "step": 14011 + }, + { + "epoch": 0.8601860093925535, + "grad_norm": 1.0647924393377448, + "learning_rate": 1.0075125106171579e-06, + "loss": 0.7299, + "step": 14012 + }, + { + "epoch": 0.86024739863102, + "grad_norm": 1.1010805351555173, + "learning_rate": 1.0066429093509456e-06, + "loss": 0.7271, + "step": 14013 + }, + { + "epoch": 0.8603087878694865, + "grad_norm": 0.9605522932099922, + "learning_rate": 1.0057736636402382e-06, + "loss": 0.6976, + "step": 14014 + }, + { + "epoch": 0.8603701771079529, + "grad_norm": 1.2042077819170418, + "learning_rate": 1.004904773519404e-06, + "loss": 0.7046, + "step": 14015 + }, + { + "epoch": 0.8604315663464195, + "grad_norm": 1.0314742989316341, + "learning_rate": 1.0040362390227931e-06, + "loss": 0.7268, + "step": 14016 + }, + { + "epoch": 0.8604929555848859, + "grad_norm": 1.0241268604677272, + "learning_rate": 1.0031680601847448e-06, + "loss": 0.6969, + "step": 14017 + }, + { + "epoch": 0.8605543448233525, + "grad_norm": 1.0087553054557854, + "learning_rate": 1.0023002370395785e-06, + "loss": 0.7555, + "step": 14018 + }, + { + "epoch": 0.860615734061819, + "grad_norm": 1.1373002515611121, + "learning_rate": 1.0014327696216087e-06, + "loss": 0.7442, + "step": 14019 + }, + { + "epoch": 0.8606771233002855, + "grad_norm": 1.0353315992517536, + "learning_rate": 1.000565657965129e-06, + "loss": 0.6935, + "step": 14020 + }, + { + "epoch": 0.860738512538752, + "grad_norm": 1.0358373325950276, + "learning_rate": 9.996989021044224e-07, + "loss": 0.733, + "step": 14021 + }, + { + "epoch": 0.8607999017772184, + "grad_norm": 1.0007786730061998, + "learning_rate": 9.988325020737533e-07, + "loss": 0.7239, + "step": 14022 + }, + { + "epoch": 0.860861291015685, + "grad_norm": 0.9896695758348261, + "learning_rate": 9.979664579073777e-07, + "loss": 0.6913, + "step": 14023 + }, + { + "epoch": 0.8609226802541514, + "grad_norm": 1.0131393720572346, + "learning_rate": 9.971007696395352e-07, + "loss": 0.7403, + "step": 14024 + }, + { + "epoch": 0.860984069492618, + "grad_norm": 1.0846562433293376, + "learning_rate": 9.96235437304447e-07, + "loss": 0.7414, + "step": 14025 + }, + { + "epoch": 0.8610454587310844, + "grad_norm": 1.1347632646657635, + "learning_rate": 9.953704609363325e-07, + "loss": 0.7882, + "step": 14026 + }, + { + "epoch": 0.861106847969551, + "grad_norm": 1.0398491566896266, + "learning_rate": 9.945058405693808e-07, + "loss": 0.7429, + "step": 14027 + }, + { + "epoch": 0.8611682372080174, + "grad_norm": 1.0858042697490327, + "learning_rate": 9.936415762377771e-07, + "loss": 0.718, + "step": 14028 + }, + { + "epoch": 0.8612296264464839, + "grad_norm": 1.1089465648202064, + "learning_rate": 9.927776679756918e-07, + "loss": 0.7117, + "step": 14029 + }, + { + "epoch": 0.8612910156849505, + "grad_norm": 1.1197613475735864, + "learning_rate": 9.919141158172807e-07, + "loss": 0.7276, + "step": 14030 + }, + { + "epoch": 0.8613524049234169, + "grad_norm": 1.1176288876472993, + "learning_rate": 9.910509197966845e-07, + "loss": 0.6944, + "step": 14031 + }, + { + "epoch": 0.8614137941618835, + "grad_norm": 1.0734469407699339, + "learning_rate": 9.901880799480246e-07, + "loss": 0.7827, + "step": 14032 + }, + { + "epoch": 0.8614751834003499, + "grad_norm": 0.9736227279037999, + "learning_rate": 9.893255963054205e-07, + "loss": 0.7236, + "step": 14033 + }, + { + "epoch": 0.8615365726388164, + "grad_norm": 0.9038041230080848, + "learning_rate": 9.884634689029672e-07, + "loss": 0.7077, + "step": 14034 + }, + { + "epoch": 0.8615979618772829, + "grad_norm": 0.9661609194074707, + "learning_rate": 9.876016977747505e-07, + "loss": 0.7446, + "step": 14035 + }, + { + "epoch": 0.8616593511157494, + "grad_norm": 1.1364809636477675, + "learning_rate": 9.8674028295484e-07, + "loss": 0.7465, + "step": 14036 + }, + { + "epoch": 0.8617207403542159, + "grad_norm": 0.9048475755727943, + "learning_rate": 9.85879224477293e-07, + "loss": 0.76, + "step": 14037 + }, + { + "epoch": 0.8617821295926824, + "grad_norm": 1.0773918500098323, + "learning_rate": 9.85018522376151e-07, + "loss": 0.7409, + "step": 14038 + }, + { + "epoch": 0.8618435188311488, + "grad_norm": 0.9695267477569627, + "learning_rate": 9.841581766854402e-07, + "loss": 0.7628, + "step": 14039 + }, + { + "epoch": 0.8619049080696154, + "grad_norm": 1.1452108396191214, + "learning_rate": 9.83298187439179e-07, + "loss": 0.6985, + "step": 14040 + }, + { + "epoch": 0.8619662973080819, + "grad_norm": 1.155048146832382, + "learning_rate": 9.824385546713666e-07, + "loss": 0.7415, + "step": 14041 + }, + { + "epoch": 0.8620276865465484, + "grad_norm": 1.0011701951399685, + "learning_rate": 9.815792784159862e-07, + "loss": 0.7375, + "step": 14042 + }, + { + "epoch": 0.8620890757850149, + "grad_norm": 1.1043650467265467, + "learning_rate": 9.80720358707008e-07, + "loss": 0.7413, + "step": 14043 + }, + { + "epoch": 0.8621504650234814, + "grad_norm": 1.118095947234642, + "learning_rate": 9.798617955783951e-07, + "loss": 0.7591, + "step": 14044 + }, + { + "epoch": 0.8622118542619479, + "grad_norm": 1.0627278887151617, + "learning_rate": 9.79003589064088e-07, + "loss": 0.7913, + "step": 14045 + }, + { + "epoch": 0.8622732435004143, + "grad_norm": 1.0641361887333551, + "learning_rate": 9.781457391980177e-07, + "loss": 0.7647, + "step": 14046 + }, + { + "epoch": 0.8623346327388809, + "grad_norm": 0.9830749218383591, + "learning_rate": 9.772882460140975e-07, + "loss": 0.7068, + "step": 14047 + }, + { + "epoch": 0.8623960219773473, + "grad_norm": 0.9477088864678708, + "learning_rate": 9.76431109546231e-07, + "loss": 0.7261, + "step": 14048 + }, + { + "epoch": 0.8624574112158139, + "grad_norm": 0.9875574102098337, + "learning_rate": 9.755743298283027e-07, + "loss": 0.7329, + "step": 14049 + }, + { + "epoch": 0.8625188004542803, + "grad_norm": 0.9721719796867984, + "learning_rate": 9.74717906894186e-07, + "loss": 0.6596, + "step": 14050 + }, + { + "epoch": 0.8625801896927469, + "grad_norm": 1.0832677256747865, + "learning_rate": 9.738618407777446e-07, + "loss": 0.6674, + "step": 14051 + }, + { + "epoch": 0.8626415789312134, + "grad_norm": 0.9844274139854682, + "learning_rate": 9.73006131512818e-07, + "loss": 0.7086, + "step": 14052 + }, + { + "epoch": 0.8627029681696798, + "grad_norm": 0.8918690466507337, + "learning_rate": 9.721507791332375e-07, + "loss": 0.7364, + "step": 14053 + }, + { + "epoch": 0.8627643574081464, + "grad_norm": 1.2076289729737293, + "learning_rate": 9.712957836728222e-07, + "loss": 0.7435, + "step": 14054 + }, + { + "epoch": 0.8628257466466128, + "grad_norm": 0.938583357142923, + "learning_rate": 9.70441145165374e-07, + "loss": 0.7429, + "step": 14055 + }, + { + "epoch": 0.8628871358850794, + "grad_norm": 1.252029935701302, + "learning_rate": 9.695868636446826e-07, + "loss": 0.7472, + "step": 14056 + }, + { + "epoch": 0.8629485251235458, + "grad_norm": 0.9902132271061325, + "learning_rate": 9.687329391445166e-07, + "loss": 0.6961, + "step": 14057 + }, + { + "epoch": 0.8630099143620124, + "grad_norm": 1.0974386614374867, + "learning_rate": 9.678793716986411e-07, + "loss": 0.7329, + "step": 14058 + }, + { + "epoch": 0.8630713036004788, + "grad_norm": 1.1176647576379162, + "learning_rate": 9.670261613408028e-07, + "loss": 0.7425, + "step": 14059 + }, + { + "epoch": 0.8631326928389453, + "grad_norm": 1.0437960664972692, + "learning_rate": 9.661733081047309e-07, + "loss": 0.7244, + "step": 14060 + }, + { + "epoch": 0.8631940820774119, + "grad_norm": 0.9311904875044622, + "learning_rate": 9.653208120241453e-07, + "loss": 0.7776, + "step": 14061 + }, + { + "epoch": 0.8632554713158783, + "grad_norm": 1.1013492160593792, + "learning_rate": 9.644686731327479e-07, + "loss": 0.7364, + "step": 14062 + }, + { + "epoch": 0.8633168605543449, + "grad_norm": 1.0333613914071784, + "learning_rate": 9.636168914642307e-07, + "loss": 0.7449, + "step": 14063 + }, + { + "epoch": 0.8633782497928113, + "grad_norm": 1.1074862832904906, + "learning_rate": 9.627654670522646e-07, + "loss": 0.6929, + "step": 14064 + }, + { + "epoch": 0.8634396390312779, + "grad_norm": 1.0857537722033541, + "learning_rate": 9.61914399930517e-07, + "loss": 0.7214, + "step": 14065 + }, + { + "epoch": 0.8635010282697443, + "grad_norm": 1.0740865656570426, + "learning_rate": 9.61063690132633e-07, + "loss": 0.7128, + "step": 14066 + }, + { + "epoch": 0.8635624175082108, + "grad_norm": 0.9748166008441691, + "learning_rate": 9.60213337692244e-07, + "loss": 0.712, + "step": 14067 + }, + { + "epoch": 0.8636238067466773, + "grad_norm": 1.0170706137544325, + "learning_rate": 9.593633426429671e-07, + "loss": 0.7409, + "step": 14068 + }, + { + "epoch": 0.8636851959851438, + "grad_norm": 1.009049889862627, + "learning_rate": 9.585137050184124e-07, + "loss": 0.7449, + "step": 14069 + }, + { + "epoch": 0.8637465852236103, + "grad_norm": 1.178751655594636, + "learning_rate": 9.576644248521682e-07, + "loss": 0.6601, + "step": 14070 + }, + { + "epoch": 0.8638079744620768, + "grad_norm": 0.9902639954107747, + "learning_rate": 9.568155021778115e-07, + "loss": 0.7288, + "step": 14071 + }, + { + "epoch": 0.8638693637005433, + "grad_norm": 0.9915194430957651, + "learning_rate": 9.559669370289038e-07, + "loss": 0.7093, + "step": 14072 + }, + { + "epoch": 0.8639307529390098, + "grad_norm": 0.9362916189523979, + "learning_rate": 9.551187294389941e-07, + "loss": 0.6931, + "step": 14073 + }, + { + "epoch": 0.8639921421774763, + "grad_norm": 1.0919832006434251, + "learning_rate": 9.542708794416168e-07, + "loss": 0.7118, + "step": 14074 + }, + { + "epoch": 0.8640535314159428, + "grad_norm": 0.9814075597960175, + "learning_rate": 9.534233870702891e-07, + "loss": 0.7378, + "step": 14075 + }, + { + "epoch": 0.8641149206544093, + "grad_norm": 1.0428681364589707, + "learning_rate": 9.525762523585236e-07, + "loss": 0.7246, + "step": 14076 + }, + { + "epoch": 0.8641763098928757, + "grad_norm": 0.9892427934439538, + "learning_rate": 9.517294753398066e-07, + "loss": 0.7347, + "step": 14077 + }, + { + "epoch": 0.8642376991313423, + "grad_norm": 1.0762851443051809, + "learning_rate": 9.508830560476134e-07, + "loss": 0.7694, + "step": 14078 + }, + { + "epoch": 0.8642990883698087, + "grad_norm": 1.0356559287320024, + "learning_rate": 9.500369945154142e-07, + "loss": 0.6762, + "step": 14079 + }, + { + "epoch": 0.8643604776082753, + "grad_norm": 1.0415464163088473, + "learning_rate": 9.491912907766554e-07, + "loss": 0.7185, + "step": 14080 + }, + { + "epoch": 0.8644218668467417, + "grad_norm": 1.0676677025829358, + "learning_rate": 9.483459448647736e-07, + "loss": 0.735, + "step": 14081 + }, + { + "epoch": 0.8644832560852083, + "grad_norm": 1.087599478794646, + "learning_rate": 9.475009568131844e-07, + "loss": 0.7444, + "step": 14082 + }, + { + "epoch": 0.8645446453236748, + "grad_norm": 1.0083836942016269, + "learning_rate": 9.466563266552997e-07, + "loss": 0.7501, + "step": 14083 + }, + { + "epoch": 0.8646060345621412, + "grad_norm": 1.0733560041254893, + "learning_rate": 9.45812054424512e-07, + "loss": 0.7706, + "step": 14084 + }, + { + "epoch": 0.8646674238006078, + "grad_norm": 1.1513085603721929, + "learning_rate": 9.449681401541987e-07, + "loss": 0.7592, + "step": 14085 + }, + { + "epoch": 0.8647288130390742, + "grad_norm": 1.029512097437498, + "learning_rate": 9.441245838777247e-07, + "loss": 0.7583, + "step": 14086 + }, + { + "epoch": 0.8647902022775408, + "grad_norm": 0.9689750311721494, + "learning_rate": 9.432813856284395e-07, + "loss": 0.7125, + "step": 14087 + }, + { + "epoch": 0.8648515915160072, + "grad_norm": 1.0895284008769313, + "learning_rate": 9.424385454396812e-07, + "loss": 0.7145, + "step": 14088 + }, + { + "epoch": 0.8649129807544738, + "grad_norm": 1.1167370286041063, + "learning_rate": 9.415960633447674e-07, + "loss": 0.6997, + "step": 14089 + }, + { + "epoch": 0.8649743699929402, + "grad_norm": 0.9295400584166107, + "learning_rate": 9.407539393770126e-07, + "loss": 0.6945, + "step": 14090 + }, + { + "epoch": 0.8650357592314067, + "grad_norm": 1.1511440749862751, + "learning_rate": 9.399121735697059e-07, + "loss": 0.7401, + "step": 14091 + }, + { + "epoch": 0.8650971484698732, + "grad_norm": 0.9954940289910654, + "learning_rate": 9.390707659561249e-07, + "loss": 0.7476, + "step": 14092 + }, + { + "epoch": 0.8651585377083397, + "grad_norm": 1.098823939156554, + "learning_rate": 9.382297165695397e-07, + "loss": 0.7352, + "step": 14093 + }, + { + "epoch": 0.8652199269468063, + "grad_norm": 1.0421595995590371, + "learning_rate": 9.373890254432006e-07, + "loss": 0.7476, + "step": 14094 + }, + { + "epoch": 0.8652813161852727, + "grad_norm": 1.0138760872869412, + "learning_rate": 9.365486926103451e-07, + "loss": 0.6764, + "step": 14095 + }, + { + "epoch": 0.8653427054237393, + "grad_norm": 0.9166821090711661, + "learning_rate": 9.357087181041902e-07, + "loss": 0.678, + "step": 14096 + }, + { + "epoch": 0.8654040946622057, + "grad_norm": 1.0532853649897973, + "learning_rate": 9.348691019579515e-07, + "loss": 0.7144, + "step": 14097 + }, + { + "epoch": 0.8654654839006722, + "grad_norm": 0.987568371857159, + "learning_rate": 9.340298442048201e-07, + "loss": 0.7076, + "step": 14098 + }, + { + "epoch": 0.8655268731391387, + "grad_norm": 1.0783974127224967, + "learning_rate": 9.331909448779775e-07, + "loss": 0.688, + "step": 14099 + }, + { + "epoch": 0.8655882623776052, + "grad_norm": 1.054504889593063, + "learning_rate": 9.323524040105902e-07, + "loss": 0.7544, + "step": 14100 + }, + { + "epoch": 0.8656496516160717, + "grad_norm": 1.0550197102169372, + "learning_rate": 9.315142216358086e-07, + "loss": 0.6944, + "step": 14101 + }, + { + "epoch": 0.8657110408545382, + "grad_norm": 0.9270249523343022, + "learning_rate": 9.306763977867716e-07, + "loss": 0.6773, + "step": 14102 + }, + { + "epoch": 0.8657724300930046, + "grad_norm": 1.129909705037915, + "learning_rate": 9.298389324966017e-07, + "loss": 0.7638, + "step": 14103 + }, + { + "epoch": 0.8658338193314712, + "grad_norm": 0.5909881066936983, + "learning_rate": 9.290018257984102e-07, + "loss": 0.6144, + "step": 14104 + }, + { + "epoch": 0.8658952085699377, + "grad_norm": 1.0378585549500694, + "learning_rate": 9.281650777252938e-07, + "loss": 0.7576, + "step": 14105 + }, + { + "epoch": 0.8659565978084042, + "grad_norm": 1.0354541911169834, + "learning_rate": 9.273286883103305e-07, + "loss": 0.7777, + "step": 14106 + }, + { + "epoch": 0.8660179870468707, + "grad_norm": 1.027138107947397, + "learning_rate": 9.264926575865851e-07, + "loss": 0.7652, + "step": 14107 + }, + { + "epoch": 0.8660793762853372, + "grad_norm": 1.0165332339035813, + "learning_rate": 9.256569855871167e-07, + "loss": 0.7252, + "step": 14108 + }, + { + "epoch": 0.8661407655238037, + "grad_norm": 1.0526213708152525, + "learning_rate": 9.248216723449599e-07, + "loss": 0.6977, + "step": 14109 + }, + { + "epoch": 0.8662021547622701, + "grad_norm": 0.6211731829146627, + "learning_rate": 9.239867178931394e-07, + "loss": 0.7005, + "step": 14110 + }, + { + "epoch": 0.8662635440007367, + "grad_norm": 0.9216988246458162, + "learning_rate": 9.231521222646666e-07, + "loss": 0.7475, + "step": 14111 + }, + { + "epoch": 0.8663249332392031, + "grad_norm": 1.0799829129502205, + "learning_rate": 9.223178854925363e-07, + "loss": 0.7178, + "step": 14112 + }, + { + "epoch": 0.8663863224776697, + "grad_norm": 1.1041613069371214, + "learning_rate": 9.214840076097309e-07, + "loss": 0.7282, + "step": 14113 + }, + { + "epoch": 0.8664477117161362, + "grad_norm": 0.9969448112319192, + "learning_rate": 9.206504886492162e-07, + "loss": 0.7332, + "step": 14114 + }, + { + "epoch": 0.8665091009546027, + "grad_norm": 1.0157650066749324, + "learning_rate": 9.198173286439515e-07, + "loss": 0.6824, + "step": 14115 + }, + { + "epoch": 0.8665704901930692, + "grad_norm": 1.1189452240767959, + "learning_rate": 9.189845276268706e-07, + "loss": 0.751, + "step": 14116 + }, + { + "epoch": 0.8666318794315356, + "grad_norm": 1.012570657193578, + "learning_rate": 9.181520856308967e-07, + "loss": 0.6797, + "step": 14117 + }, + { + "epoch": 0.8666932686700022, + "grad_norm": 1.0983500527557915, + "learning_rate": 9.173200026889473e-07, + "loss": 0.7337, + "step": 14118 + }, + { + "epoch": 0.8667546579084686, + "grad_norm": 0.9483137586406345, + "learning_rate": 9.164882788339147e-07, + "loss": 0.7607, + "step": 14119 + }, + { + "epoch": 0.8668160471469352, + "grad_norm": 0.9797090592515862, + "learning_rate": 9.156569140986848e-07, + "loss": 0.7452, + "step": 14120 + }, + { + "epoch": 0.8668774363854016, + "grad_norm": 1.1159099249542692, + "learning_rate": 9.148259085161204e-07, + "loss": 0.743, + "step": 14121 + }, + { + "epoch": 0.8669388256238681, + "grad_norm": 1.022647290735339, + "learning_rate": 9.139952621190795e-07, + "loss": 0.7372, + "step": 14122 + }, + { + "epoch": 0.8670002148623346, + "grad_norm": 1.1323722637213576, + "learning_rate": 9.131649749404015e-07, + "loss": 0.7269, + "step": 14123 + }, + { + "epoch": 0.8670616041008011, + "grad_norm": 1.001432083346432, + "learning_rate": 9.123350470129122e-07, + "loss": 0.6785, + "step": 14124 + }, + { + "epoch": 0.8671229933392677, + "grad_norm": 1.106882562076477, + "learning_rate": 9.115054783694233e-07, + "loss": 0.685, + "step": 14125 + }, + { + "epoch": 0.8671843825777341, + "grad_norm": 1.0728960675821184, + "learning_rate": 9.106762690427306e-07, + "loss": 0.6717, + "step": 14126 + }, + { + "epoch": 0.8672457718162007, + "grad_norm": 1.0200475163357858, + "learning_rate": 9.098474190656182e-07, + "loss": 0.7575, + "step": 14127 + }, + { + "epoch": 0.8673071610546671, + "grad_norm": 1.117893756169789, + "learning_rate": 9.090189284708539e-07, + "loss": 0.7922, + "step": 14128 + }, + { + "epoch": 0.8673685502931336, + "grad_norm": 0.5885103117665295, + "learning_rate": 9.081907972911941e-07, + "loss": 0.6444, + "step": 14129 + }, + { + "epoch": 0.8674299395316001, + "grad_norm": 1.002982372233151, + "learning_rate": 9.073630255593813e-07, + "loss": 0.7242, + "step": 14130 + }, + { + "epoch": 0.8674913287700666, + "grad_norm": 1.131286781144851, + "learning_rate": 9.065356133081338e-07, + "loss": 0.6843, + "step": 14131 + }, + { + "epoch": 0.8675527180085331, + "grad_norm": 1.007594191404355, + "learning_rate": 9.057085605701721e-07, + "loss": 0.6976, + "step": 14132 + }, + { + "epoch": 0.8676141072469996, + "grad_norm": 1.0354750825231593, + "learning_rate": 9.0488186737819e-07, + "loss": 0.7386, + "step": 14133 + }, + { + "epoch": 0.867675496485466, + "grad_norm": 1.090175563532409, + "learning_rate": 9.040555337648715e-07, + "loss": 0.7034, + "step": 14134 + }, + { + "epoch": 0.8677368857239326, + "grad_norm": 1.0541246450930468, + "learning_rate": 9.032295597628871e-07, + "loss": 0.7452, + "step": 14135 + }, + { + "epoch": 0.8677982749623991, + "grad_norm": 0.9492691934792021, + "learning_rate": 9.024039454048905e-07, + "loss": 0.7485, + "step": 14136 + }, + { + "epoch": 0.8678596642008656, + "grad_norm": 1.1562543883661287, + "learning_rate": 9.015786907235235e-07, + "loss": 0.7471, + "step": 14137 + }, + { + "epoch": 0.8679210534393321, + "grad_norm": 0.9834662805424651, + "learning_rate": 9.007537957514134e-07, + "loss": 0.7148, + "step": 14138 + }, + { + "epoch": 0.8679824426777986, + "grad_norm": 1.0702724931617336, + "learning_rate": 8.999292605211695e-07, + "loss": 0.7562, + "step": 14139 + }, + { + "epoch": 0.8680438319162651, + "grad_norm": 1.0144426954175898, + "learning_rate": 8.991050850653959e-07, + "loss": 0.6753, + "step": 14140 + }, + { + "epoch": 0.8681052211547315, + "grad_norm": 1.068212903940945, + "learning_rate": 8.98281269416672e-07, + "loss": 0.7421, + "step": 14141 + }, + { + "epoch": 0.8681666103931981, + "grad_norm": 0.9827655181800692, + "learning_rate": 8.974578136075662e-07, + "loss": 0.733, + "step": 14142 + }, + { + "epoch": 0.8682279996316645, + "grad_norm": 1.1269427449645806, + "learning_rate": 8.966347176706391e-07, + "loss": 0.7415, + "step": 14143 + }, + { + "epoch": 0.8682893888701311, + "grad_norm": 1.1140300160131413, + "learning_rate": 8.958119816384303e-07, + "loss": 0.7389, + "step": 14144 + }, + { + "epoch": 0.8683507781085975, + "grad_norm": 1.0637377857861674, + "learning_rate": 8.949896055434682e-07, + "loss": 0.716, + "step": 14145 + }, + { + "epoch": 0.8684121673470641, + "grad_norm": 0.9735452900159601, + "learning_rate": 8.9416758941826e-07, + "loss": 0.7427, + "step": 14146 + }, + { + "epoch": 0.8684735565855306, + "grad_norm": 1.066988695698447, + "learning_rate": 8.933459332953098e-07, + "loss": 0.7773, + "step": 14147 + }, + { + "epoch": 0.868534945823997, + "grad_norm": 1.0002622604361546, + "learning_rate": 8.925246372071017e-07, + "loss": 0.7359, + "step": 14148 + }, + { + "epoch": 0.8685963350624636, + "grad_norm": 1.0492547126365348, + "learning_rate": 8.917037011861041e-07, + "loss": 0.7535, + "step": 14149 + }, + { + "epoch": 0.86865772430093, + "grad_norm": 1.1002912932185873, + "learning_rate": 8.908831252647742e-07, + "loss": 0.7134, + "step": 14150 + }, + { + "epoch": 0.8687191135393966, + "grad_norm": 1.1072529319808253, + "learning_rate": 8.900629094755531e-07, + "loss": 0.7081, + "step": 14151 + }, + { + "epoch": 0.868780502777863, + "grad_norm": 0.9699090927639414, + "learning_rate": 8.892430538508689e-07, + "loss": 0.6765, + "step": 14152 + }, + { + "epoch": 0.8688418920163296, + "grad_norm": 0.9222605837124696, + "learning_rate": 8.884235584231326e-07, + "loss": 0.7647, + "step": 14153 + }, + { + "epoch": 0.868903281254796, + "grad_norm": 1.0590474293487568, + "learning_rate": 8.876044232247494e-07, + "loss": 0.7765, + "step": 14154 + }, + { + "epoch": 0.8689646704932625, + "grad_norm": 1.1555552526467585, + "learning_rate": 8.867856482880965e-07, + "loss": 0.7557, + "step": 14155 + }, + { + "epoch": 0.869026059731729, + "grad_norm": 0.9715524549380316, + "learning_rate": 8.859672336455471e-07, + "loss": 0.7321, + "step": 14156 + }, + { + "epoch": 0.8690874489701955, + "grad_norm": 1.103040475455256, + "learning_rate": 8.851491793294598e-07, + "loss": 0.7377, + "step": 14157 + }, + { + "epoch": 0.8691488382086621, + "grad_norm": 1.0204394680417168, + "learning_rate": 8.843314853721752e-07, + "loss": 0.7153, + "step": 14158 + }, + { + "epoch": 0.8692102274471285, + "grad_norm": 1.0239024362288207, + "learning_rate": 8.835141518060231e-07, + "loss": 0.7623, + "step": 14159 + }, + { + "epoch": 0.869271616685595, + "grad_norm": 1.1127703384698706, + "learning_rate": 8.826971786633109e-07, + "loss": 0.7532, + "step": 14160 + }, + { + "epoch": 0.8693330059240615, + "grad_norm": 0.9913865962587474, + "learning_rate": 8.818805659763441e-07, + "loss": 0.6615, + "step": 14161 + }, + { + "epoch": 0.869394395162528, + "grad_norm": 1.0155623216123069, + "learning_rate": 8.810643137774055e-07, + "loss": 0.7152, + "step": 14162 + }, + { + "epoch": 0.8694557844009945, + "grad_norm": 1.1091575931755906, + "learning_rate": 8.802484220987661e-07, + "loss": 0.7263, + "step": 14163 + }, + { + "epoch": 0.869517173639461, + "grad_norm": 0.9923051520315292, + "learning_rate": 8.794328909726823e-07, + "loss": 0.7406, + "step": 14164 + }, + { + "epoch": 0.8695785628779275, + "grad_norm": 1.0286003545812266, + "learning_rate": 8.786177204313962e-07, + "loss": 0.7337, + "step": 14165 + }, + { + "epoch": 0.869639952116394, + "grad_norm": 0.9942642075033932, + "learning_rate": 8.778029105071362e-07, + "loss": 0.697, + "step": 14166 + }, + { + "epoch": 0.8697013413548605, + "grad_norm": 1.1469879349484617, + "learning_rate": 8.769884612321156e-07, + "loss": 0.7779, + "step": 14167 + }, + { + "epoch": 0.869762730593327, + "grad_norm": 0.5865440179179336, + "learning_rate": 8.761743726385352e-07, + "loss": 0.6197, + "step": 14168 + }, + { + "epoch": 0.8698241198317935, + "grad_norm": 1.0496637038871417, + "learning_rate": 8.753606447585816e-07, + "loss": 0.7361, + "step": 14169 + }, + { + "epoch": 0.86988550907026, + "grad_norm": 1.0585611321100201, + "learning_rate": 8.745472776244191e-07, + "loss": 0.7965, + "step": 14170 + }, + { + "epoch": 0.8699468983087265, + "grad_norm": 0.9687668161118531, + "learning_rate": 8.737342712682117e-07, + "loss": 0.7557, + "step": 14171 + }, + { + "epoch": 0.870008287547193, + "grad_norm": 0.9523636521904337, + "learning_rate": 8.729216257220996e-07, + "loss": 0.7055, + "step": 14172 + }, + { + "epoch": 0.8700696767856595, + "grad_norm": 0.5540430391802039, + "learning_rate": 8.721093410182102e-07, + "loss": 0.6483, + "step": 14173 + }, + { + "epoch": 0.8701310660241259, + "grad_norm": 1.0530902335527246, + "learning_rate": 8.712974171886579e-07, + "loss": 0.728, + "step": 14174 + }, + { + "epoch": 0.8701924552625925, + "grad_norm": 1.0931565975581043, + "learning_rate": 8.704858542655425e-07, + "loss": 0.7725, + "step": 14175 + }, + { + "epoch": 0.8702538445010589, + "grad_norm": 1.1052840843345297, + "learning_rate": 8.696746522809496e-07, + "loss": 0.7421, + "step": 14176 + }, + { + "epoch": 0.8703152337395255, + "grad_norm": 1.0147052053043213, + "learning_rate": 8.6886381126695e-07, + "loss": 0.6816, + "step": 14177 + }, + { + "epoch": 0.870376622977992, + "grad_norm": 1.023757401377171, + "learning_rate": 8.680533312555994e-07, + "loss": 0.7313, + "step": 14178 + }, + { + "epoch": 0.8704380122164584, + "grad_norm": 1.1277235252390454, + "learning_rate": 8.672432122789442e-07, + "loss": 0.6552, + "step": 14179 + }, + { + "epoch": 0.870499401454925, + "grad_norm": 0.970613983074239, + "learning_rate": 8.664334543690089e-07, + "loss": 0.7234, + "step": 14180 + }, + { + "epoch": 0.8705607906933914, + "grad_norm": 0.9300966138148358, + "learning_rate": 8.656240575578079e-07, + "loss": 0.7275, + "step": 14181 + }, + { + "epoch": 0.870622179931858, + "grad_norm": 0.9882228783792691, + "learning_rate": 8.648150218773421e-07, + "loss": 0.698, + "step": 14182 + }, + { + "epoch": 0.8706835691703244, + "grad_norm": 1.1673842806793187, + "learning_rate": 8.640063473595984e-07, + "loss": 0.7329, + "step": 14183 + }, + { + "epoch": 0.870744958408791, + "grad_norm": 1.0412418927990363, + "learning_rate": 8.631980340365476e-07, + "loss": 0.7398, + "step": 14184 + }, + { + "epoch": 0.8708063476472574, + "grad_norm": 0.9395488795870693, + "learning_rate": 8.623900819401421e-07, + "loss": 0.6715, + "step": 14185 + }, + { + "epoch": 0.8708677368857239, + "grad_norm": 1.2376255420432447, + "learning_rate": 8.615824911023296e-07, + "loss": 0.7155, + "step": 14186 + }, + { + "epoch": 0.8709291261241904, + "grad_norm": 1.0845241124231981, + "learning_rate": 8.60775261555038e-07, + "loss": 0.7093, + "step": 14187 + }, + { + "epoch": 0.8709905153626569, + "grad_norm": 1.120937008310193, + "learning_rate": 8.599683933301794e-07, + "loss": 0.744, + "step": 14188 + }, + { + "epoch": 0.8710519046011235, + "grad_norm": 1.0294726540723405, + "learning_rate": 8.591618864596541e-07, + "loss": 0.7516, + "step": 14189 + }, + { + "epoch": 0.8711132938395899, + "grad_norm": 1.059139901334522, + "learning_rate": 8.583557409753485e-07, + "loss": 0.7609, + "step": 14190 + }, + { + "epoch": 0.8711746830780565, + "grad_norm": 1.0566903332826245, + "learning_rate": 8.575499569091339e-07, + "loss": 0.7566, + "step": 14191 + }, + { + "epoch": 0.8712360723165229, + "grad_norm": 1.2372749243222685, + "learning_rate": 8.567445342928649e-07, + "loss": 0.7418, + "step": 14192 + }, + { + "epoch": 0.8712974615549894, + "grad_norm": 0.9596081487334672, + "learning_rate": 8.55939473158387e-07, + "loss": 0.7767, + "step": 14193 + }, + { + "epoch": 0.8713588507934559, + "grad_norm": 0.9731462908586528, + "learning_rate": 8.551347735375304e-07, + "loss": 0.691, + "step": 14194 + }, + { + "epoch": 0.8714202400319224, + "grad_norm": 0.9611771601856423, + "learning_rate": 8.543304354621018e-07, + "loss": 0.7124, + "step": 14195 + }, + { + "epoch": 0.8714816292703889, + "grad_norm": 1.052783785708899, + "learning_rate": 8.53526458963908e-07, + "loss": 0.7966, + "step": 14196 + }, + { + "epoch": 0.8715430185088554, + "grad_norm": 0.9957882031152941, + "learning_rate": 8.527228440747326e-07, + "loss": 0.727, + "step": 14197 + }, + { + "epoch": 0.8716044077473218, + "grad_norm": 1.1268567177568363, + "learning_rate": 8.519195908263456e-07, + "loss": 0.7024, + "step": 14198 + }, + { + "epoch": 0.8716657969857884, + "grad_norm": 1.076835311940601, + "learning_rate": 8.511166992505038e-07, + "loss": 0.7379, + "step": 14199 + }, + { + "epoch": 0.8717271862242549, + "grad_norm": 1.101777402174345, + "learning_rate": 8.503141693789518e-07, + "loss": 0.7544, + "step": 14200 + }, + { + "epoch": 0.8717885754627214, + "grad_norm": 1.0292477626103491, + "learning_rate": 8.495120012434155e-07, + "loss": 0.7008, + "step": 14201 + }, + { + "epoch": 0.8718499647011879, + "grad_norm": 0.9652980985192544, + "learning_rate": 8.487101948756105e-07, + "loss": 0.7501, + "step": 14202 + }, + { + "epoch": 0.8719113539396544, + "grad_norm": 1.077216642115135, + "learning_rate": 8.479087503072348e-07, + "loss": 0.7508, + "step": 14203 + }, + { + "epoch": 0.8719727431781209, + "grad_norm": 1.1475567717990116, + "learning_rate": 8.471076675699785e-07, + "loss": 0.6638, + "step": 14204 + }, + { + "epoch": 0.8720341324165873, + "grad_norm": 1.0836433701572, + "learning_rate": 8.463069466955065e-07, + "loss": 0.7334, + "step": 14205 + }, + { + "epoch": 0.8720955216550539, + "grad_norm": 0.971017971750488, + "learning_rate": 8.455065877154778e-07, + "loss": 0.7265, + "step": 14206 + }, + { + "epoch": 0.8721569108935203, + "grad_norm": 1.1045845406196666, + "learning_rate": 8.447065906615359e-07, + "loss": 0.688, + "step": 14207 + }, + { + "epoch": 0.8722183001319869, + "grad_norm": 1.0246174305695892, + "learning_rate": 8.43906955565309e-07, + "loss": 0.6609, + "step": 14208 + }, + { + "epoch": 0.8722796893704534, + "grad_norm": 1.0712567437360305, + "learning_rate": 8.431076824584106e-07, + "loss": 0.708, + "step": 14209 + }, + { + "epoch": 0.8723410786089199, + "grad_norm": 1.0530078258574969, + "learning_rate": 8.423087713724399e-07, + "loss": 0.7158, + "step": 14210 + }, + { + "epoch": 0.8724024678473864, + "grad_norm": 1.0072794772033322, + "learning_rate": 8.415102223389815e-07, + "loss": 0.7786, + "step": 14211 + }, + { + "epoch": 0.8724638570858528, + "grad_norm": 1.0461741117742687, + "learning_rate": 8.407120353896081e-07, + "loss": 0.7101, + "step": 14212 + }, + { + "epoch": 0.8725252463243194, + "grad_norm": 1.0180378658102027, + "learning_rate": 8.399142105558745e-07, + "loss": 0.7066, + "step": 14213 + }, + { + "epoch": 0.8725866355627858, + "grad_norm": 1.2398861571316697, + "learning_rate": 8.391167478693241e-07, + "loss": 0.7459, + "step": 14214 + }, + { + "epoch": 0.8726480248012524, + "grad_norm": 0.9669742531422485, + "learning_rate": 8.383196473614852e-07, + "loss": 0.716, + "step": 14215 + }, + { + "epoch": 0.8727094140397188, + "grad_norm": 1.0052326292925635, + "learning_rate": 8.375229090638693e-07, + "loss": 0.7197, + "step": 14216 + }, + { + "epoch": 0.8727708032781853, + "grad_norm": 0.976354324750943, + "learning_rate": 8.367265330079766e-07, + "loss": 0.6755, + "step": 14217 + }, + { + "epoch": 0.8728321925166518, + "grad_norm": 1.0900817987349831, + "learning_rate": 8.359305192252954e-07, + "loss": 0.7541, + "step": 14218 + }, + { + "epoch": 0.8728935817551183, + "grad_norm": 1.0335690149548404, + "learning_rate": 8.351348677472926e-07, + "loss": 0.6883, + "step": 14219 + }, + { + "epoch": 0.8729549709935849, + "grad_norm": 0.9524654025873415, + "learning_rate": 8.343395786054231e-07, + "loss": 0.7307, + "step": 14220 + }, + { + "epoch": 0.8730163602320513, + "grad_norm": 1.0365771210452552, + "learning_rate": 8.335446518311341e-07, + "loss": 0.7168, + "step": 14221 + }, + { + "epoch": 0.8730777494705179, + "grad_norm": 1.0485967780644807, + "learning_rate": 8.327500874558502e-07, + "loss": 0.7303, + "step": 14222 + }, + { + "epoch": 0.8731391387089843, + "grad_norm": 1.1240336182994097, + "learning_rate": 8.319558855109866e-07, + "loss": 0.7238, + "step": 14223 + }, + { + "epoch": 0.8732005279474508, + "grad_norm": 1.0138329681837992, + "learning_rate": 8.31162046027938e-07, + "loss": 0.7538, + "step": 14224 + }, + { + "epoch": 0.8732619171859173, + "grad_norm": 1.0896123302426495, + "learning_rate": 8.303685690380935e-07, + "loss": 0.7285, + "step": 14225 + }, + { + "epoch": 0.8733233064243838, + "grad_norm": 1.0895736122869495, + "learning_rate": 8.295754545728229e-07, + "loss": 0.702, + "step": 14226 + }, + { + "epoch": 0.8733846956628503, + "grad_norm": 1.0393733172856137, + "learning_rate": 8.28782702663481e-07, + "loss": 0.7241, + "step": 14227 + }, + { + "epoch": 0.8734460849013168, + "grad_norm": 0.9236982245371945, + "learning_rate": 8.279903133414091e-07, + "loss": 0.6961, + "step": 14228 + }, + { + "epoch": 0.8735074741397832, + "grad_norm": 1.012958135491722, + "learning_rate": 8.271982866379369e-07, + "loss": 0.6932, + "step": 14229 + }, + { + "epoch": 0.8735688633782498, + "grad_norm": 0.9706759058663413, + "learning_rate": 8.264066225843747e-07, + "loss": 0.7296, + "step": 14230 + }, + { + "epoch": 0.8736302526167163, + "grad_norm": 1.0535074632457369, + "learning_rate": 8.256153212120222e-07, + "loss": 0.6664, + "step": 14231 + }, + { + "epoch": 0.8736916418551828, + "grad_norm": 1.0863814196246075, + "learning_rate": 8.248243825521652e-07, + "loss": 0.6699, + "step": 14232 + }, + { + "epoch": 0.8737530310936493, + "grad_norm": 1.046684646905032, + "learning_rate": 8.240338066360742e-07, + "loss": 0.6981, + "step": 14233 + }, + { + "epoch": 0.8738144203321158, + "grad_norm": 1.1214895800023015, + "learning_rate": 8.232435934950001e-07, + "loss": 0.7601, + "step": 14234 + }, + { + "epoch": 0.8738758095705823, + "grad_norm": 0.9779766095947654, + "learning_rate": 8.224537431601886e-07, + "loss": 0.7141, + "step": 14235 + }, + { + "epoch": 0.8739371988090487, + "grad_norm": 1.0822322994676536, + "learning_rate": 8.216642556628662e-07, + "loss": 0.7317, + "step": 14236 + }, + { + "epoch": 0.8739985880475153, + "grad_norm": 1.09757405668737, + "learning_rate": 8.208751310342444e-07, + "loss": 0.7437, + "step": 14237 + }, + { + "epoch": 0.8740599772859817, + "grad_norm": 1.0934482537151422, + "learning_rate": 8.200863693055228e-07, + "loss": 0.7458, + "step": 14238 + }, + { + "epoch": 0.8741213665244483, + "grad_norm": 1.0912613013972452, + "learning_rate": 8.192979705078852e-07, + "loss": 0.7465, + "step": 14239 + }, + { + "epoch": 0.8741827557629147, + "grad_norm": 0.5927452445356433, + "learning_rate": 8.18509934672499e-07, + "loss": 0.6527, + "step": 14240 + }, + { + "epoch": 0.8742441450013813, + "grad_norm": 1.0656038360479565, + "learning_rate": 8.177222618305225e-07, + "loss": 0.6781, + "step": 14241 + }, + { + "epoch": 0.8743055342398478, + "grad_norm": 1.0951997505274156, + "learning_rate": 8.169349520130931e-07, + "loss": 0.7599, + "step": 14242 + }, + { + "epoch": 0.8743669234783142, + "grad_norm": 1.0554124916238568, + "learning_rate": 8.161480052513426e-07, + "loss": 0.7362, + "step": 14243 + }, + { + "epoch": 0.8744283127167808, + "grad_norm": 0.6338222567050021, + "learning_rate": 8.153614215763783e-07, + "loss": 0.6763, + "step": 14244 + }, + { + "epoch": 0.8744897019552472, + "grad_norm": 1.1235603028123218, + "learning_rate": 8.145752010192986e-07, + "loss": 0.7267, + "step": 14245 + }, + { + "epoch": 0.8745510911937138, + "grad_norm": 0.9503977215275282, + "learning_rate": 8.13789343611191e-07, + "loss": 0.7423, + "step": 14246 + }, + { + "epoch": 0.8746124804321802, + "grad_norm": 1.0881504174210321, + "learning_rate": 8.130038493831205e-07, + "loss": 0.7338, + "step": 14247 + }, + { + "epoch": 0.8746738696706468, + "grad_norm": 1.1333582544521938, + "learning_rate": 8.122187183661434e-07, + "loss": 0.7035, + "step": 14248 + }, + { + "epoch": 0.8747352589091132, + "grad_norm": 1.044558558033991, + "learning_rate": 8.114339505913016e-07, + "loss": 0.7508, + "step": 14249 + }, + { + "epoch": 0.8747966481475797, + "grad_norm": 1.0597995860781226, + "learning_rate": 8.10649546089618e-07, + "loss": 0.746, + "step": 14250 + }, + { + "epoch": 0.8748580373860462, + "grad_norm": 1.0145175451700055, + "learning_rate": 8.098655048921067e-07, + "loss": 0.6867, + "step": 14251 + }, + { + "epoch": 0.8749194266245127, + "grad_norm": 1.0215124225535142, + "learning_rate": 8.09081827029764e-07, + "loss": 0.7463, + "step": 14252 + }, + { + "epoch": 0.8749808158629793, + "grad_norm": 1.1514087146869905, + "learning_rate": 8.082985125335729e-07, + "loss": 0.7349, + "step": 14253 + }, + { + "epoch": 0.8750422051014457, + "grad_norm": 1.020354546800476, + "learning_rate": 8.075155614345031e-07, + "loss": 0.7188, + "step": 14254 + }, + { + "epoch": 0.8751035943399122, + "grad_norm": 0.9636601492619256, + "learning_rate": 8.067329737635077e-07, + "loss": 0.721, + "step": 14255 + }, + { + "epoch": 0.8751649835783787, + "grad_norm": 1.0511510237753703, + "learning_rate": 8.059507495515251e-07, + "loss": 0.7988, + "step": 14256 + }, + { + "epoch": 0.8752263728168452, + "grad_norm": 1.0836314247309606, + "learning_rate": 8.05168888829484e-07, + "loss": 0.7238, + "step": 14257 + }, + { + "epoch": 0.8752877620553117, + "grad_norm": 0.9372399162587072, + "learning_rate": 8.043873916282963e-07, + "loss": 0.6911, + "step": 14258 + }, + { + "epoch": 0.8753491512937782, + "grad_norm": 1.067912757993286, + "learning_rate": 8.036062579788528e-07, + "loss": 0.7691, + "step": 14259 + }, + { + "epoch": 0.8754105405322447, + "grad_norm": 1.0750351433167653, + "learning_rate": 8.028254879120412e-07, + "loss": 0.7429, + "step": 14260 + }, + { + "epoch": 0.8754719297707112, + "grad_norm": 1.098750474412468, + "learning_rate": 8.020450814587289e-07, + "loss": 0.769, + "step": 14261 + }, + { + "epoch": 0.8755333190091777, + "grad_norm": 1.0261770111322204, + "learning_rate": 8.012650386497678e-07, + "loss": 0.7354, + "step": 14262 + }, + { + "epoch": 0.8755947082476442, + "grad_norm": 0.9000319297385576, + "learning_rate": 8.00485359515999e-07, + "loss": 0.6992, + "step": 14263 + }, + { + "epoch": 0.8756560974861107, + "grad_norm": 1.0985570010572399, + "learning_rate": 7.997060440882453e-07, + "loss": 0.7337, + "step": 14264 + }, + { + "epoch": 0.8757174867245772, + "grad_norm": 1.0141830743957534, + "learning_rate": 7.989270923973191e-07, + "loss": 0.7188, + "step": 14265 + }, + { + "epoch": 0.8757788759630437, + "grad_norm": 0.9060530847853187, + "learning_rate": 7.981485044740145e-07, + "loss": 0.7357, + "step": 14266 + }, + { + "epoch": 0.8758402652015101, + "grad_norm": 1.0187146858059157, + "learning_rate": 7.973702803491145e-07, + "loss": 0.6872, + "step": 14267 + }, + { + "epoch": 0.8759016544399767, + "grad_norm": 0.9394383311602272, + "learning_rate": 7.965924200533892e-07, + "loss": 0.7506, + "step": 14268 + }, + { + "epoch": 0.8759630436784431, + "grad_norm": 0.9296426511566923, + "learning_rate": 7.95814923617586e-07, + "loss": 0.8002, + "step": 14269 + }, + { + "epoch": 0.8760244329169097, + "grad_norm": 1.0975353437874227, + "learning_rate": 7.950377910724461e-07, + "loss": 0.7764, + "step": 14270 + }, + { + "epoch": 0.8760858221553761, + "grad_norm": 0.9787181479542547, + "learning_rate": 7.942610224486947e-07, + "loss": 0.7737, + "step": 14271 + }, + { + "epoch": 0.8761472113938427, + "grad_norm": 0.9981888948330094, + "learning_rate": 7.934846177770417e-07, + "loss": 0.7334, + "step": 14272 + }, + { + "epoch": 0.8762086006323092, + "grad_norm": 0.9911074727605086, + "learning_rate": 7.927085770881815e-07, + "loss": 0.726, + "step": 14273 + }, + { + "epoch": 0.8762699898707756, + "grad_norm": 1.010026624576597, + "learning_rate": 7.91932900412794e-07, + "loss": 0.6898, + "step": 14274 + }, + { + "epoch": 0.8763313791092422, + "grad_norm": 1.037283250489844, + "learning_rate": 7.91157587781548e-07, + "loss": 0.7325, + "step": 14275 + }, + { + "epoch": 0.8763927683477086, + "grad_norm": 1.0025115450681843, + "learning_rate": 7.903826392250957e-07, + "loss": 0.7228, + "step": 14276 + }, + { + "epoch": 0.8764541575861752, + "grad_norm": 0.9529895992530428, + "learning_rate": 7.896080547740737e-07, + "loss": 0.7388, + "step": 14277 + }, + { + "epoch": 0.8765155468246416, + "grad_norm": 0.5891348116835377, + "learning_rate": 7.888338344591051e-07, + "loss": 0.6703, + "step": 14278 + }, + { + "epoch": 0.8765769360631082, + "grad_norm": 1.089849889678772, + "learning_rate": 7.880599783108012e-07, + "loss": 0.7447, + "step": 14279 + }, + { + "epoch": 0.8766383253015746, + "grad_norm": 0.9176152642186858, + "learning_rate": 7.87286486359754e-07, + "loss": 0.6958, + "step": 14280 + }, + { + "epoch": 0.8766997145400411, + "grad_norm": 1.0219356587730386, + "learning_rate": 7.865133586365436e-07, + "loss": 0.6703, + "step": 14281 + }, + { + "epoch": 0.8767611037785076, + "grad_norm": 1.1073120227167372, + "learning_rate": 7.857405951717412e-07, + "loss": 0.7237, + "step": 14282 + }, + { + "epoch": 0.8768224930169741, + "grad_norm": 1.0971192701176216, + "learning_rate": 7.849681959958921e-07, + "loss": 0.7195, + "step": 14283 + }, + { + "epoch": 0.8768838822554407, + "grad_norm": 1.1335449562544986, + "learning_rate": 7.841961611395354e-07, + "loss": 0.726, + "step": 14284 + }, + { + "epoch": 0.8769452714939071, + "grad_norm": 1.161404732292044, + "learning_rate": 7.834244906331945e-07, + "loss": 0.6838, + "step": 14285 + }, + { + "epoch": 0.8770066607323737, + "grad_norm": 0.8632658745615978, + "learning_rate": 7.82653184507377e-07, + "loss": 0.6894, + "step": 14286 + }, + { + "epoch": 0.8770680499708401, + "grad_norm": 1.0509134744001964, + "learning_rate": 7.818822427925777e-07, + "loss": 0.6837, + "step": 14287 + }, + { + "epoch": 0.8771294392093066, + "grad_norm": 1.1070529825136382, + "learning_rate": 7.811116655192752e-07, + "loss": 0.6926, + "step": 14288 + }, + { + "epoch": 0.8771908284477731, + "grad_norm": 1.1793847813844198, + "learning_rate": 7.803414527179343e-07, + "loss": 0.7476, + "step": 14289 + }, + { + "epoch": 0.8772522176862396, + "grad_norm": 1.2171969007665078, + "learning_rate": 7.795716044190061e-07, + "loss": 0.7493, + "step": 14290 + }, + { + "epoch": 0.8773136069247061, + "grad_norm": 0.945541885302312, + "learning_rate": 7.788021206529262e-07, + "loss": 0.7288, + "step": 14291 + }, + { + "epoch": 0.8773749961631726, + "grad_norm": 1.1625850503211987, + "learning_rate": 7.78033001450117e-07, + "loss": 0.7325, + "step": 14292 + }, + { + "epoch": 0.877436385401639, + "grad_norm": 1.0151640447430845, + "learning_rate": 7.772642468409864e-07, + "loss": 0.7329, + "step": 14293 + }, + { + "epoch": 0.8774977746401056, + "grad_norm": 0.9748210071100404, + "learning_rate": 7.764958568559267e-07, + "loss": 0.7412, + "step": 14294 + }, + { + "epoch": 0.8775591638785721, + "grad_norm": 1.1434395814687492, + "learning_rate": 7.757278315253147e-07, + "loss": 0.6928, + "step": 14295 + }, + { + "epoch": 0.8776205531170386, + "grad_norm": 1.1690287113279465, + "learning_rate": 7.749601708795173e-07, + "loss": 0.7381, + "step": 14296 + }, + { + "epoch": 0.8776819423555051, + "grad_norm": 0.9711106880208047, + "learning_rate": 7.74192874948887e-07, + "loss": 0.7488, + "step": 14297 + }, + { + "epoch": 0.8777433315939716, + "grad_norm": 1.047433435841147, + "learning_rate": 7.734259437637504e-07, + "loss": 0.7568, + "step": 14298 + }, + { + "epoch": 0.8778047208324381, + "grad_norm": 1.2312573417232888, + "learning_rate": 7.726593773544355e-07, + "loss": 0.7147, + "step": 14299 + }, + { + "epoch": 0.8778661100709045, + "grad_norm": 1.0287484871737835, + "learning_rate": 7.718931757512471e-07, + "loss": 0.7395, + "step": 14300 + }, + { + "epoch": 0.8779274993093711, + "grad_norm": 1.0127443754476124, + "learning_rate": 7.711273389844764e-07, + "loss": 0.708, + "step": 14301 + }, + { + "epoch": 0.8779888885478375, + "grad_norm": 1.1381038917839752, + "learning_rate": 7.703618670844016e-07, + "loss": 0.7443, + "step": 14302 + }, + { + "epoch": 0.8780502777863041, + "grad_norm": 1.0411823543178949, + "learning_rate": 7.69596760081286e-07, + "loss": 0.7569, + "step": 14303 + }, + { + "epoch": 0.8781116670247705, + "grad_norm": 1.0123592516616091, + "learning_rate": 7.688320180053777e-07, + "loss": 0.688, + "step": 14304 + }, + { + "epoch": 0.878173056263237, + "grad_norm": 1.1434701634886006, + "learning_rate": 7.680676408869114e-07, + "loss": 0.7359, + "step": 14305 + }, + { + "epoch": 0.8782344455017036, + "grad_norm": 1.0967437565104619, + "learning_rate": 7.673036287561053e-07, + "loss": 0.6917, + "step": 14306 + }, + { + "epoch": 0.87829583474017, + "grad_norm": 0.9493718902241088, + "learning_rate": 7.665399816431707e-07, + "loss": 0.6875, + "step": 14307 + }, + { + "epoch": 0.8783572239786366, + "grad_norm": 0.9886743241604414, + "learning_rate": 7.657766995782923e-07, + "loss": 0.6943, + "step": 14308 + }, + { + "epoch": 0.878418613217103, + "grad_norm": 1.1330504480660153, + "learning_rate": 7.650137825916482e-07, + "loss": 0.7175, + "step": 14309 + }, + { + "epoch": 0.8784800024555696, + "grad_norm": 1.0436044867585788, + "learning_rate": 7.642512307134032e-07, + "loss": 0.719, + "step": 14310 + }, + { + "epoch": 0.878541391694036, + "grad_norm": 1.1411649271098445, + "learning_rate": 7.634890439737019e-07, + "loss": 0.7355, + "step": 14311 + }, + { + "epoch": 0.8786027809325025, + "grad_norm": 1.0348770289137699, + "learning_rate": 7.627272224026805e-07, + "loss": 0.7073, + "step": 14312 + }, + { + "epoch": 0.878664170170969, + "grad_norm": 1.0815851019820018, + "learning_rate": 7.619657660304558e-07, + "loss": 0.7393, + "step": 14313 + }, + { + "epoch": 0.8787255594094355, + "grad_norm": 0.5891449299986927, + "learning_rate": 7.612046748871327e-07, + "loss": 0.6223, + "step": 14314 + }, + { + "epoch": 0.8787869486479021, + "grad_norm": 0.9948914484526825, + "learning_rate": 7.604439490028015e-07, + "loss": 0.7551, + "step": 14315 + }, + { + "epoch": 0.8788483378863685, + "grad_norm": 0.8565050536323474, + "learning_rate": 7.596835884075382e-07, + "loss": 0.7345, + "step": 14316 + }, + { + "epoch": 0.8789097271248351, + "grad_norm": 1.0714551100855092, + "learning_rate": 7.589235931314021e-07, + "loss": 0.7063, + "step": 14317 + }, + { + "epoch": 0.8789711163633015, + "grad_norm": 1.1409998571468596, + "learning_rate": 7.581639632044424e-07, + "loss": 0.7494, + "step": 14318 + }, + { + "epoch": 0.879032505601768, + "grad_norm": 1.0601819954375131, + "learning_rate": 7.574046986566897e-07, + "loss": 0.7013, + "step": 14319 + }, + { + "epoch": 0.8790938948402345, + "grad_norm": 1.2152454192886224, + "learning_rate": 7.566457995181598e-07, + "loss": 0.7804, + "step": 14320 + }, + { + "epoch": 0.879155284078701, + "grad_norm": 1.082886955131632, + "learning_rate": 7.55887265818861e-07, + "loss": 0.7062, + "step": 14321 + }, + { + "epoch": 0.8792166733171675, + "grad_norm": 1.020381057197206, + "learning_rate": 7.551290975887804e-07, + "loss": 0.7484, + "step": 14322 + }, + { + "epoch": 0.879278062555634, + "grad_norm": 0.9630509925733477, + "learning_rate": 7.543712948578885e-07, + "loss": 0.7383, + "step": 14323 + }, + { + "epoch": 0.8793394517941004, + "grad_norm": 0.9854330075553163, + "learning_rate": 7.536138576561502e-07, + "loss": 0.7166, + "step": 14324 + }, + { + "epoch": 0.879400841032567, + "grad_norm": 1.0469889472190486, + "learning_rate": 7.528567860135094e-07, + "loss": 0.7742, + "step": 14325 + }, + { + "epoch": 0.8794622302710335, + "grad_norm": 0.9657784028406675, + "learning_rate": 7.521000799598965e-07, + "loss": 0.7563, + "step": 14326 + }, + { + "epoch": 0.8795236195095, + "grad_norm": 1.0610056507507217, + "learning_rate": 7.513437395252298e-07, + "loss": 0.6934, + "step": 14327 + }, + { + "epoch": 0.8795850087479665, + "grad_norm": 1.1954357950023453, + "learning_rate": 7.505877647394089e-07, + "loss": 0.7572, + "step": 14328 + }, + { + "epoch": 0.879646397986433, + "grad_norm": 0.9778119830578311, + "learning_rate": 7.49832155632324e-07, + "loss": 0.734, + "step": 14329 + }, + { + "epoch": 0.8797077872248995, + "grad_norm": 1.076144771771537, + "learning_rate": 7.49076912233847e-07, + "loss": 0.7533, + "step": 14330 + }, + { + "epoch": 0.8797691764633659, + "grad_norm": 1.072749684752331, + "learning_rate": 7.483220345738352e-07, + "loss": 0.7155, + "step": 14331 + }, + { + "epoch": 0.8798305657018325, + "grad_norm": 1.0404077216519036, + "learning_rate": 7.475675226821388e-07, + "loss": 0.7227, + "step": 14332 + }, + { + "epoch": 0.8798919549402989, + "grad_norm": 1.165512886602215, + "learning_rate": 7.468133765885821e-07, + "loss": 0.7185, + "step": 14333 + }, + { + "epoch": 0.8799533441787655, + "grad_norm": 1.1032134661708837, + "learning_rate": 7.460595963229799e-07, + "loss": 0.752, + "step": 14334 + }, + { + "epoch": 0.8800147334172319, + "grad_norm": 1.0482756755405334, + "learning_rate": 7.453061819151375e-07, + "loss": 0.7169, + "step": 14335 + }, + { + "epoch": 0.8800761226556985, + "grad_norm": 1.0239614200654077, + "learning_rate": 7.445531333948385e-07, + "loss": 0.6951, + "step": 14336 + }, + { + "epoch": 0.880137511894165, + "grad_norm": 1.1410197826966506, + "learning_rate": 7.438004507918562e-07, + "loss": 0.7313, + "step": 14337 + }, + { + "epoch": 0.8801989011326314, + "grad_norm": 0.9895039329426258, + "learning_rate": 7.430481341359486e-07, + "loss": 0.7248, + "step": 14338 + }, + { + "epoch": 0.880260290371098, + "grad_norm": 0.9896760597955246, + "learning_rate": 7.422961834568565e-07, + "loss": 0.7192, + "step": 14339 + }, + { + "epoch": 0.8803216796095644, + "grad_norm": 1.0332298670284346, + "learning_rate": 7.415445987843106e-07, + "loss": 0.6861, + "step": 14340 + }, + { + "epoch": 0.880383068848031, + "grad_norm": 1.107969485923165, + "learning_rate": 7.407933801480249e-07, + "loss": 0.7101, + "step": 14341 + }, + { + "epoch": 0.8804444580864974, + "grad_norm": 1.1717627446774996, + "learning_rate": 7.400425275776979e-07, + "loss": 0.7746, + "step": 14342 + }, + { + "epoch": 0.880505847324964, + "grad_norm": 1.0551418056145785, + "learning_rate": 7.392920411030158e-07, + "loss": 0.7041, + "step": 14343 + }, + { + "epoch": 0.8805672365634304, + "grad_norm": 0.9867223531331752, + "learning_rate": 7.385419207536493e-07, + "loss": 0.7126, + "step": 14344 + }, + { + "epoch": 0.8806286258018969, + "grad_norm": 0.9531692974479884, + "learning_rate": 7.377921665592525e-07, + "loss": 0.7011, + "step": 14345 + }, + { + "epoch": 0.8806900150403634, + "grad_norm": 0.9830256996207866, + "learning_rate": 7.370427785494704e-07, + "loss": 0.7298, + "step": 14346 + }, + { + "epoch": 0.8807514042788299, + "grad_norm": 0.9768402226870262, + "learning_rate": 7.362937567539307e-07, + "loss": 0.7185, + "step": 14347 + }, + { + "epoch": 0.8808127935172965, + "grad_norm": 1.0348508980036635, + "learning_rate": 7.355451012022418e-07, + "loss": 0.7278, + "step": 14348 + }, + { + "epoch": 0.8808741827557629, + "grad_norm": 1.0835324328453806, + "learning_rate": 7.347968119240068e-07, + "loss": 0.7554, + "step": 14349 + }, + { + "epoch": 0.8809355719942294, + "grad_norm": 1.2025621133309552, + "learning_rate": 7.340488889488073e-07, + "loss": 0.7238, + "step": 14350 + }, + { + "epoch": 0.8809969612326959, + "grad_norm": 1.0134360415014596, + "learning_rate": 7.333013323062121e-07, + "loss": 0.7476, + "step": 14351 + }, + { + "epoch": 0.8810583504711624, + "grad_norm": 1.1321821028321226, + "learning_rate": 7.325541420257776e-07, + "loss": 0.6883, + "step": 14352 + }, + { + "epoch": 0.8811197397096289, + "grad_norm": 1.05893236682044, + "learning_rate": 7.318073181370444e-07, + "loss": 0.7056, + "step": 14353 + }, + { + "epoch": 0.8811811289480954, + "grad_norm": 1.0558241474496557, + "learning_rate": 7.310608606695369e-07, + "loss": 0.7175, + "step": 14354 + }, + { + "epoch": 0.8812425181865619, + "grad_norm": 0.9745588391710938, + "learning_rate": 7.30314769652768e-07, + "loss": 0.7116, + "step": 14355 + }, + { + "epoch": 0.8813039074250284, + "grad_norm": 1.1180126915483186, + "learning_rate": 7.29569045116233e-07, + "loss": 0.7179, + "step": 14356 + }, + { + "epoch": 0.8813652966634948, + "grad_norm": 1.1672599653084028, + "learning_rate": 7.28823687089416e-07, + "loss": 0.761, + "step": 14357 + }, + { + "epoch": 0.8814266859019614, + "grad_norm": 0.8671814093376091, + "learning_rate": 7.280786956017849e-07, + "loss": 0.6799, + "step": 14358 + }, + { + "epoch": 0.8814880751404279, + "grad_norm": 0.5610948385901219, + "learning_rate": 7.273340706827902e-07, + "loss": 0.5824, + "step": 14359 + }, + { + "epoch": 0.8815494643788944, + "grad_norm": 1.1271911551028222, + "learning_rate": 7.265898123618753e-07, + "loss": 0.7911, + "step": 14360 + }, + { + "epoch": 0.8816108536173609, + "grad_norm": 1.100385122819543, + "learning_rate": 7.258459206684642e-07, + "loss": 0.7288, + "step": 14361 + }, + { + "epoch": 0.8816722428558273, + "grad_norm": 1.058936189782451, + "learning_rate": 7.251023956319624e-07, + "loss": 0.7581, + "step": 14362 + }, + { + "epoch": 0.8817336320942939, + "grad_norm": 1.0606205588112905, + "learning_rate": 7.24359237281771e-07, + "loss": 0.7188, + "step": 14363 + }, + { + "epoch": 0.8817950213327603, + "grad_norm": 1.0008084788275395, + "learning_rate": 7.236164456472672e-07, + "loss": 0.7103, + "step": 14364 + }, + { + "epoch": 0.8818564105712269, + "grad_norm": 1.0899586607541023, + "learning_rate": 7.2287402075782e-07, + "loss": 0.6951, + "step": 14365 + }, + { + "epoch": 0.8819177998096933, + "grad_norm": 1.04996019503947, + "learning_rate": 7.221319626427791e-07, + "loss": 0.7557, + "step": 14366 + }, + { + "epoch": 0.8819791890481599, + "grad_norm": 1.1208845317430518, + "learning_rate": 7.213902713314846e-07, + "loss": 0.7271, + "step": 14367 + }, + { + "epoch": 0.8820405782866264, + "grad_norm": 1.0026676142369655, + "learning_rate": 7.206489468532574e-07, + "loss": 0.6803, + "step": 14368 + }, + { + "epoch": 0.8821019675250928, + "grad_norm": 0.943522681878739, + "learning_rate": 7.199079892374072e-07, + "loss": 0.7176, + "step": 14369 + }, + { + "epoch": 0.8821633567635594, + "grad_norm": 1.1663228383657749, + "learning_rate": 7.191673985132252e-07, + "loss": 0.749, + "step": 14370 + }, + { + "epoch": 0.8822247460020258, + "grad_norm": 1.112976544655712, + "learning_rate": 7.18427174709998e-07, + "loss": 0.7401, + "step": 14371 + }, + { + "epoch": 0.8822861352404924, + "grad_norm": 1.0695471908589267, + "learning_rate": 7.176873178569832e-07, + "loss": 0.7214, + "step": 14372 + }, + { + "epoch": 0.8823475244789588, + "grad_norm": 1.169416469795754, + "learning_rate": 7.169478279834319e-07, + "loss": 0.7715, + "step": 14373 + }, + { + "epoch": 0.8824089137174254, + "grad_norm": 1.1028800416710636, + "learning_rate": 7.162087051185851e-07, + "loss": 0.7575, + "step": 14374 + }, + { + "epoch": 0.8824703029558918, + "grad_norm": 1.0891175690316208, + "learning_rate": 7.154699492916606e-07, + "loss": 0.7474, + "step": 14375 + }, + { + "epoch": 0.8825316921943583, + "grad_norm": 1.0748100579451487, + "learning_rate": 7.147315605318661e-07, + "loss": 0.7451, + "step": 14376 + }, + { + "epoch": 0.8825930814328248, + "grad_norm": 1.17829962627647, + "learning_rate": 7.139935388683949e-07, + "loss": 0.7474, + "step": 14377 + }, + { + "epoch": 0.8826544706712913, + "grad_norm": 1.0223315998378084, + "learning_rate": 7.132558843304238e-07, + "loss": 0.7502, + "step": 14378 + }, + { + "epoch": 0.8827158599097579, + "grad_norm": 1.0068425575966569, + "learning_rate": 7.12518596947116e-07, + "loss": 0.7714, + "step": 14379 + }, + { + "epoch": 0.8827772491482243, + "grad_norm": 1.0762000152123732, + "learning_rate": 7.117816767476216e-07, + "loss": 0.7299, + "step": 14380 + }, + { + "epoch": 0.8828386383866909, + "grad_norm": 1.1007292228075822, + "learning_rate": 7.110451237610749e-07, + "loss": 0.762, + "step": 14381 + }, + { + "epoch": 0.8829000276251573, + "grad_norm": 1.09168141089109, + "learning_rate": 7.103089380165939e-07, + "loss": 0.7238, + "step": 14382 + }, + { + "epoch": 0.8829614168636238, + "grad_norm": 1.0639973231868967, + "learning_rate": 7.095731195432865e-07, + "loss": 0.7304, + "step": 14383 + }, + { + "epoch": 0.8830228061020903, + "grad_norm": 1.0330182361340174, + "learning_rate": 7.088376683702403e-07, + "loss": 0.7115, + "step": 14384 + }, + { + "epoch": 0.8830841953405568, + "grad_norm": 1.0578779285945514, + "learning_rate": 7.081025845265355e-07, + "loss": 0.7196, + "step": 14385 + }, + { + "epoch": 0.8831455845790233, + "grad_norm": 0.9302789722594589, + "learning_rate": 7.073678680412333e-07, + "loss": 0.7769, + "step": 14386 + }, + { + "epoch": 0.8832069738174898, + "grad_norm": 0.9955172262669383, + "learning_rate": 7.066335189433771e-07, + "loss": 0.7313, + "step": 14387 + }, + { + "epoch": 0.8832683630559562, + "grad_norm": 0.9831840323438714, + "learning_rate": 7.058995372620037e-07, + "loss": 0.6758, + "step": 14388 + }, + { + "epoch": 0.8833297522944228, + "grad_norm": 1.0084486779260453, + "learning_rate": 7.051659230261299e-07, + "loss": 0.7756, + "step": 14389 + }, + { + "epoch": 0.8833911415328893, + "grad_norm": 1.0741621202358336, + "learning_rate": 7.044326762647591e-07, + "loss": 0.7294, + "step": 14390 + }, + { + "epoch": 0.8834525307713558, + "grad_norm": 1.0753836616577739, + "learning_rate": 7.036997970068815e-07, + "loss": 0.7436, + "step": 14391 + }, + { + "epoch": 0.8835139200098223, + "grad_norm": 0.9997859996550849, + "learning_rate": 7.029672852814706e-07, + "loss": 0.729, + "step": 14392 + }, + { + "epoch": 0.8835753092482888, + "grad_norm": 1.0126526635009614, + "learning_rate": 7.022351411174866e-07, + "loss": 0.7195, + "step": 14393 + }, + { + "epoch": 0.8836366984867553, + "grad_norm": 1.0003160226186976, + "learning_rate": 7.015033645438763e-07, + "loss": 0.7639, + "step": 14394 + }, + { + "epoch": 0.8836980877252217, + "grad_norm": 1.0857990344722654, + "learning_rate": 7.007719555895676e-07, + "loss": 0.7399, + "step": 14395 + }, + { + "epoch": 0.8837594769636883, + "grad_norm": 0.9664803233052685, + "learning_rate": 7.000409142834819e-07, + "loss": 0.7228, + "step": 14396 + }, + { + "epoch": 0.8838208662021547, + "grad_norm": 1.0802031641375496, + "learning_rate": 6.993102406545182e-07, + "loss": 0.7262, + "step": 14397 + }, + { + "epoch": 0.8838822554406213, + "grad_norm": 0.9785996860161005, + "learning_rate": 6.985799347315625e-07, + "loss": 0.705, + "step": 14398 + }, + { + "epoch": 0.8839436446790877, + "grad_norm": 1.0721254706189438, + "learning_rate": 6.978499965434904e-07, + "loss": 0.7019, + "step": 14399 + }, + { + "epoch": 0.8840050339175543, + "grad_norm": 1.0643686719329626, + "learning_rate": 6.9712042611916e-07, + "loss": 0.7164, + "step": 14400 + }, + { + "epoch": 0.8840664231560208, + "grad_norm": 1.0759015043637548, + "learning_rate": 6.963912234874137e-07, + "loss": 0.724, + "step": 14401 + }, + { + "epoch": 0.8841278123944872, + "grad_norm": 0.9497219661358405, + "learning_rate": 6.956623886770819e-07, + "loss": 0.7148, + "step": 14402 + }, + { + "epoch": 0.8841892016329538, + "grad_norm": 1.010711720868488, + "learning_rate": 6.949339217169792e-07, + "loss": 0.7257, + "step": 14403 + }, + { + "epoch": 0.8842505908714202, + "grad_norm": 1.0384435959505418, + "learning_rate": 6.94205822635905e-07, + "loss": 0.7071, + "step": 14404 + }, + { + "epoch": 0.8843119801098868, + "grad_norm": 0.9694592811157526, + "learning_rate": 6.934780914626437e-07, + "loss": 0.7427, + "step": 14405 + }, + { + "epoch": 0.8843733693483532, + "grad_norm": 1.0616551259547484, + "learning_rate": 6.927507282259727e-07, + "loss": 0.7604, + "step": 14406 + }, + { + "epoch": 0.8844347585868197, + "grad_norm": 1.0569397598428985, + "learning_rate": 6.920237329546419e-07, + "loss": 0.7508, + "step": 14407 + }, + { + "epoch": 0.8844961478252862, + "grad_norm": 0.9941625991603673, + "learning_rate": 6.912971056773954e-07, + "loss": 0.7284, + "step": 14408 + }, + { + "epoch": 0.8845575370637527, + "grad_norm": 1.1712082046857644, + "learning_rate": 6.905708464229588e-07, + "loss": 0.7364, + "step": 14409 + }, + { + "epoch": 0.8846189263022192, + "grad_norm": 1.0534615539379606, + "learning_rate": 6.898449552200493e-07, + "loss": 0.7348, + "step": 14410 + }, + { + "epoch": 0.8846803155406857, + "grad_norm": 1.0031590669030692, + "learning_rate": 6.891194320973638e-07, + "loss": 0.7416, + "step": 14411 + }, + { + "epoch": 0.8847417047791523, + "grad_norm": 1.1033481933255016, + "learning_rate": 6.883942770835827e-07, + "loss": 0.716, + "step": 14412 + }, + { + "epoch": 0.8848030940176187, + "grad_norm": 1.031719864007191, + "learning_rate": 6.876694902073788e-07, + "loss": 0.7122, + "step": 14413 + }, + { + "epoch": 0.8848644832560852, + "grad_norm": 1.1469792607887044, + "learning_rate": 6.869450714974058e-07, + "loss": 0.6726, + "step": 14414 + }, + { + "epoch": 0.8849258724945517, + "grad_norm": 1.0921929831071786, + "learning_rate": 6.862210209823039e-07, + "loss": 0.7731, + "step": 14415 + }, + { + "epoch": 0.8849872617330182, + "grad_norm": 1.0187613630240704, + "learning_rate": 6.854973386906994e-07, + "loss": 0.7443, + "step": 14416 + }, + { + "epoch": 0.8850486509714847, + "grad_norm": 1.1491353648225178, + "learning_rate": 6.847740246512014e-07, + "loss": 0.7319, + "step": 14417 + }, + { + "epoch": 0.8851100402099512, + "grad_norm": 1.1178395426659102, + "learning_rate": 6.840510788924082e-07, + "loss": 0.7629, + "step": 14418 + }, + { + "epoch": 0.8851714294484176, + "grad_norm": 1.038332001982971, + "learning_rate": 6.833285014429014e-07, + "loss": 0.74, + "step": 14419 + }, + { + "epoch": 0.8852328186868842, + "grad_norm": 1.1005381645436407, + "learning_rate": 6.82606292331247e-07, + "loss": 0.747, + "step": 14420 + }, + { + "epoch": 0.8852942079253507, + "grad_norm": 1.018923952641633, + "learning_rate": 6.818844515860002e-07, + "loss": 0.724, + "step": 14421 + }, + { + "epoch": 0.8853555971638172, + "grad_norm": 0.9869719905172243, + "learning_rate": 6.811629792356967e-07, + "loss": 0.6989, + "step": 14422 + }, + { + "epoch": 0.8854169864022837, + "grad_norm": 0.9658657733597172, + "learning_rate": 6.804418753088593e-07, + "loss": 0.7793, + "step": 14423 + }, + { + "epoch": 0.8854783756407502, + "grad_norm": 1.1236775554058434, + "learning_rate": 6.79721139834002e-07, + "loss": 0.7115, + "step": 14424 + }, + { + "epoch": 0.8855397648792167, + "grad_norm": 0.9738186155835691, + "learning_rate": 6.790007728396175e-07, + "loss": 0.7224, + "step": 14425 + }, + { + "epoch": 0.8856011541176831, + "grad_norm": 1.0253868654810565, + "learning_rate": 6.782807743541809e-07, + "loss": 0.7342, + "step": 14426 + }, + { + "epoch": 0.8856625433561497, + "grad_norm": 1.0265409781355577, + "learning_rate": 6.775611444061636e-07, + "loss": 0.6714, + "step": 14427 + }, + { + "epoch": 0.8857239325946161, + "grad_norm": 0.9743834611666528, + "learning_rate": 6.768418830240131e-07, + "loss": 0.7666, + "step": 14428 + }, + { + "epoch": 0.8857853218330827, + "grad_norm": 0.9597055929356042, + "learning_rate": 6.761229902361677e-07, + "loss": 0.7005, + "step": 14429 + }, + { + "epoch": 0.8858467110715491, + "grad_norm": 1.102207033503173, + "learning_rate": 6.754044660710479e-07, + "loss": 0.7708, + "step": 14430 + }, + { + "epoch": 0.8859081003100157, + "grad_norm": 1.0461210591806116, + "learning_rate": 6.746863105570611e-07, + "loss": 0.6923, + "step": 14431 + }, + { + "epoch": 0.8859694895484822, + "grad_norm": 1.0912051188416445, + "learning_rate": 6.739685237226001e-07, + "loss": 0.7836, + "step": 14432 + }, + { + "epoch": 0.8860308787869486, + "grad_norm": 1.0226765179975579, + "learning_rate": 6.732511055960412e-07, + "loss": 0.6773, + "step": 14433 + }, + { + "epoch": 0.8860922680254152, + "grad_norm": 0.9928521504890098, + "learning_rate": 6.725340562057492e-07, + "loss": 0.7415, + "step": 14434 + }, + { + "epoch": 0.8861536572638816, + "grad_norm": 0.8173666916942367, + "learning_rate": 6.718173755800749e-07, + "loss": 0.693, + "step": 14435 + }, + { + "epoch": 0.8862150465023482, + "grad_norm": 0.9181786219266731, + "learning_rate": 6.71101063747348e-07, + "loss": 0.7282, + "step": 14436 + }, + { + "epoch": 0.8862764357408146, + "grad_norm": 1.0281515971081074, + "learning_rate": 6.703851207358902e-07, + "loss": 0.7488, + "step": 14437 + }, + { + "epoch": 0.8863378249792812, + "grad_norm": 1.0383145871776978, + "learning_rate": 6.696695465740077e-07, + "loss": 0.77, + "step": 14438 + }, + { + "epoch": 0.8863992142177476, + "grad_norm": 1.1892191073419753, + "learning_rate": 6.689543412899913e-07, + "loss": 0.7403, + "step": 14439 + }, + { + "epoch": 0.8864606034562141, + "grad_norm": 1.0406268848516083, + "learning_rate": 6.682395049121149e-07, + "loss": 0.7662, + "step": 14440 + }, + { + "epoch": 0.8865219926946806, + "grad_norm": 1.0926023463103847, + "learning_rate": 6.675250374686404e-07, + "loss": 0.6849, + "step": 14441 + }, + { + "epoch": 0.8865833819331471, + "grad_norm": 1.0491899268881033, + "learning_rate": 6.668109389878152e-07, + "loss": 0.7228, + "step": 14442 + }, + { + "epoch": 0.8866447711716137, + "grad_norm": 0.9920595809687027, + "learning_rate": 6.660972094978702e-07, + "loss": 0.6888, + "step": 14443 + }, + { + "epoch": 0.8867061604100801, + "grad_norm": 1.1351565943102015, + "learning_rate": 6.653838490270237e-07, + "loss": 0.7739, + "step": 14444 + }, + { + "epoch": 0.8867675496485466, + "grad_norm": 1.0213706022422773, + "learning_rate": 6.6467085760348e-07, + "loss": 0.7218, + "step": 14445 + }, + { + "epoch": 0.8868289388870131, + "grad_norm": 1.0810202705192893, + "learning_rate": 6.639582352554263e-07, + "loss": 0.7175, + "step": 14446 + }, + { + "epoch": 0.8868903281254796, + "grad_norm": 1.1294797134608432, + "learning_rate": 6.632459820110348e-07, + "loss": 0.7328, + "step": 14447 + }, + { + "epoch": 0.8869517173639461, + "grad_norm": 1.041468927626315, + "learning_rate": 6.625340978984651e-07, + "loss": 0.722, + "step": 14448 + }, + { + "epoch": 0.8870131066024126, + "grad_norm": 0.9879536161862806, + "learning_rate": 6.618225829458647e-07, + "loss": 0.787, + "step": 14449 + }, + { + "epoch": 0.887074495840879, + "grad_norm": 1.0474851629853381, + "learning_rate": 6.611114371813632e-07, + "loss": 0.6826, + "step": 14450 + }, + { + "epoch": 0.8871358850793456, + "grad_norm": 1.1734771790839473, + "learning_rate": 6.604006606330704e-07, + "loss": 0.6817, + "step": 14451 + }, + { + "epoch": 0.887197274317812, + "grad_norm": 1.0773774294284761, + "learning_rate": 6.596902533290939e-07, + "loss": 0.6836, + "step": 14452 + }, + { + "epoch": 0.8872586635562786, + "grad_norm": 1.0570081237885514, + "learning_rate": 6.589802152975167e-07, + "loss": 0.7091, + "step": 14453 + }, + { + "epoch": 0.8873200527947451, + "grad_norm": 1.0349113936768763, + "learning_rate": 6.582705465664107e-07, + "loss": 0.7549, + "step": 14454 + }, + { + "epoch": 0.8873814420332116, + "grad_norm": 1.1831692911050222, + "learning_rate": 6.575612471638327e-07, + "loss": 0.7452, + "step": 14455 + }, + { + "epoch": 0.8874428312716781, + "grad_norm": 1.0606756660103729, + "learning_rate": 6.568523171178265e-07, + "loss": 0.7246, + "step": 14456 + }, + { + "epoch": 0.8875042205101445, + "grad_norm": 1.0611258339819267, + "learning_rate": 6.561437564564177e-07, + "loss": 0.6699, + "step": 14457 + }, + { + "epoch": 0.8875656097486111, + "grad_norm": 1.1414965339465237, + "learning_rate": 6.554355652076216e-07, + "loss": 0.7595, + "step": 14458 + }, + { + "epoch": 0.8876269989870775, + "grad_norm": 0.9270734575970551, + "learning_rate": 6.547277433994348e-07, + "loss": 0.7423, + "step": 14459 + }, + { + "epoch": 0.8876883882255441, + "grad_norm": 1.0908807423236693, + "learning_rate": 6.540202910598436e-07, + "loss": 0.6715, + "step": 14460 + }, + { + "epoch": 0.8877497774640105, + "grad_norm": 1.1048376532711992, + "learning_rate": 6.533132082168159e-07, + "loss": 0.6882, + "step": 14461 + }, + { + "epoch": 0.8878111667024771, + "grad_norm": 0.9349978469194982, + "learning_rate": 6.526064948983047e-07, + "loss": 0.7468, + "step": 14462 + }, + { + "epoch": 0.8878725559409435, + "grad_norm": 0.9188516385366832, + "learning_rate": 6.519001511322542e-07, + "loss": 0.7293, + "step": 14463 + }, + { + "epoch": 0.88793394517941, + "grad_norm": 0.9875641140020619, + "learning_rate": 6.51194176946588e-07, + "loss": 0.6949, + "step": 14464 + }, + { + "epoch": 0.8879953344178766, + "grad_norm": 1.1128443698683035, + "learning_rate": 6.504885723692156e-07, + "loss": 0.7065, + "step": 14465 + }, + { + "epoch": 0.888056723656343, + "grad_norm": 1.024222182401252, + "learning_rate": 6.49783337428036e-07, + "loss": 0.7211, + "step": 14466 + }, + { + "epoch": 0.8881181128948096, + "grad_norm": 1.0888744469069156, + "learning_rate": 6.490784721509291e-07, + "loss": 0.7405, + "step": 14467 + }, + { + "epoch": 0.888179502133276, + "grad_norm": 1.0706654380151595, + "learning_rate": 6.483739765657626e-07, + "loss": 0.7182, + "step": 14468 + }, + { + "epoch": 0.8882408913717426, + "grad_norm": 1.087765908780014, + "learning_rate": 6.476698507003864e-07, + "loss": 0.7074, + "step": 14469 + }, + { + "epoch": 0.888302280610209, + "grad_norm": 1.2025544693044026, + "learning_rate": 6.46966094582645e-07, + "loss": 0.7307, + "step": 14470 + }, + { + "epoch": 0.8883636698486755, + "grad_norm": 0.9925235770290917, + "learning_rate": 6.46262708240355e-07, + "loss": 0.7221, + "step": 14471 + }, + { + "epoch": 0.888425059087142, + "grad_norm": 1.0471935184308847, + "learning_rate": 6.455596917013274e-07, + "loss": 0.7368, + "step": 14472 + }, + { + "epoch": 0.8884864483256085, + "grad_norm": 1.0533876194888705, + "learning_rate": 6.448570449933555e-07, + "loss": 0.7198, + "step": 14473 + }, + { + "epoch": 0.8885478375640751, + "grad_norm": 1.0128608956163996, + "learning_rate": 6.441547681442206e-07, + "loss": 0.7692, + "step": 14474 + }, + { + "epoch": 0.8886092268025415, + "grad_norm": 1.0835658421415182, + "learning_rate": 6.434528611816881e-07, + "loss": 0.749, + "step": 14475 + }, + { + "epoch": 0.888670616041008, + "grad_norm": 0.9971241494354643, + "learning_rate": 6.427513241335026e-07, + "loss": 0.7493, + "step": 14476 + }, + { + "epoch": 0.8887320052794745, + "grad_norm": 1.0723475766506068, + "learning_rate": 6.420501570274051e-07, + "loss": 0.7364, + "step": 14477 + }, + { + "epoch": 0.888793394517941, + "grad_norm": 1.090337846335206, + "learning_rate": 6.413493598911147e-07, + "loss": 0.7342, + "step": 14478 + }, + { + "epoch": 0.8888547837564075, + "grad_norm": 0.9833866225216036, + "learning_rate": 6.406489327523379e-07, + "loss": 0.7534, + "step": 14479 + }, + { + "epoch": 0.888916172994874, + "grad_norm": 0.9769312691941595, + "learning_rate": 6.399488756387661e-07, + "loss": 0.7171, + "step": 14480 + }, + { + "epoch": 0.8889775622333405, + "grad_norm": 1.021196207215283, + "learning_rate": 6.392491885780772e-07, + "loss": 0.7539, + "step": 14481 + }, + { + "epoch": 0.889038951471807, + "grad_norm": 0.9986594718402159, + "learning_rate": 6.38549871597931e-07, + "loss": 0.7514, + "step": 14482 + }, + { + "epoch": 0.8891003407102734, + "grad_norm": 0.9864865877744531, + "learning_rate": 6.378509247259767e-07, + "loss": 0.7936, + "step": 14483 + }, + { + "epoch": 0.88916172994874, + "grad_norm": 1.0491117488805264, + "learning_rate": 6.371523479898501e-07, + "loss": 0.7259, + "step": 14484 + }, + { + "epoch": 0.8892231191872065, + "grad_norm": 0.6002341159938658, + "learning_rate": 6.364541414171655e-07, + "loss": 0.634, + "step": 14485 + }, + { + "epoch": 0.889284508425673, + "grad_norm": 1.0512789620382683, + "learning_rate": 6.357563050355287e-07, + "loss": 0.7044, + "step": 14486 + }, + { + "epoch": 0.8893458976641395, + "grad_norm": 1.142135725218729, + "learning_rate": 6.350588388725276e-07, + "loss": 0.7396, + "step": 14487 + }, + { + "epoch": 0.889407286902606, + "grad_norm": 1.0359157653230522, + "learning_rate": 6.343617429557392e-07, + "loss": 0.7346, + "step": 14488 + }, + { + "epoch": 0.8894686761410725, + "grad_norm": 1.107809940557569, + "learning_rate": 6.336650173127224e-07, + "loss": 0.7223, + "step": 14489 + }, + { + "epoch": 0.8895300653795389, + "grad_norm": 1.083373428428231, + "learning_rate": 6.329686619710207e-07, + "loss": 0.7514, + "step": 14490 + }, + { + "epoch": 0.8895914546180055, + "grad_norm": 1.0681509614969802, + "learning_rate": 6.322726769581666e-07, + "loss": 0.7573, + "step": 14491 + }, + { + "epoch": 0.8896528438564719, + "grad_norm": 0.9964253511344334, + "learning_rate": 6.315770623016759e-07, + "loss": 0.743, + "step": 14492 + }, + { + "epoch": 0.8897142330949385, + "grad_norm": 1.0385627101575683, + "learning_rate": 6.308818180290499e-07, + "loss": 0.7547, + "step": 14493 + }, + { + "epoch": 0.8897756223334049, + "grad_norm": 1.0221794563713282, + "learning_rate": 6.301869441677755e-07, + "loss": 0.6812, + "step": 14494 + }, + { + "epoch": 0.8898370115718715, + "grad_norm": 0.9328972024863216, + "learning_rate": 6.294924407453241e-07, + "loss": 0.7336, + "step": 14495 + }, + { + "epoch": 0.889898400810338, + "grad_norm": 1.024769384317232, + "learning_rate": 6.287983077891547e-07, + "loss": 0.7516, + "step": 14496 + }, + { + "epoch": 0.8899597900488044, + "grad_norm": 1.0472251652378513, + "learning_rate": 6.281045453267076e-07, + "loss": 0.7183, + "step": 14497 + }, + { + "epoch": 0.890021179287271, + "grad_norm": 1.0940095582651337, + "learning_rate": 6.27411153385411e-07, + "loss": 0.6787, + "step": 14498 + }, + { + "epoch": 0.8900825685257374, + "grad_norm": 1.0576514107452597, + "learning_rate": 6.267181319926818e-07, + "loss": 0.7309, + "step": 14499 + }, + { + "epoch": 0.890143957764204, + "grad_norm": 0.9432802260155785, + "learning_rate": 6.26025481175917e-07, + "loss": 0.7035, + "step": 14500 + }, + { + "epoch": 0.8902053470026704, + "grad_norm": 1.1214972007824104, + "learning_rate": 6.25333200962498e-07, + "loss": 0.7412, + "step": 14501 + }, + { + "epoch": 0.890266736241137, + "grad_norm": 1.0772688369464298, + "learning_rate": 6.246412913797983e-07, + "loss": 0.7, + "step": 14502 + }, + { + "epoch": 0.8903281254796034, + "grad_norm": 1.0747629812607922, + "learning_rate": 6.239497524551708e-07, + "loss": 0.7153, + "step": 14503 + }, + { + "epoch": 0.8903895147180699, + "grad_norm": 1.07234230561666, + "learning_rate": 6.232585842159566e-07, + "loss": 0.7317, + "step": 14504 + }, + { + "epoch": 0.8904509039565364, + "grad_norm": 1.015621674010325, + "learning_rate": 6.225677866894808e-07, + "loss": 0.7603, + "step": 14505 + }, + { + "epoch": 0.8905122931950029, + "grad_norm": 0.9971529002079078, + "learning_rate": 6.218773599030547e-07, + "loss": 0.7153, + "step": 14506 + }, + { + "epoch": 0.8905736824334695, + "grad_norm": 1.1408440136421885, + "learning_rate": 6.211873038839745e-07, + "loss": 0.7098, + "step": 14507 + }, + { + "epoch": 0.8906350716719359, + "grad_norm": 1.0590367522818083, + "learning_rate": 6.204976186595201e-07, + "loss": 0.7568, + "step": 14508 + }, + { + "epoch": 0.8906964609104024, + "grad_norm": 1.0004683499719993, + "learning_rate": 6.198083042569625e-07, + "loss": 0.7087, + "step": 14509 + }, + { + "epoch": 0.8907578501488689, + "grad_norm": 1.0565277877092834, + "learning_rate": 6.191193607035506e-07, + "loss": 0.7843, + "step": 14510 + }, + { + "epoch": 0.8908192393873354, + "grad_norm": 1.0817688616850685, + "learning_rate": 6.184307880265217e-07, + "loss": 0.6811, + "step": 14511 + }, + { + "epoch": 0.8908806286258019, + "grad_norm": 0.9735749092182173, + "learning_rate": 6.177425862530995e-07, + "loss": 0.6983, + "step": 14512 + }, + { + "epoch": 0.8909420178642684, + "grad_norm": 0.9464862564634449, + "learning_rate": 6.170547554104933e-07, + "loss": 0.7294, + "step": 14513 + }, + { + "epoch": 0.8910034071027348, + "grad_norm": 1.0158096107164374, + "learning_rate": 6.163672955258982e-07, + "loss": 0.7495, + "step": 14514 + }, + { + "epoch": 0.8910647963412014, + "grad_norm": 0.9040222358426145, + "learning_rate": 6.156802066264888e-07, + "loss": 0.7389, + "step": 14515 + }, + { + "epoch": 0.8911261855796678, + "grad_norm": 1.2183658454003972, + "learning_rate": 6.149934887394315e-07, + "loss": 0.7616, + "step": 14516 + }, + { + "epoch": 0.8911875748181344, + "grad_norm": 1.2566869263265683, + "learning_rate": 6.143071418918778e-07, + "loss": 0.725, + "step": 14517 + }, + { + "epoch": 0.8912489640566009, + "grad_norm": 1.0550337326666792, + "learning_rate": 6.136211661109603e-07, + "loss": 0.7203, + "step": 14518 + }, + { + "epoch": 0.8913103532950674, + "grad_norm": 0.9585602047863085, + "learning_rate": 6.129355614237997e-07, + "loss": 0.6778, + "step": 14519 + }, + { + "epoch": 0.8913717425335339, + "grad_norm": 1.037977977964986, + "learning_rate": 6.12250327857502e-07, + "loss": 0.7415, + "step": 14520 + }, + { + "epoch": 0.8914331317720003, + "grad_norm": 1.0934037406270327, + "learning_rate": 6.115654654391579e-07, + "loss": 0.711, + "step": 14521 + }, + { + "epoch": 0.8914945210104669, + "grad_norm": 1.011251734156968, + "learning_rate": 6.108809741958433e-07, + "loss": 0.7141, + "step": 14522 + }, + { + "epoch": 0.8915559102489333, + "grad_norm": 1.0115746028665613, + "learning_rate": 6.10196854154621e-07, + "loss": 0.7082, + "step": 14523 + }, + { + "epoch": 0.8916172994873999, + "grad_norm": 1.1028503860386387, + "learning_rate": 6.095131053425385e-07, + "loss": 0.7484, + "step": 14524 + }, + { + "epoch": 0.8916786887258663, + "grad_norm": 0.999967365160849, + "learning_rate": 6.088297277866262e-07, + "loss": 0.7469, + "step": 14525 + }, + { + "epoch": 0.8917400779643329, + "grad_norm": 1.013503001425205, + "learning_rate": 6.081467215139003e-07, + "loss": 0.732, + "step": 14526 + }, + { + "epoch": 0.8918014672027994, + "grad_norm": 1.0071713150960153, + "learning_rate": 6.074640865513671e-07, + "loss": 0.7569, + "step": 14527 + }, + { + "epoch": 0.8918628564412658, + "grad_norm": 0.994241654692686, + "learning_rate": 6.067818229260137e-07, + "loss": 0.6793, + "step": 14528 + }, + { + "epoch": 0.8919242456797324, + "grad_norm": 0.9895542582268343, + "learning_rate": 6.060999306648129e-07, + "loss": 0.6973, + "step": 14529 + }, + { + "epoch": 0.8919856349181988, + "grad_norm": 1.0288595672966905, + "learning_rate": 6.054184097947235e-07, + "loss": 0.7152, + "step": 14530 + }, + { + "epoch": 0.8920470241566654, + "grad_norm": 1.0716750132743427, + "learning_rate": 6.047372603426915e-07, + "loss": 0.7068, + "step": 14531 + }, + { + "epoch": 0.8921084133951318, + "grad_norm": 1.1130181916871995, + "learning_rate": 6.040564823356432e-07, + "loss": 0.7817, + "step": 14532 + }, + { + "epoch": 0.8921698026335984, + "grad_norm": 1.0898031341270418, + "learning_rate": 6.033760758004948e-07, + "loss": 0.7608, + "step": 14533 + }, + { + "epoch": 0.8922311918720648, + "grad_norm": 1.035895908626553, + "learning_rate": 6.026960407641502e-07, + "loss": 0.7175, + "step": 14534 + }, + { + "epoch": 0.8922925811105313, + "grad_norm": 1.1002361389106003, + "learning_rate": 6.020163772534892e-07, + "loss": 0.7297, + "step": 14535 + }, + { + "epoch": 0.8923539703489978, + "grad_norm": 1.0417587398737556, + "learning_rate": 6.013370852953848e-07, + "loss": 0.6731, + "step": 14536 + }, + { + "epoch": 0.8924153595874643, + "grad_norm": 0.9618228709866203, + "learning_rate": 6.006581649166921e-07, + "loss": 0.6765, + "step": 14537 + }, + { + "epoch": 0.8924767488259309, + "grad_norm": 1.0079945217522566, + "learning_rate": 5.999796161442539e-07, + "loss": 0.7779, + "step": 14538 + }, + { + "epoch": 0.8925381380643973, + "grad_norm": 1.0043828930664345, + "learning_rate": 5.99301439004899e-07, + "loss": 0.7402, + "step": 14539 + }, + { + "epoch": 0.8925995273028638, + "grad_norm": 1.0594607865047143, + "learning_rate": 5.986236335254325e-07, + "loss": 0.697, + "step": 14540 + }, + { + "epoch": 0.8926609165413303, + "grad_norm": 1.175663409445028, + "learning_rate": 5.979461997326575e-07, + "loss": 0.7254, + "step": 14541 + }, + { + "epoch": 0.8927223057797968, + "grad_norm": 1.145547708567117, + "learning_rate": 5.972691376533557e-07, + "loss": 0.7116, + "step": 14542 + }, + { + "epoch": 0.8927836950182633, + "grad_norm": 1.1545013387614287, + "learning_rate": 5.965924473142936e-07, + "loss": 0.7092, + "step": 14543 + }, + { + "epoch": 0.8928450842567298, + "grad_norm": 1.0995503766481185, + "learning_rate": 5.959161287422255e-07, + "loss": 0.721, + "step": 14544 + }, + { + "epoch": 0.8929064734951963, + "grad_norm": 1.0061442033339232, + "learning_rate": 5.952401819638887e-07, + "loss": 0.7129, + "step": 14545 + }, + { + "epoch": 0.8929678627336628, + "grad_norm": 1.095398914710489, + "learning_rate": 5.945646070060085e-07, + "loss": 0.6988, + "step": 14546 + }, + { + "epoch": 0.8930292519721292, + "grad_norm": 0.9967067112627901, + "learning_rate": 5.938894038952914e-07, + "loss": 0.739, + "step": 14547 + }, + { + "epoch": 0.8930906412105958, + "grad_norm": 1.0920791419699456, + "learning_rate": 5.932145726584371e-07, + "loss": 0.7089, + "step": 14548 + }, + { + "epoch": 0.8931520304490623, + "grad_norm": 1.1577266181964552, + "learning_rate": 5.925401133221198e-07, + "loss": 0.7719, + "step": 14549 + }, + { + "epoch": 0.8932134196875288, + "grad_norm": 0.9986034108986359, + "learning_rate": 5.91866025913006e-07, + "loss": 0.7551, + "step": 14550 + }, + { + "epoch": 0.8932748089259953, + "grad_norm": 1.1074998465666857, + "learning_rate": 5.911923104577455e-07, + "loss": 0.7464, + "step": 14551 + }, + { + "epoch": 0.8933361981644617, + "grad_norm": 1.0119989632695214, + "learning_rate": 5.905189669829759e-07, + "loss": 0.7301, + "step": 14552 + }, + { + "epoch": 0.8933975874029283, + "grad_norm": 1.1261952594648705, + "learning_rate": 5.898459955153179e-07, + "loss": 0.7406, + "step": 14553 + }, + { + "epoch": 0.8934589766413947, + "grad_norm": 1.0443822436142172, + "learning_rate": 5.89173396081375e-07, + "loss": 0.6946, + "step": 14554 + }, + { + "epoch": 0.8935203658798613, + "grad_norm": 1.1004250153971589, + "learning_rate": 5.885011687077413e-07, + "loss": 0.7692, + "step": 14555 + }, + { + "epoch": 0.8935817551183277, + "grad_norm": 0.9389559952397288, + "learning_rate": 5.878293134209934e-07, + "loss": 0.7169, + "step": 14556 + }, + { + "epoch": 0.8936431443567943, + "grad_norm": 1.0518746162375474, + "learning_rate": 5.871578302476911e-07, + "loss": 0.6935, + "step": 14557 + }, + { + "epoch": 0.8937045335952607, + "grad_norm": 0.987053495579959, + "learning_rate": 5.864867192143842e-07, + "loss": 0.7121, + "step": 14558 + }, + { + "epoch": 0.8937659228337272, + "grad_norm": 0.5921589584782895, + "learning_rate": 5.858159803476038e-07, + "loss": 0.6716, + "step": 14559 + }, + { + "epoch": 0.8938273120721938, + "grad_norm": 1.120456807143552, + "learning_rate": 5.851456136738687e-07, + "loss": 0.719, + "step": 14560 + }, + { + "epoch": 0.8938887013106602, + "grad_norm": 1.0851988225022462, + "learning_rate": 5.844756192196798e-07, + "loss": 0.7101, + "step": 14561 + }, + { + "epoch": 0.8939500905491268, + "grad_norm": 0.956071244047562, + "learning_rate": 5.838059970115295e-07, + "loss": 0.7402, + "step": 14562 + }, + { + "epoch": 0.8940114797875932, + "grad_norm": 1.043550635603458, + "learning_rate": 5.831367470758908e-07, + "loss": 0.702, + "step": 14563 + }, + { + "epoch": 0.8940728690260598, + "grad_norm": 1.0477790595129193, + "learning_rate": 5.824678694392194e-07, + "loss": 0.6822, + "step": 14564 + }, + { + "epoch": 0.8941342582645262, + "grad_norm": 1.1238202974858214, + "learning_rate": 5.817993641279606e-07, + "loss": 0.6879, + "step": 14565 + }, + { + "epoch": 0.8941956475029927, + "grad_norm": 1.027480300724948, + "learning_rate": 5.811312311685469e-07, + "loss": 0.7342, + "step": 14566 + }, + { + "epoch": 0.8942570367414592, + "grad_norm": 1.111236666084227, + "learning_rate": 5.804634705873912e-07, + "loss": 0.7099, + "step": 14567 + }, + { + "epoch": 0.8943184259799257, + "grad_norm": 1.0776975534977875, + "learning_rate": 5.797960824108928e-07, + "loss": 0.7226, + "step": 14568 + }, + { + "epoch": 0.8943798152183923, + "grad_norm": 1.0226665496536669, + "learning_rate": 5.791290666654392e-07, + "loss": 0.7141, + "step": 14569 + }, + { + "epoch": 0.8944412044568587, + "grad_norm": 1.0136888563141597, + "learning_rate": 5.784624233773983e-07, + "loss": 0.705, + "step": 14570 + }, + { + "epoch": 0.8945025936953253, + "grad_norm": 0.9980560885863156, + "learning_rate": 5.777961525731291e-07, + "loss": 0.7251, + "step": 14571 + }, + { + "epoch": 0.8945639829337917, + "grad_norm": 1.0287077006965786, + "learning_rate": 5.771302542789703e-07, + "loss": 0.7292, + "step": 14572 + }, + { + "epoch": 0.8946253721722582, + "grad_norm": 0.9197143755193719, + "learning_rate": 5.76464728521251e-07, + "loss": 0.6872, + "step": 14573 + }, + { + "epoch": 0.8946867614107247, + "grad_norm": 1.0174441250476687, + "learning_rate": 5.757995753262813e-07, + "loss": 0.7081, + "step": 14574 + }, + { + "epoch": 0.8947481506491912, + "grad_norm": 1.1168484016745488, + "learning_rate": 5.75134794720359e-07, + "loss": 0.7604, + "step": 14575 + }, + { + "epoch": 0.8948095398876577, + "grad_norm": 1.1135603081521304, + "learning_rate": 5.744703867297629e-07, + "loss": 0.7379, + "step": 14576 + }, + { + "epoch": 0.8948709291261242, + "grad_norm": 1.024483141283961, + "learning_rate": 5.738063513807668e-07, + "loss": 0.7069, + "step": 14577 + }, + { + "epoch": 0.8949323183645906, + "grad_norm": 0.9846087290174073, + "learning_rate": 5.731426886996205e-07, + "loss": 0.6911, + "step": 14578 + }, + { + "epoch": 0.8949937076030572, + "grad_norm": 1.0516846913839237, + "learning_rate": 5.724793987125598e-07, + "loss": 0.7722, + "step": 14579 + }, + { + "epoch": 0.8950550968415237, + "grad_norm": 1.0225133748817319, + "learning_rate": 5.718164814458128e-07, + "loss": 0.7062, + "step": 14580 + }, + { + "epoch": 0.8951164860799902, + "grad_norm": 1.0672340201735153, + "learning_rate": 5.711539369255848e-07, + "loss": 0.7296, + "step": 14581 + }, + { + "epoch": 0.8951778753184567, + "grad_norm": 1.0664101407955153, + "learning_rate": 5.704917651780705e-07, + "loss": 0.7894, + "step": 14582 + }, + { + "epoch": 0.8952392645569232, + "grad_norm": 1.1039273410596748, + "learning_rate": 5.698299662294493e-07, + "loss": 0.7342, + "step": 14583 + }, + { + "epoch": 0.8953006537953897, + "grad_norm": 1.020187266577602, + "learning_rate": 5.691685401058855e-07, + "loss": 0.7619, + "step": 14584 + }, + { + "epoch": 0.8953620430338561, + "grad_norm": 1.0380979246348716, + "learning_rate": 5.685074868335294e-07, + "loss": 0.7029, + "step": 14585 + }, + { + "epoch": 0.8954234322723227, + "grad_norm": 1.0783832210092932, + "learning_rate": 5.678468064385145e-07, + "loss": 0.7143, + "step": 14586 + }, + { + "epoch": 0.8954848215107891, + "grad_norm": 1.0316452141200432, + "learning_rate": 5.671864989469633e-07, + "loss": 0.7558, + "step": 14587 + }, + { + "epoch": 0.8955462107492557, + "grad_norm": 1.000921256261718, + "learning_rate": 5.665265643849804e-07, + "loss": 0.733, + "step": 14588 + }, + { + "epoch": 0.8956075999877221, + "grad_norm": 1.17578773243338, + "learning_rate": 5.658670027786561e-07, + "loss": 0.7412, + "step": 14589 + }, + { + "epoch": 0.8956689892261886, + "grad_norm": 1.1718305649306384, + "learning_rate": 5.65207814154064e-07, + "loss": 0.7597, + "step": 14590 + }, + { + "epoch": 0.8957303784646552, + "grad_norm": 1.1355326454521306, + "learning_rate": 5.645489985372698e-07, + "loss": 0.7434, + "step": 14591 + }, + { + "epoch": 0.8957917677031216, + "grad_norm": 1.0138579492285023, + "learning_rate": 5.638905559543174e-07, + "loss": 0.7353, + "step": 14592 + }, + { + "epoch": 0.8958531569415882, + "grad_norm": 1.0184815727611243, + "learning_rate": 5.6323248643124e-07, + "loss": 0.6979, + "step": 14593 + }, + { + "epoch": 0.8959145461800546, + "grad_norm": 1.0912380129977843, + "learning_rate": 5.625747899940537e-07, + "loss": 0.749, + "step": 14594 + }, + { + "epoch": 0.8959759354185212, + "grad_norm": 1.106307358703209, + "learning_rate": 5.61917466668761e-07, + "loss": 0.7241, + "step": 14595 + }, + { + "epoch": 0.8960373246569876, + "grad_norm": 0.9830243734505285, + "learning_rate": 5.612605164813478e-07, + "loss": 0.6914, + "step": 14596 + }, + { + "epoch": 0.8960987138954541, + "grad_norm": 1.0494285299501689, + "learning_rate": 5.606039394577889e-07, + "loss": 0.7188, + "step": 14597 + }, + { + "epoch": 0.8961601031339206, + "grad_norm": 1.096471811475145, + "learning_rate": 5.599477356240434e-07, + "loss": 0.7727, + "step": 14598 + }, + { + "epoch": 0.8962214923723871, + "grad_norm": 0.9602070617059935, + "learning_rate": 5.592919050060519e-07, + "loss": 0.7603, + "step": 14599 + }, + { + "epoch": 0.8962828816108536, + "grad_norm": 1.1965130910975013, + "learning_rate": 5.586364476297435e-07, + "loss": 0.743, + "step": 14600 + }, + { + "epoch": 0.8963442708493201, + "grad_norm": 1.1359631300252253, + "learning_rate": 5.579813635210308e-07, + "loss": 0.7107, + "step": 14601 + }, + { + "epoch": 0.8964056600877867, + "grad_norm": 0.9243060172028728, + "learning_rate": 5.573266527058153e-07, + "loss": 0.6933, + "step": 14602 + }, + { + "epoch": 0.8964670493262531, + "grad_norm": 0.9735240722552719, + "learning_rate": 5.566723152099829e-07, + "loss": 0.6726, + "step": 14603 + }, + { + "epoch": 0.8965284385647196, + "grad_norm": 1.0486342881883206, + "learning_rate": 5.560183510593964e-07, + "loss": 0.7417, + "step": 14604 + }, + { + "epoch": 0.8965898278031861, + "grad_norm": 1.2174474190577267, + "learning_rate": 5.553647602799162e-07, + "loss": 0.7714, + "step": 14605 + }, + { + "epoch": 0.8966512170416526, + "grad_norm": 1.0460374768697285, + "learning_rate": 5.547115428973804e-07, + "loss": 0.6898, + "step": 14606 + }, + { + "epoch": 0.8967126062801191, + "grad_norm": 1.0195951239266137, + "learning_rate": 5.54058698937614e-07, + "loss": 0.7747, + "step": 14607 + }, + { + "epoch": 0.8967739955185856, + "grad_norm": 1.1173941241556753, + "learning_rate": 5.534062284264286e-07, + "loss": 0.7164, + "step": 14608 + }, + { + "epoch": 0.896835384757052, + "grad_norm": 1.1373121864641693, + "learning_rate": 5.527541313896179e-07, + "loss": 0.7681, + "step": 14609 + }, + { + "epoch": 0.8968967739955186, + "grad_norm": 1.063298068708494, + "learning_rate": 5.521024078529646e-07, + "loss": 0.6926, + "step": 14610 + }, + { + "epoch": 0.896958163233985, + "grad_norm": 0.9408601646489317, + "learning_rate": 5.514510578422328e-07, + "loss": 0.7742, + "step": 14611 + }, + { + "epoch": 0.8970195524724516, + "grad_norm": 0.9522094238387051, + "learning_rate": 5.508000813831771e-07, + "loss": 0.7638, + "step": 14612 + }, + { + "epoch": 0.8970809417109181, + "grad_norm": 1.098487841365323, + "learning_rate": 5.501494785015305e-07, + "loss": 0.7421, + "step": 14613 + }, + { + "epoch": 0.8971423309493846, + "grad_norm": 1.0659448413179244, + "learning_rate": 5.494992492230167e-07, + "loss": 0.7589, + "step": 14614 + }, + { + "epoch": 0.8972037201878511, + "grad_norm": 1.0024063474618976, + "learning_rate": 5.488493935733418e-07, + "loss": 0.7164, + "step": 14615 + }, + { + "epoch": 0.8972651094263175, + "grad_norm": 1.1062548065922373, + "learning_rate": 5.481999115781989e-07, + "loss": 0.7263, + "step": 14616 + }, + { + "epoch": 0.8973264986647841, + "grad_norm": 1.073818755068626, + "learning_rate": 5.475508032632671e-07, + "loss": 0.7071, + "step": 14617 + }, + { + "epoch": 0.8973878879032505, + "grad_norm": 1.1108089594410415, + "learning_rate": 5.469020686542048e-07, + "loss": 0.7745, + "step": 14618 + }, + { + "epoch": 0.8974492771417171, + "grad_norm": 0.9973093715230462, + "learning_rate": 5.462537077766638e-07, + "loss": 0.7513, + "step": 14619 + }, + { + "epoch": 0.8975106663801835, + "grad_norm": 1.012838977295746, + "learning_rate": 5.45605720656276e-07, + "loss": 0.7165, + "step": 14620 + }, + { + "epoch": 0.89757205561865, + "grad_norm": 1.0097329324527817, + "learning_rate": 5.449581073186593e-07, + "loss": 0.6597, + "step": 14621 + }, + { + "epoch": 0.8976334448571166, + "grad_norm": 0.9972426614883554, + "learning_rate": 5.443108677894182e-07, + "loss": 0.7313, + "step": 14622 + }, + { + "epoch": 0.897694834095583, + "grad_norm": 1.0332830248057483, + "learning_rate": 5.436640020941409e-07, + "loss": 0.7204, + "step": 14623 + }, + { + "epoch": 0.8977562233340496, + "grad_norm": 1.0747018200090352, + "learning_rate": 5.430175102584012e-07, + "loss": 0.7079, + "step": 14624 + }, + { + "epoch": 0.897817612572516, + "grad_norm": 1.1160361051347611, + "learning_rate": 5.423713923077579e-07, + "loss": 0.6852, + "step": 14625 + }, + { + "epoch": 0.8978790018109826, + "grad_norm": 1.0399936020779728, + "learning_rate": 5.417256482677569e-07, + "loss": 0.6997, + "step": 14626 + }, + { + "epoch": 0.897940391049449, + "grad_norm": 0.9909194161070084, + "learning_rate": 5.410802781639301e-07, + "loss": 0.7232, + "step": 14627 + }, + { + "epoch": 0.8980017802879156, + "grad_norm": 0.5840227023093137, + "learning_rate": 5.404352820217873e-07, + "loss": 0.6643, + "step": 14628 + }, + { + "epoch": 0.898063169526382, + "grad_norm": 1.0650965865887496, + "learning_rate": 5.397906598668301e-07, + "loss": 0.7148, + "step": 14629 + }, + { + "epoch": 0.8981245587648485, + "grad_norm": 0.976348583216926, + "learning_rate": 5.391464117245471e-07, + "loss": 0.6892, + "step": 14630 + }, + { + "epoch": 0.898185948003315, + "grad_norm": 1.077169151775273, + "learning_rate": 5.385025376204056e-07, + "loss": 0.7004, + "step": 14631 + }, + { + "epoch": 0.8982473372417815, + "grad_norm": 1.037512443507994, + "learning_rate": 5.378590375798631e-07, + "loss": 0.7238, + "step": 14632 + }, + { + "epoch": 0.8983087264802481, + "grad_norm": 1.0139553002367945, + "learning_rate": 5.372159116283592e-07, + "loss": 0.701, + "step": 14633 + }, + { + "epoch": 0.8983701157187145, + "grad_norm": 1.0789949343916472, + "learning_rate": 5.365731597913215e-07, + "loss": 0.7514, + "step": 14634 + }, + { + "epoch": 0.898431504957181, + "grad_norm": 0.9289209390482878, + "learning_rate": 5.359307820941606e-07, + "loss": 0.7242, + "step": 14635 + }, + { + "epoch": 0.8984928941956475, + "grad_norm": 1.138601114430521, + "learning_rate": 5.352887785622718e-07, + "loss": 0.7182, + "step": 14636 + }, + { + "epoch": 0.898554283434114, + "grad_norm": 1.0340574739244397, + "learning_rate": 5.346471492210415e-07, + "loss": 0.7665, + "step": 14637 + }, + { + "epoch": 0.8986156726725805, + "grad_norm": 1.0125953360742785, + "learning_rate": 5.340058940958315e-07, + "loss": 0.7281, + "step": 14638 + }, + { + "epoch": 0.898677061911047, + "grad_norm": 1.0547475563825768, + "learning_rate": 5.333650132119972e-07, + "loss": 0.7075, + "step": 14639 + }, + { + "epoch": 0.8987384511495135, + "grad_norm": 1.0097895483111463, + "learning_rate": 5.327245065948728e-07, + "loss": 0.7688, + "step": 14640 + }, + { + "epoch": 0.89879984038798, + "grad_norm": 1.1481071049322895, + "learning_rate": 5.320843742697846e-07, + "loss": 0.7298, + "step": 14641 + }, + { + "epoch": 0.8988612296264464, + "grad_norm": 1.1121935039591107, + "learning_rate": 5.314446162620413e-07, + "loss": 0.7315, + "step": 14642 + }, + { + "epoch": 0.898922618864913, + "grad_norm": 1.0160867971840029, + "learning_rate": 5.308052325969304e-07, + "loss": 0.7008, + "step": 14643 + }, + { + "epoch": 0.8989840081033795, + "grad_norm": 1.1253463401860744, + "learning_rate": 5.301662232997351e-07, + "loss": 0.7416, + "step": 14644 + }, + { + "epoch": 0.899045397341846, + "grad_norm": 1.0488836268214266, + "learning_rate": 5.295275883957163e-07, + "loss": 0.7748, + "step": 14645 + }, + { + "epoch": 0.8991067865803125, + "grad_norm": 1.026637941077403, + "learning_rate": 5.288893279101248e-07, + "loss": 0.7671, + "step": 14646 + }, + { + "epoch": 0.899168175818779, + "grad_norm": 1.011172905058589, + "learning_rate": 5.282514418681928e-07, + "loss": 0.7383, + "step": 14647 + }, + { + "epoch": 0.8992295650572455, + "grad_norm": 1.0718510116694209, + "learning_rate": 5.2761393029514e-07, + "loss": 0.7398, + "step": 14648 + }, + { + "epoch": 0.8992909542957119, + "grad_norm": 1.0537192377922049, + "learning_rate": 5.269767932161696e-07, + "loss": 0.7317, + "step": 14649 + }, + { + "epoch": 0.8993523435341785, + "grad_norm": 0.967473234038203, + "learning_rate": 5.263400306564714e-07, + "loss": 0.7165, + "step": 14650 + }, + { + "epoch": 0.8994137327726449, + "grad_norm": 1.1048557932883738, + "learning_rate": 5.25703642641221e-07, + "loss": 0.7528, + "step": 14651 + }, + { + "epoch": 0.8994751220111115, + "grad_norm": 1.0817765315377352, + "learning_rate": 5.250676291955792e-07, + "loss": 0.7402, + "step": 14652 + }, + { + "epoch": 0.8995365112495779, + "grad_norm": 1.0780935535814111, + "learning_rate": 5.244319903446893e-07, + "loss": 0.7111, + "step": 14653 + }, + { + "epoch": 0.8995979004880444, + "grad_norm": 1.0728663044844853, + "learning_rate": 5.23796726113679e-07, + "loss": 0.7209, + "step": 14654 + }, + { + "epoch": 0.899659289726511, + "grad_norm": 1.0416535210293654, + "learning_rate": 5.23161836527668e-07, + "loss": 0.7333, + "step": 14655 + }, + { + "epoch": 0.8997206789649774, + "grad_norm": 1.0349711548521348, + "learning_rate": 5.225273216117554e-07, + "loss": 0.7486, + "step": 14656 + }, + { + "epoch": 0.899782068203444, + "grad_norm": 1.0582032979059803, + "learning_rate": 5.218931813910278e-07, + "loss": 0.7627, + "step": 14657 + }, + { + "epoch": 0.8998434574419104, + "grad_norm": 0.9464078833261043, + "learning_rate": 5.212594158905548e-07, + "loss": 0.7144, + "step": 14658 + }, + { + "epoch": 0.899904846680377, + "grad_norm": 1.1178542610312832, + "learning_rate": 5.206260251353923e-07, + "loss": 0.6894, + "step": 14659 + }, + { + "epoch": 0.8999662359188434, + "grad_norm": 1.055841918568973, + "learning_rate": 5.199930091505823e-07, + "loss": 0.7889, + "step": 14660 + }, + { + "epoch": 0.9000276251573099, + "grad_norm": 1.0663267408706345, + "learning_rate": 5.193603679611503e-07, + "loss": 0.7087, + "step": 14661 + }, + { + "epoch": 0.9000890143957764, + "grad_norm": 1.2508536565294377, + "learning_rate": 5.187281015921119e-07, + "loss": 0.771, + "step": 14662 + }, + { + "epoch": 0.9001504036342429, + "grad_norm": 0.8784159316272446, + "learning_rate": 5.180962100684594e-07, + "loss": 0.6955, + "step": 14663 + }, + { + "epoch": 0.9002117928727094, + "grad_norm": 1.0452999279042174, + "learning_rate": 5.174646934151751e-07, + "loss": 0.6953, + "step": 14664 + }, + { + "epoch": 0.9002731821111759, + "grad_norm": 0.9950351533815058, + "learning_rate": 5.168335516572287e-07, + "loss": 0.684, + "step": 14665 + }, + { + "epoch": 0.9003345713496425, + "grad_norm": 1.0245777610086673, + "learning_rate": 5.162027848195727e-07, + "loss": 0.7506, + "step": 14666 + }, + { + "epoch": 0.9003959605881089, + "grad_norm": 0.9664698432500112, + "learning_rate": 5.155723929271439e-07, + "loss": 0.7249, + "step": 14667 + }, + { + "epoch": 0.9004573498265754, + "grad_norm": 0.9314887278359544, + "learning_rate": 5.149423760048622e-07, + "loss": 0.7418, + "step": 14668 + }, + { + "epoch": 0.9005187390650419, + "grad_norm": 1.039672906741277, + "learning_rate": 5.143127340776389e-07, + "loss": 0.7729, + "step": 14669 + }, + { + "epoch": 0.9005801283035084, + "grad_norm": 0.9916317277709562, + "learning_rate": 5.136834671703672e-07, + "loss": 0.7409, + "step": 14670 + }, + { + "epoch": 0.9006415175419749, + "grad_norm": 1.0478828084225256, + "learning_rate": 5.130545753079241e-07, + "loss": 0.7531, + "step": 14671 + }, + { + "epoch": 0.9007029067804414, + "grad_norm": 1.1953542927928693, + "learning_rate": 5.12426058515173e-07, + "loss": 0.7272, + "step": 14672 + }, + { + "epoch": 0.9007642960189078, + "grad_norm": 1.0818093273437974, + "learning_rate": 5.117979168169629e-07, + "loss": 0.764, + "step": 14673 + }, + { + "epoch": 0.9008256852573744, + "grad_norm": 1.0723271042437954, + "learning_rate": 5.111701502381283e-07, + "loss": 0.7349, + "step": 14674 + }, + { + "epoch": 0.9008870744958409, + "grad_norm": 1.1395173299540138, + "learning_rate": 5.10542758803485e-07, + "loss": 0.7851, + "step": 14675 + }, + { + "epoch": 0.9009484637343074, + "grad_norm": 1.0237141430900683, + "learning_rate": 5.09915742537842e-07, + "loss": 0.7126, + "step": 14676 + }, + { + "epoch": 0.9010098529727739, + "grad_norm": 0.9399165479367421, + "learning_rate": 5.092891014659873e-07, + "loss": 0.7618, + "step": 14677 + }, + { + "epoch": 0.9010712422112404, + "grad_norm": 1.1104622575058978, + "learning_rate": 5.086628356126932e-07, + "loss": 0.7796, + "step": 14678 + }, + { + "epoch": 0.9011326314497069, + "grad_norm": 0.9860329646025242, + "learning_rate": 5.080369450027189e-07, + "loss": 0.7012, + "step": 14679 + }, + { + "epoch": 0.9011940206881733, + "grad_norm": 1.0661982068974227, + "learning_rate": 5.074114296608112e-07, + "loss": 0.736, + "step": 14680 + }, + { + "epoch": 0.9012554099266399, + "grad_norm": 1.0278335829461958, + "learning_rate": 5.067862896117026e-07, + "loss": 0.7412, + "step": 14681 + }, + { + "epoch": 0.9013167991651063, + "grad_norm": 1.0912785294439322, + "learning_rate": 5.061615248801011e-07, + "loss": 0.735, + "step": 14682 + }, + { + "epoch": 0.9013781884035729, + "grad_norm": 1.092762255444913, + "learning_rate": 5.055371354907135e-07, + "loss": 0.7391, + "step": 14683 + }, + { + "epoch": 0.9014395776420393, + "grad_norm": 1.0028435601537569, + "learning_rate": 5.049131214682223e-07, + "loss": 0.7589, + "step": 14684 + }, + { + "epoch": 0.9015009668805058, + "grad_norm": 1.076761448495749, + "learning_rate": 5.042894828372991e-07, + "loss": 0.7502, + "step": 14685 + }, + { + "epoch": 0.9015623561189724, + "grad_norm": 1.1476711187478101, + "learning_rate": 5.036662196225994e-07, + "loss": 0.7278, + "step": 14686 + }, + { + "epoch": 0.9016237453574388, + "grad_norm": 1.00926153599091, + "learning_rate": 5.030433318487638e-07, + "loss": 0.7517, + "step": 14687 + }, + { + "epoch": 0.9016851345959054, + "grad_norm": 0.9599133233289746, + "learning_rate": 5.024208195404179e-07, + "loss": 0.6706, + "step": 14688 + }, + { + "epoch": 0.9017465238343718, + "grad_norm": 1.2007274494277167, + "learning_rate": 5.017986827221733e-07, + "loss": 0.7614, + "step": 14689 + }, + { + "epoch": 0.9018079130728384, + "grad_norm": 1.023892024063136, + "learning_rate": 5.011769214186269e-07, + "loss": 0.7096, + "step": 14690 + }, + { + "epoch": 0.9018693023113048, + "grad_norm": 0.9370799399152956, + "learning_rate": 5.005555356543624e-07, + "loss": 0.7354, + "step": 14691 + }, + { + "epoch": 0.9019306915497713, + "grad_norm": 1.177569085540025, + "learning_rate": 4.999345254539434e-07, + "loss": 0.7344, + "step": 14692 + }, + { + "epoch": 0.9019920807882378, + "grad_norm": 0.8981120524206696, + "learning_rate": 4.993138908419193e-07, + "loss": 0.7289, + "step": 14693 + }, + { + "epoch": 0.9020534700267043, + "grad_norm": 0.9712982675611527, + "learning_rate": 4.986936318428337e-07, + "loss": 0.7441, + "step": 14694 + }, + { + "epoch": 0.9021148592651708, + "grad_norm": 1.1403891352236704, + "learning_rate": 4.980737484812038e-07, + "loss": 0.7146, + "step": 14695 + }, + { + "epoch": 0.9021762485036373, + "grad_norm": 1.0472167955700606, + "learning_rate": 4.974542407815398e-07, + "loss": 0.7155, + "step": 14696 + }, + { + "epoch": 0.9022376377421039, + "grad_norm": 0.9910904278087551, + "learning_rate": 4.968351087683321e-07, + "loss": 0.7021, + "step": 14697 + }, + { + "epoch": 0.9022990269805703, + "grad_norm": 0.9151074401662952, + "learning_rate": 4.962163524660591e-07, + "loss": 0.7626, + "step": 14698 + }, + { + "epoch": 0.9023604162190368, + "grad_norm": 1.0656061520890023, + "learning_rate": 4.955979718991832e-07, + "loss": 0.7068, + "step": 14699 + }, + { + "epoch": 0.9024218054575033, + "grad_norm": 1.0486360242963029, + "learning_rate": 4.949799670921518e-07, + "loss": 0.7312, + "step": 14700 + }, + { + "epoch": 0.9024831946959698, + "grad_norm": 1.1058696942404027, + "learning_rate": 4.943623380694007e-07, + "loss": 0.6942, + "step": 14701 + }, + { + "epoch": 0.9025445839344363, + "grad_norm": 1.1597501053336696, + "learning_rate": 4.93745084855346e-07, + "loss": 0.7452, + "step": 14702 + }, + { + "epoch": 0.9026059731729028, + "grad_norm": 1.1329462165929698, + "learning_rate": 4.931282074743881e-07, + "loss": 0.7576, + "step": 14703 + }, + { + "epoch": 0.9026673624113692, + "grad_norm": 1.1217888742268276, + "learning_rate": 4.925117059509211e-07, + "loss": 0.6996, + "step": 14704 + }, + { + "epoch": 0.9027287516498358, + "grad_norm": 1.127928129040518, + "learning_rate": 4.918955803093162e-07, + "loss": 0.7524, + "step": 14705 + }, + { + "epoch": 0.9027901408883022, + "grad_norm": 0.6208725282221722, + "learning_rate": 4.912798305739319e-07, + "loss": 0.7047, + "step": 14706 + }, + { + "epoch": 0.9028515301267688, + "grad_norm": 1.0895944502186563, + "learning_rate": 4.90664456769111e-07, + "loss": 0.7502, + "step": 14707 + }, + { + "epoch": 0.9029129193652353, + "grad_norm": 1.0851694881909988, + "learning_rate": 4.90049458919184e-07, + "loss": 0.7983, + "step": 14708 + }, + { + "epoch": 0.9029743086037018, + "grad_norm": 1.10069794270768, + "learning_rate": 4.894348370484648e-07, + "loss": 0.6883, + "step": 14709 + }, + { + "epoch": 0.9030356978421683, + "grad_norm": 1.105389995892529, + "learning_rate": 4.888205911812527e-07, + "loss": 0.7239, + "step": 14710 + }, + { + "epoch": 0.9030970870806347, + "grad_norm": 1.0393069419292218, + "learning_rate": 4.882067213418318e-07, + "loss": 0.7579, + "step": 14711 + }, + { + "epoch": 0.9031584763191013, + "grad_norm": 1.2096929978187132, + "learning_rate": 4.875932275544715e-07, + "loss": 0.7212, + "step": 14712 + }, + { + "epoch": 0.9032198655575677, + "grad_norm": 0.9729082029625098, + "learning_rate": 4.869801098434279e-07, + "loss": 0.7284, + "step": 14713 + }, + { + "epoch": 0.9032812547960343, + "grad_norm": 1.0936695987899678, + "learning_rate": 4.863673682329373e-07, + "loss": 0.7519, + "step": 14714 + }, + { + "epoch": 0.9033426440345007, + "grad_norm": 1.1288052347691382, + "learning_rate": 4.857550027472291e-07, + "loss": 0.7274, + "step": 14715 + }, + { + "epoch": 0.9034040332729673, + "grad_norm": 1.0314491144787663, + "learning_rate": 4.851430134105128e-07, + "loss": 0.7211, + "step": 14716 + }, + { + "epoch": 0.9034654225114337, + "grad_norm": 1.040899249158939, + "learning_rate": 4.845314002469814e-07, + "loss": 0.7283, + "step": 14717 + }, + { + "epoch": 0.9035268117499002, + "grad_norm": 0.9612610358911645, + "learning_rate": 4.839201632808133e-07, + "loss": 0.7219, + "step": 14718 + }, + { + "epoch": 0.9035882009883668, + "grad_norm": 1.0350339206656025, + "learning_rate": 4.83309302536179e-07, + "loss": 0.7318, + "step": 14719 + }, + { + "epoch": 0.9036495902268332, + "grad_norm": 1.2025978530254626, + "learning_rate": 4.826988180372272e-07, + "loss": 0.7888, + "step": 14720 + }, + { + "epoch": 0.9037109794652998, + "grad_norm": 1.1174301058605227, + "learning_rate": 4.820887098080918e-07, + "loss": 0.7648, + "step": 14721 + }, + { + "epoch": 0.9037723687037662, + "grad_norm": 0.9509934729352731, + "learning_rate": 4.814789778728957e-07, + "loss": 0.7475, + "step": 14722 + }, + { + "epoch": 0.9038337579422328, + "grad_norm": 1.1841157422506905, + "learning_rate": 4.808696222557452e-07, + "loss": 0.7935, + "step": 14723 + }, + { + "epoch": 0.9038951471806992, + "grad_norm": 1.042078348364619, + "learning_rate": 4.802606429807299e-07, + "loss": 0.7324, + "step": 14724 + }, + { + "epoch": 0.9039565364191657, + "grad_norm": 0.9854003907323275, + "learning_rate": 4.79652040071924e-07, + "loss": 0.7149, + "step": 14725 + }, + { + "epoch": 0.9040179256576322, + "grad_norm": 1.0141553483722217, + "learning_rate": 4.79043813553396e-07, + "loss": 0.7146, + "step": 14726 + }, + { + "epoch": 0.9040793148960987, + "grad_norm": 1.0191501973142139, + "learning_rate": 4.784359634491853e-07, + "loss": 0.7283, + "step": 14727 + }, + { + "epoch": 0.9041407041345653, + "grad_norm": 1.1396207360960025, + "learning_rate": 4.778284897833241e-07, + "loss": 0.7446, + "step": 14728 + }, + { + "epoch": 0.9042020933730317, + "grad_norm": 1.1405528476750455, + "learning_rate": 4.772213925798331e-07, + "loss": 0.7486, + "step": 14729 + }, + { + "epoch": 0.9042634826114982, + "grad_norm": 0.8460659379903261, + "learning_rate": 4.766146718627107e-07, + "loss": 0.6776, + "step": 14730 + }, + { + "epoch": 0.9043248718499647, + "grad_norm": 1.0204297750423743, + "learning_rate": 4.760083276559468e-07, + "loss": 0.6812, + "step": 14731 + }, + { + "epoch": 0.9043862610884312, + "grad_norm": 1.0421613209198743, + "learning_rate": 4.7540235998351004e-07, + "loss": 0.7044, + "step": 14732 + }, + { + "epoch": 0.9044476503268977, + "grad_norm": 1.1397539567604302, + "learning_rate": 4.747967688693589e-07, + "loss": 0.7628, + "step": 14733 + }, + { + "epoch": 0.9045090395653642, + "grad_norm": 1.1302001441885514, + "learning_rate": 4.7419155433743644e-07, + "loss": 0.7008, + "step": 14734 + }, + { + "epoch": 0.9045704288038307, + "grad_norm": 1.0908477686991929, + "learning_rate": 4.735867164116703e-07, + "loss": 0.747, + "step": 14735 + }, + { + "epoch": 0.9046318180422972, + "grad_norm": 0.9436106062149446, + "learning_rate": 4.7298225511597127e-07, + "loss": 0.6646, + "step": 14736 + }, + { + "epoch": 0.9046932072807636, + "grad_norm": 0.9136737176740182, + "learning_rate": 4.7237817047423694e-07, + "loss": 0.7501, + "step": 14737 + }, + { + "epoch": 0.9047545965192302, + "grad_norm": 0.9852537868816443, + "learning_rate": 4.7177446251035263e-07, + "loss": 0.7055, + "step": 14738 + }, + { + "epoch": 0.9048159857576967, + "grad_norm": 1.1332875417518253, + "learning_rate": 4.711711312481815e-07, + "loss": 0.7065, + "step": 14739 + }, + { + "epoch": 0.9048773749961632, + "grad_norm": 1.1279768472990708, + "learning_rate": 4.7056817671158106e-07, + "loss": 0.7028, + "step": 14740 + }, + { + "epoch": 0.9049387642346297, + "grad_norm": 1.1176418751005832, + "learning_rate": 4.6996559892438896e-07, + "loss": 0.7492, + "step": 14741 + }, + { + "epoch": 0.9050001534730961, + "grad_norm": 1.0369712552147716, + "learning_rate": 4.6936339791042505e-07, + "loss": 0.7216, + "step": 14742 + }, + { + "epoch": 0.9050615427115627, + "grad_norm": 1.0864883358754203, + "learning_rate": 4.687615736935003e-07, + "loss": 0.7095, + "step": 14743 + }, + { + "epoch": 0.9051229319500291, + "grad_norm": 0.9728040742426804, + "learning_rate": 4.681601262974067e-07, + "loss": 0.7166, + "step": 14744 + }, + { + "epoch": 0.9051843211884957, + "grad_norm": 1.0672858904708489, + "learning_rate": 4.675590557459253e-07, + "loss": 0.7373, + "step": 14745 + }, + { + "epoch": 0.9052457104269621, + "grad_norm": 0.9654290615890408, + "learning_rate": 4.669583620628138e-07, + "loss": 0.7143, + "step": 14746 + }, + { + "epoch": 0.9053070996654287, + "grad_norm": 1.0934551628863423, + "learning_rate": 4.663580452718264e-07, + "loss": 0.7462, + "step": 14747 + }, + { + "epoch": 0.9053684889038951, + "grad_norm": 1.1196306690625397, + "learning_rate": 4.657581053966953e-07, + "loss": 0.7579, + "step": 14748 + }, + { + "epoch": 0.9054298781423616, + "grad_norm": 1.079887524186457, + "learning_rate": 4.651585424611382e-07, + "loss": 0.7147, + "step": 14749 + }, + { + "epoch": 0.9054912673808282, + "grad_norm": 0.962093902214052, + "learning_rate": 4.6455935648886064e-07, + "loss": 0.6842, + "step": 14750 + }, + { + "epoch": 0.9055526566192946, + "grad_norm": 1.0100931744406239, + "learning_rate": 4.6396054750355024e-07, + "loss": 0.7483, + "step": 14751 + }, + { + "epoch": 0.9056140458577612, + "grad_norm": 1.1150692378417506, + "learning_rate": 4.6336211552888254e-07, + "loss": 0.7449, + "step": 14752 + }, + { + "epoch": 0.9056754350962276, + "grad_norm": 1.0640126611247727, + "learning_rate": 4.627640605885142e-07, + "loss": 0.6987, + "step": 14753 + }, + { + "epoch": 0.9057368243346942, + "grad_norm": 0.9891512361854929, + "learning_rate": 4.621663827060918e-07, + "loss": 0.699, + "step": 14754 + }, + { + "epoch": 0.9057982135731606, + "grad_norm": 1.1359692883053056, + "learning_rate": 4.6156908190524653e-07, + "loss": 0.6723, + "step": 14755 + }, + { + "epoch": 0.9058596028116271, + "grad_norm": 1.0939155744918516, + "learning_rate": 4.609721582095894e-07, + "loss": 0.7315, + "step": 14756 + }, + { + "epoch": 0.9059209920500936, + "grad_norm": 1.0619225563561427, + "learning_rate": 4.603756116427194e-07, + "loss": 0.7264, + "step": 14757 + }, + { + "epoch": 0.9059823812885601, + "grad_norm": 1.0378423887265442, + "learning_rate": 4.5977944222822423e-07, + "loss": 0.7278, + "step": 14758 + }, + { + "epoch": 0.9060437705270266, + "grad_norm": 1.0202491885698801, + "learning_rate": 4.591836499896718e-07, + "loss": 0.6952, + "step": 14759 + }, + { + "epoch": 0.9061051597654931, + "grad_norm": 1.0637286575459692, + "learning_rate": 4.5858823495061876e-07, + "loss": 0.7213, + "step": 14760 + }, + { + "epoch": 0.9061665490039597, + "grad_norm": 1.0172963384640095, + "learning_rate": 4.57993197134603e-07, + "loss": 0.7182, + "step": 14761 + }, + { + "epoch": 0.9062279382424261, + "grad_norm": 1.070460492643269, + "learning_rate": 4.573985365651512e-07, + "loss": 0.7604, + "step": 14762 + }, + { + "epoch": 0.9062893274808926, + "grad_norm": 1.0714934560487208, + "learning_rate": 4.568042532657713e-07, + "loss": 0.763, + "step": 14763 + }, + { + "epoch": 0.9063507167193591, + "grad_norm": 1.0329674231207548, + "learning_rate": 4.5621034725995994e-07, + "loss": 0.7308, + "step": 14764 + }, + { + "epoch": 0.9064121059578256, + "grad_norm": 0.9816977450599943, + "learning_rate": 4.556168185711995e-07, + "loss": 0.7009, + "step": 14765 + }, + { + "epoch": 0.9064734951962921, + "grad_norm": 0.9607982449075395, + "learning_rate": 4.550236672229513e-07, + "loss": 0.7653, + "step": 14766 + }, + { + "epoch": 0.9065348844347586, + "grad_norm": 1.0228683425494292, + "learning_rate": 4.544308932386665e-07, + "loss": 0.7548, + "step": 14767 + }, + { + "epoch": 0.906596273673225, + "grad_norm": 1.1102431242439847, + "learning_rate": 4.5383849664178415e-07, + "loss": 0.6798, + "step": 14768 + }, + { + "epoch": 0.9066576629116916, + "grad_norm": 1.0367654578258199, + "learning_rate": 4.5324647745572103e-07, + "loss": 0.7243, + "step": 14769 + }, + { + "epoch": 0.906719052150158, + "grad_norm": 1.0022963246635515, + "learning_rate": 4.5265483570388733e-07, + "loss": 0.6891, + "step": 14770 + }, + { + "epoch": 0.9067804413886246, + "grad_norm": 1.0917088202663388, + "learning_rate": 4.520635714096666e-07, + "loss": 0.7209, + "step": 14771 + }, + { + "epoch": 0.9068418306270911, + "grad_norm": 1.1158792967219613, + "learning_rate": 4.514726845964412e-07, + "loss": 0.7058, + "step": 14772 + }, + { + "epoch": 0.9069032198655576, + "grad_norm": 1.1548369697401162, + "learning_rate": 4.508821752875692e-07, + "loss": 0.6948, + "step": 14773 + }, + { + "epoch": 0.9069646091040241, + "grad_norm": 1.1341546567816372, + "learning_rate": 4.502920435063962e-07, + "loss": 0.6899, + "step": 14774 + }, + { + "epoch": 0.9070259983424905, + "grad_norm": 1.0544356114752553, + "learning_rate": 4.4970228927625593e-07, + "loss": 0.7034, + "step": 14775 + }, + { + "epoch": 0.9070873875809571, + "grad_norm": 1.045522145125511, + "learning_rate": 4.4911291262046074e-07, + "loss": 0.6922, + "step": 14776 + }, + { + "epoch": 0.9071487768194235, + "grad_norm": 1.257447753188984, + "learning_rate": 4.4852391356231537e-07, + "loss": 0.7224, + "step": 14777 + }, + { + "epoch": 0.9072101660578901, + "grad_norm": 1.2723330236286192, + "learning_rate": 4.479352921251034e-07, + "loss": 0.7322, + "step": 14778 + }, + { + "epoch": 0.9072715552963565, + "grad_norm": 1.0555375225694188, + "learning_rate": 4.473470483320974e-07, + "loss": 0.7354, + "step": 14779 + }, + { + "epoch": 0.907332944534823, + "grad_norm": 1.05308297010916, + "learning_rate": 4.4675918220655646e-07, + "loss": 0.741, + "step": 14780 + }, + { + "epoch": 0.9073943337732896, + "grad_norm": 1.0277698832413917, + "learning_rate": 4.4617169377171534e-07, + "loss": 0.7167, + "step": 14781 + }, + { + "epoch": 0.907455723011756, + "grad_norm": 1.0071383111326981, + "learning_rate": 4.455845830508065e-07, + "loss": 0.7758, + "step": 14782 + }, + { + "epoch": 0.9075171122502226, + "grad_norm": 1.1382206362966742, + "learning_rate": 4.4499785006704044e-07, + "loss": 0.7099, + "step": 14783 + }, + { + "epoch": 0.907578501488689, + "grad_norm": 1.145681363240931, + "learning_rate": 4.444114948436129e-07, + "loss": 0.6857, + "step": 14784 + }, + { + "epoch": 0.9076398907271556, + "grad_norm": 1.1155100792313453, + "learning_rate": 4.438255174037054e-07, + "loss": 0.7262, + "step": 14785 + }, + { + "epoch": 0.907701279965622, + "grad_norm": 0.5807866386879013, + "learning_rate": 4.432399177704849e-07, + "loss": 0.625, + "step": 14786 + }, + { + "epoch": 0.9077626692040885, + "grad_norm": 0.9680034905423306, + "learning_rate": 4.426546959671041e-07, + "loss": 0.7503, + "step": 14787 + }, + { + "epoch": 0.907824058442555, + "grad_norm": 1.028015167068333, + "learning_rate": 4.420698520166988e-07, + "loss": 0.6631, + "step": 14788 + }, + { + "epoch": 0.9078854476810215, + "grad_norm": 1.1428300599174002, + "learning_rate": 4.4148538594239176e-07, + "loss": 0.7169, + "step": 14789 + }, + { + "epoch": 0.907946836919488, + "grad_norm": 0.9733118755724041, + "learning_rate": 4.4090129776729107e-07, + "loss": 0.7049, + "step": 14790 + }, + { + "epoch": 0.9080082261579545, + "grad_norm": 1.1608662894555346, + "learning_rate": 4.4031758751448717e-07, + "loss": 0.698, + "step": 14791 + }, + { + "epoch": 0.9080696153964211, + "grad_norm": 1.113492931709002, + "learning_rate": 4.3973425520705605e-07, + "loss": 0.7499, + "step": 14792 + }, + { + "epoch": 0.9081310046348875, + "grad_norm": 0.9509662600526635, + "learning_rate": 4.391513008680637e-07, + "loss": 0.7106, + "step": 14793 + }, + { + "epoch": 0.908192393873354, + "grad_norm": 1.0601173457545012, + "learning_rate": 4.3856872452055497e-07, + "loss": 0.6847, + "step": 14794 + }, + { + "epoch": 0.9082537831118205, + "grad_norm": 0.9724774800493344, + "learning_rate": 4.379865261875649e-07, + "loss": 0.7152, + "step": 14795 + }, + { + "epoch": 0.908315172350287, + "grad_norm": 1.0376468293929242, + "learning_rate": 4.3740470589210495e-07, + "loss": 0.7011, + "step": 14796 + }, + { + "epoch": 0.9083765615887535, + "grad_norm": 1.1350150621837019, + "learning_rate": 4.368232636571823e-07, + "loss": 0.736, + "step": 14797 + }, + { + "epoch": 0.90843795082722, + "grad_norm": 1.0358298578922103, + "learning_rate": 4.3624219950578527e-07, + "loss": 0.794, + "step": 14798 + }, + { + "epoch": 0.9084993400656864, + "grad_norm": 1.1195816205689015, + "learning_rate": 4.3566151346088323e-07, + "loss": 0.7572, + "step": 14799 + }, + { + "epoch": 0.908560729304153, + "grad_norm": 0.9761111212768598, + "learning_rate": 4.350812055454356e-07, + "loss": 0.7067, + "step": 14800 + }, + { + "epoch": 0.9086221185426194, + "grad_norm": 0.9733693916191165, + "learning_rate": 4.345012757823841e-07, + "loss": 0.6888, + "step": 14801 + }, + { + "epoch": 0.908683507781086, + "grad_norm": 1.1107611320833652, + "learning_rate": 4.3392172419465804e-07, + "loss": 0.7513, + "step": 14802 + }, + { + "epoch": 0.9087448970195525, + "grad_norm": 1.0090210532090393, + "learning_rate": 4.3334255080516805e-07, + "loss": 0.7808, + "step": 14803 + }, + { + "epoch": 0.908806286258019, + "grad_norm": 0.9185021682103472, + "learning_rate": 4.327637556368136e-07, + "loss": 0.6451, + "step": 14804 + }, + { + "epoch": 0.9088676754964855, + "grad_norm": 1.1175514621664977, + "learning_rate": 4.3218533871247857e-07, + "loss": 0.7401, + "step": 14805 + }, + { + "epoch": 0.9089290647349519, + "grad_norm": 1.1638235388194227, + "learning_rate": 4.3160730005502695e-07, + "loss": 0.7667, + "step": 14806 + }, + { + "epoch": 0.9089904539734185, + "grad_norm": 1.0183900042032779, + "learning_rate": 4.310296396873148e-07, + "loss": 0.7155, + "step": 14807 + }, + { + "epoch": 0.9090518432118849, + "grad_norm": 1.0521413311614558, + "learning_rate": 4.304523576321806e-07, + "loss": 0.6708, + "step": 14808 + }, + { + "epoch": 0.9091132324503515, + "grad_norm": 0.9673667718638181, + "learning_rate": 4.2987545391244613e-07, + "loss": 0.7488, + "step": 14809 + }, + { + "epoch": 0.9091746216888179, + "grad_norm": 1.1460044839158432, + "learning_rate": 4.292989285509186e-07, + "loss": 0.7338, + "step": 14810 + }, + { + "epoch": 0.9092360109272845, + "grad_norm": 1.110705977243931, + "learning_rate": 4.2872278157039206e-07, + "loss": 0.777, + "step": 14811 + }, + { + "epoch": 0.9092974001657509, + "grad_norm": 1.0887311675204574, + "learning_rate": 4.281470129936449e-07, + "loss": 0.7295, + "step": 14812 + }, + { + "epoch": 0.9093587894042174, + "grad_norm": 1.091991438395408, + "learning_rate": 4.2757162284344123e-07, + "loss": 0.7376, + "step": 14813 + }, + { + "epoch": 0.909420178642684, + "grad_norm": 1.0576022042432534, + "learning_rate": 4.269966111425272e-07, + "loss": 0.739, + "step": 14814 + }, + { + "epoch": 0.9094815678811504, + "grad_norm": 0.9511730245224013, + "learning_rate": 4.2642197791363806e-07, + "loss": 0.7354, + "step": 14815 + }, + { + "epoch": 0.909542957119617, + "grad_norm": 0.9385551921550657, + "learning_rate": 4.2584772317948995e-07, + "loss": 0.7258, + "step": 14816 + }, + { + "epoch": 0.9096043463580834, + "grad_norm": 1.1681354537423128, + "learning_rate": 4.2527384696278706e-07, + "loss": 0.7821, + "step": 14817 + }, + { + "epoch": 0.90966573559655, + "grad_norm": 1.083283452872324, + "learning_rate": 4.2470034928622004e-07, + "loss": 0.7252, + "step": 14818 + }, + { + "epoch": 0.9097271248350164, + "grad_norm": 1.1291166327312576, + "learning_rate": 4.241272301724608e-07, + "loss": 0.7264, + "step": 14819 + }, + { + "epoch": 0.9097885140734829, + "grad_norm": 1.0317542211674122, + "learning_rate": 4.235544896441657e-07, + "loss": 0.721, + "step": 14820 + }, + { + "epoch": 0.9098499033119494, + "grad_norm": 1.0925118826938176, + "learning_rate": 4.2298212772398096e-07, + "loss": 0.7523, + "step": 14821 + }, + { + "epoch": 0.9099112925504159, + "grad_norm": 0.9915464003717442, + "learning_rate": 4.2241014443453407e-07, + "loss": 0.6979, + "step": 14822 + }, + { + "epoch": 0.9099726817888824, + "grad_norm": 1.002612506724415, + "learning_rate": 4.2183853979843816e-07, + "loss": 0.6996, + "step": 14823 + }, + { + "epoch": 0.9100340710273489, + "grad_norm": 1.1141400173790394, + "learning_rate": 4.212673138382939e-07, + "loss": 0.7432, + "step": 14824 + }, + { + "epoch": 0.9100954602658154, + "grad_norm": 0.9945674153934555, + "learning_rate": 4.2069646657668215e-07, + "loss": 0.7608, + "step": 14825 + }, + { + "epoch": 0.9101568495042819, + "grad_norm": 0.961667953120991, + "learning_rate": 4.2012599803617384e-07, + "loss": 0.7481, + "step": 14826 + }, + { + "epoch": 0.9102182387427484, + "grad_norm": 1.1320717134417213, + "learning_rate": 4.195559082393208e-07, + "loss": 0.7395, + "step": 14827 + }, + { + "epoch": 0.9102796279812149, + "grad_norm": 0.9435768468276746, + "learning_rate": 4.1898619720866063e-07, + "loss": 0.7255, + "step": 14828 + }, + { + "epoch": 0.9103410172196814, + "grad_norm": 1.029075609028183, + "learning_rate": 4.1841686496672306e-07, + "loss": 0.7191, + "step": 14829 + }, + { + "epoch": 0.9104024064581479, + "grad_norm": 1.208456198916276, + "learning_rate": 4.178479115360101e-07, + "loss": 0.7573, + "step": 14830 + }, + { + "epoch": 0.9104637956966144, + "grad_norm": 1.1869647407138986, + "learning_rate": 4.1727933693901825e-07, + "loss": 0.6996, + "step": 14831 + }, + { + "epoch": 0.9105251849350808, + "grad_norm": 1.0440220356247467, + "learning_rate": 4.167111411982261e-07, + "loss": 0.7265, + "step": 14832 + }, + { + "epoch": 0.9105865741735474, + "grad_norm": 1.0492321079616083, + "learning_rate": 4.1614332433609797e-07, + "loss": 0.7592, + "step": 14833 + }, + { + "epoch": 0.9106479634120139, + "grad_norm": 1.153795246825898, + "learning_rate": 4.1557588637508363e-07, + "loss": 0.6978, + "step": 14834 + }, + { + "epoch": 0.9107093526504804, + "grad_norm": 1.1797144834408193, + "learning_rate": 4.1500882733761403e-07, + "loss": 0.7749, + "step": 14835 + }, + { + "epoch": 0.9107707418889469, + "grad_norm": 0.9466487813816205, + "learning_rate": 4.144421472461102e-07, + "loss": 0.6911, + "step": 14836 + }, + { + "epoch": 0.9108321311274133, + "grad_norm": 1.1238476873927103, + "learning_rate": 4.138758461229753e-07, + "loss": 0.7551, + "step": 14837 + }, + { + "epoch": 0.9108935203658799, + "grad_norm": 1.2142244164825904, + "learning_rate": 4.13309923990598e-07, + "loss": 0.7156, + "step": 14838 + }, + { + "epoch": 0.9109549096043463, + "grad_norm": 0.9774391412235166, + "learning_rate": 4.1274438087135273e-07, + "loss": 0.7244, + "step": 14839 + }, + { + "epoch": 0.9110162988428129, + "grad_norm": 1.0563742074664597, + "learning_rate": 4.1217921678759934e-07, + "loss": 0.7001, + "step": 14840 + }, + { + "epoch": 0.9110776880812793, + "grad_norm": 1.1352087107296538, + "learning_rate": 4.116144317616799e-07, + "loss": 0.7133, + "step": 14841 + }, + { + "epoch": 0.9111390773197459, + "grad_norm": 1.0610748537857346, + "learning_rate": 4.1105002581592334e-07, + "loss": 0.7579, + "step": 14842 + }, + { + "epoch": 0.9112004665582123, + "grad_norm": 1.0070247580869385, + "learning_rate": 4.104859989726451e-07, + "loss": 0.7242, + "step": 14843 + }, + { + "epoch": 0.9112618557966788, + "grad_norm": 1.1504672201351547, + "learning_rate": 4.0992235125414616e-07, + "loss": 0.7607, + "step": 14844 + }, + { + "epoch": 0.9113232450351454, + "grad_norm": 0.9959421296882573, + "learning_rate": 4.093590826827043e-07, + "loss": 0.7241, + "step": 14845 + }, + { + "epoch": 0.9113846342736118, + "grad_norm": 1.028413041177727, + "learning_rate": 4.087961932805939e-07, + "loss": 0.7258, + "step": 14846 + }, + { + "epoch": 0.9114460235120784, + "grad_norm": 1.0317272345015478, + "learning_rate": 4.0823368307006727e-07, + "loss": 0.7771, + "step": 14847 + }, + { + "epoch": 0.9115074127505448, + "grad_norm": 1.0744978905601437, + "learning_rate": 4.076715520733643e-07, + "loss": 0.6537, + "step": 14848 + }, + { + "epoch": 0.9115688019890114, + "grad_norm": 1.124233339123176, + "learning_rate": 4.071098003127072e-07, + "loss": 0.7571, + "step": 14849 + }, + { + "epoch": 0.9116301912274778, + "grad_norm": 0.9859804739499398, + "learning_rate": 4.0654842781030714e-07, + "loss": 0.6799, + "step": 14850 + }, + { + "epoch": 0.9116915804659443, + "grad_norm": 1.0407572294315053, + "learning_rate": 4.0598743458835634e-07, + "loss": 0.7474, + "step": 14851 + }, + { + "epoch": 0.9117529697044108, + "grad_norm": 0.963478810239919, + "learning_rate": 4.054268206690348e-07, + "loss": 0.7758, + "step": 14852 + }, + { + "epoch": 0.9118143589428773, + "grad_norm": 1.0991952412691943, + "learning_rate": 4.048665860745049e-07, + "loss": 0.7543, + "step": 14853 + }, + { + "epoch": 0.9118757481813438, + "grad_norm": 1.0916078175112722, + "learning_rate": 4.0430673082691993e-07, + "loss": 0.7262, + "step": 14854 + }, + { + "epoch": 0.9119371374198103, + "grad_norm": 1.0182980300727265, + "learning_rate": 4.037472549484101e-07, + "loss": 0.7332, + "step": 14855 + }, + { + "epoch": 0.9119985266582769, + "grad_norm": 0.9726049241993724, + "learning_rate": 4.031881584610953e-07, + "loss": 0.7005, + "step": 14856 + }, + { + "epoch": 0.9120599158967433, + "grad_norm": 1.0196042310247921, + "learning_rate": 4.0262944138708017e-07, + "loss": 0.7566, + "step": 14857 + }, + { + "epoch": 0.9121213051352098, + "grad_norm": 1.1348351261304166, + "learning_rate": 4.020711037484537e-07, + "loss": 0.7394, + "step": 14858 + }, + { + "epoch": 0.9121826943736763, + "grad_norm": 0.9811749203647688, + "learning_rate": 4.015131455672894e-07, + "loss": 0.6973, + "step": 14859 + }, + { + "epoch": 0.9122440836121428, + "grad_norm": 0.9959826967163332, + "learning_rate": 4.009555668656473e-07, + "loss": 0.7237, + "step": 14860 + }, + { + "epoch": 0.9123054728506093, + "grad_norm": 1.10607725400457, + "learning_rate": 4.003983676655709e-07, + "loss": 0.7312, + "step": 14861 + }, + { + "epoch": 0.9123668620890758, + "grad_norm": 1.0770733246169766, + "learning_rate": 3.998415479890894e-07, + "loss": 0.7328, + "step": 14862 + }, + { + "epoch": 0.9124282513275422, + "grad_norm": 0.9918095714127128, + "learning_rate": 3.9928510785821607e-07, + "loss": 0.7168, + "step": 14863 + }, + { + "epoch": 0.9124896405660088, + "grad_norm": 1.0605084633691364, + "learning_rate": 3.9872904729495123e-07, + "loss": 0.786, + "step": 14864 + }, + { + "epoch": 0.9125510298044752, + "grad_norm": 1.1873484825651215, + "learning_rate": 3.9817336632127833e-07, + "loss": 0.735, + "step": 14865 + }, + { + "epoch": 0.9126124190429418, + "grad_norm": 1.1501765690722852, + "learning_rate": 3.9761806495916656e-07, + "loss": 0.7147, + "step": 14866 + }, + { + "epoch": 0.9126738082814083, + "grad_norm": 1.029282235709837, + "learning_rate": 3.9706314323056936e-07, + "loss": 0.7884, + "step": 14867 + }, + { + "epoch": 0.9127351975198748, + "grad_norm": 1.06164929776317, + "learning_rate": 3.9650860115742595e-07, + "loss": 0.7032, + "step": 14868 + }, + { + "epoch": 0.9127965867583413, + "grad_norm": 1.1288995261803305, + "learning_rate": 3.959544387616632e-07, + "loss": 0.7466, + "step": 14869 + }, + { + "epoch": 0.9128579759968077, + "grad_norm": 1.11434862867947, + "learning_rate": 3.9540065606518353e-07, + "loss": 0.7328, + "step": 14870 + }, + { + "epoch": 0.9129193652352743, + "grad_norm": 0.991099325753921, + "learning_rate": 3.9484725308988725e-07, + "loss": 0.7551, + "step": 14871 + }, + { + "epoch": 0.9129807544737407, + "grad_norm": 1.033825457914686, + "learning_rate": 3.942942298576513e-07, + "loss": 0.7206, + "step": 14872 + }, + { + "epoch": 0.9130421437122073, + "grad_norm": 1.1055197666146812, + "learning_rate": 3.937415863903382e-07, + "loss": 0.7204, + "step": 14873 + }, + { + "epoch": 0.9131035329506737, + "grad_norm": 1.1428933275790767, + "learning_rate": 3.931893227097994e-07, + "loss": 0.7012, + "step": 14874 + }, + { + "epoch": 0.9131649221891402, + "grad_norm": 1.045798831148204, + "learning_rate": 3.926374388378662e-07, + "loss": 0.7135, + "step": 14875 + }, + { + "epoch": 0.9132263114276067, + "grad_norm": 1.008355936146096, + "learning_rate": 3.92085934796359e-07, + "loss": 0.6785, + "step": 14876 + }, + { + "epoch": 0.9132877006660732, + "grad_norm": 1.1770405982223064, + "learning_rate": 3.9153481060708264e-07, + "loss": 0.7827, + "step": 14877 + }, + { + "epoch": 0.9133490899045398, + "grad_norm": 1.1878933619178111, + "learning_rate": 3.909840662918241e-07, + "loss": 0.7423, + "step": 14878 + }, + { + "epoch": 0.9134104791430062, + "grad_norm": 1.0407951819506598, + "learning_rate": 3.904337018723581e-07, + "loss": 0.7258, + "step": 14879 + }, + { + "epoch": 0.9134718683814728, + "grad_norm": 1.083067244407415, + "learning_rate": 3.8988371737044396e-07, + "loss": 0.7248, + "step": 14880 + }, + { + "epoch": 0.9135332576199392, + "grad_norm": 1.0296806184954592, + "learning_rate": 3.893341128078232e-07, + "loss": 0.7101, + "step": 14881 + }, + { + "epoch": 0.9135946468584057, + "grad_norm": 0.9938683272003206, + "learning_rate": 3.887848882062273e-07, + "loss": 0.6782, + "step": 14882 + }, + { + "epoch": 0.9136560360968722, + "grad_norm": 1.1585663110236846, + "learning_rate": 3.882360435873711e-07, + "loss": 0.7453, + "step": 14883 + }, + { + "epoch": 0.9137174253353387, + "grad_norm": 1.0313429245779058, + "learning_rate": 3.876875789729484e-07, + "loss": 0.7708, + "step": 14884 + }, + { + "epoch": 0.9137788145738052, + "grad_norm": 1.0857266325503157, + "learning_rate": 3.871394943846485e-07, + "loss": 0.752, + "step": 14885 + }, + { + "epoch": 0.9138402038122717, + "grad_norm": 1.1225288376226572, + "learning_rate": 3.8659178984413625e-07, + "loss": 0.7046, + "step": 14886 + }, + { + "epoch": 0.9139015930507383, + "grad_norm": 1.0862894754900605, + "learning_rate": 3.860444653730666e-07, + "loss": 0.71, + "step": 14887 + }, + { + "epoch": 0.9139629822892047, + "grad_norm": 1.138451057709267, + "learning_rate": 3.854975209930789e-07, + "loss": 0.7237, + "step": 14888 + }, + { + "epoch": 0.9140243715276712, + "grad_norm": 1.0363803278568824, + "learning_rate": 3.8495095672579584e-07, + "loss": 0.7439, + "step": 14889 + }, + { + "epoch": 0.9140857607661377, + "grad_norm": 1.0288977058548567, + "learning_rate": 3.8440477259282685e-07, + "loss": 0.7146, + "step": 14890 + }, + { + "epoch": 0.9141471500046042, + "grad_norm": 1.0303998228500488, + "learning_rate": 3.8385896861576454e-07, + "loss": 0.7331, + "step": 14891 + }, + { + "epoch": 0.9142085392430707, + "grad_norm": 1.054285494253376, + "learning_rate": 3.8331354481618623e-07, + "loss": 0.6478, + "step": 14892 + }, + { + "epoch": 0.9142699284815372, + "grad_norm": 0.8978300044166794, + "learning_rate": 3.827685012156612e-07, + "loss": 0.7704, + "step": 14893 + }, + { + "epoch": 0.9143313177200036, + "grad_norm": 1.0803651348013414, + "learning_rate": 3.8222383783573124e-07, + "loss": 0.7244, + "step": 14894 + }, + { + "epoch": 0.9143927069584702, + "grad_norm": 1.0114338008384856, + "learning_rate": 3.8167955469793126e-07, + "loss": 0.739, + "step": 14895 + }, + { + "epoch": 0.9144540961969366, + "grad_norm": 1.0433757617100763, + "learning_rate": 3.81135651823783e-07, + "loss": 0.7068, + "step": 14896 + }, + { + "epoch": 0.9145154854354032, + "grad_norm": 1.056463834188005, + "learning_rate": 3.8059212923478693e-07, + "loss": 0.761, + "step": 14897 + }, + { + "epoch": 0.9145768746738697, + "grad_norm": 0.9117513713421502, + "learning_rate": 3.8004898695243375e-07, + "loss": 0.7045, + "step": 14898 + }, + { + "epoch": 0.9146382639123362, + "grad_norm": 1.0846780886077294, + "learning_rate": 3.795062249981929e-07, + "loss": 0.7231, + "step": 14899 + }, + { + "epoch": 0.9146996531508027, + "grad_norm": 1.1335235670875201, + "learning_rate": 3.789638433935261e-07, + "loss": 0.7906, + "step": 14900 + }, + { + "epoch": 0.9147610423892691, + "grad_norm": 1.0604545074406144, + "learning_rate": 3.784218421598751e-07, + "loss": 0.7292, + "step": 14901 + }, + { + "epoch": 0.9148224316277357, + "grad_norm": 0.9477892570593831, + "learning_rate": 3.778802213186694e-07, + "loss": 0.713, + "step": 14902 + }, + { + "epoch": 0.9148838208662021, + "grad_norm": 0.9540797083943796, + "learning_rate": 3.7733898089132083e-07, + "loss": 0.737, + "step": 14903 + }, + { + "epoch": 0.9149452101046687, + "grad_norm": 1.0746406784720908, + "learning_rate": 3.7679812089922775e-07, + "loss": 0.6906, + "step": 14904 + }, + { + "epoch": 0.9150065993431351, + "grad_norm": 1.0997224270634722, + "learning_rate": 3.762576413637731e-07, + "loss": 0.7323, + "step": 14905 + }, + { + "epoch": 0.9150679885816017, + "grad_norm": 1.0850850598411044, + "learning_rate": 3.757175423063242e-07, + "loss": 0.7013, + "step": 14906 + }, + { + "epoch": 0.9151293778200681, + "grad_norm": 0.9652584748612104, + "learning_rate": 3.751778237482373e-07, + "loss": 0.7462, + "step": 14907 + }, + { + "epoch": 0.9151907670585346, + "grad_norm": 1.0482698192647422, + "learning_rate": 3.746384857108487e-07, + "loss": 0.7158, + "step": 14908 + }, + { + "epoch": 0.9152521562970012, + "grad_norm": 0.9958019249944906, + "learning_rate": 3.74099528215478e-07, + "loss": 0.7076, + "step": 14909 + }, + { + "epoch": 0.9153135455354676, + "grad_norm": 1.1541270939937704, + "learning_rate": 3.7356095128343816e-07, + "loss": 0.7154, + "step": 14910 + }, + { + "epoch": 0.9153749347739342, + "grad_norm": 1.0032036911760904, + "learning_rate": 3.730227549360188e-07, + "loss": 0.7551, + "step": 14911 + }, + { + "epoch": 0.9154363240124006, + "grad_norm": 1.1627942424238695, + "learning_rate": 3.7248493919449844e-07, + "loss": 0.7921, + "step": 14912 + }, + { + "epoch": 0.9154977132508672, + "grad_norm": 1.193631691949944, + "learning_rate": 3.719475040801412e-07, + "loss": 0.7051, + "step": 14913 + }, + { + "epoch": 0.9155591024893336, + "grad_norm": 1.1360627180256087, + "learning_rate": 3.714104496141924e-07, + "loss": 0.7441, + "step": 14914 + }, + { + "epoch": 0.9156204917278001, + "grad_norm": 1.026214833625885, + "learning_rate": 3.708737758178871e-07, + "loss": 0.6998, + "step": 14915 + }, + { + "epoch": 0.9156818809662666, + "grad_norm": 1.0163633442097817, + "learning_rate": 3.703374827124406e-07, + "loss": 0.6633, + "step": 14916 + }, + { + "epoch": 0.9157432702047331, + "grad_norm": 1.071561626382581, + "learning_rate": 3.6980157031905494e-07, + "loss": 0.7047, + "step": 14917 + }, + { + "epoch": 0.9158046594431996, + "grad_norm": 1.0448857205775377, + "learning_rate": 3.6926603865892196e-07, + "loss": 0.7174, + "step": 14918 + }, + { + "epoch": 0.9158660486816661, + "grad_norm": 1.0011432894153482, + "learning_rate": 3.687308877532103e-07, + "loss": 0.7203, + "step": 14919 + }, + { + "epoch": 0.9159274379201326, + "grad_norm": 1.0930027567856029, + "learning_rate": 3.681961176230775e-07, + "loss": 0.7299, + "step": 14920 + }, + { + "epoch": 0.9159888271585991, + "grad_norm": 1.1354901901713885, + "learning_rate": 3.676617282896666e-07, + "loss": 0.7094, + "step": 14921 + }, + { + "epoch": 0.9160502163970656, + "grad_norm": 0.997473261615118, + "learning_rate": 3.6712771977410634e-07, + "loss": 0.7283, + "step": 14922 + }, + { + "epoch": 0.9161116056355321, + "grad_norm": 1.1153013718647584, + "learning_rate": 3.665940920975064e-07, + "loss": 0.6856, + "step": 14923 + }, + { + "epoch": 0.9161729948739986, + "grad_norm": 1.0220536562485385, + "learning_rate": 3.660608452809655e-07, + "loss": 0.7246, + "step": 14924 + }, + { + "epoch": 0.916234384112465, + "grad_norm": 0.9725340944236288, + "learning_rate": 3.655279793455657e-07, + "loss": 0.7187, + "step": 14925 + }, + { + "epoch": 0.9162957733509316, + "grad_norm": 0.9962621053004833, + "learning_rate": 3.649954943123735e-07, + "loss": 0.7946, + "step": 14926 + }, + { + "epoch": 0.916357162589398, + "grad_norm": 1.0810789101427858, + "learning_rate": 3.644633902024408e-07, + "loss": 0.7512, + "step": 14927 + }, + { + "epoch": 0.9164185518278646, + "grad_norm": 1.0433532701817432, + "learning_rate": 3.639316670368054e-07, + "loss": 0.7038, + "step": 14928 + }, + { + "epoch": 0.9164799410663311, + "grad_norm": 1.170566147406989, + "learning_rate": 3.634003248364881e-07, + "loss": 0.71, + "step": 14929 + }, + { + "epoch": 0.9165413303047976, + "grad_norm": 1.021050129226184, + "learning_rate": 3.6286936362249556e-07, + "loss": 0.715, + "step": 14930 + }, + { + "epoch": 0.9166027195432641, + "grad_norm": 1.067515616439148, + "learning_rate": 3.623387834158187e-07, + "loss": 0.7267, + "step": 14931 + }, + { + "epoch": 0.9166641087817305, + "grad_norm": 1.1191751297088635, + "learning_rate": 3.6180858423743745e-07, + "loss": 0.6738, + "step": 14932 + }, + { + "epoch": 0.9167254980201971, + "grad_norm": 1.0646047710804019, + "learning_rate": 3.612787661083128e-07, + "loss": 0.7231, + "step": 14933 + }, + { + "epoch": 0.9167868872586635, + "grad_norm": 0.9774883522946186, + "learning_rate": 3.6074932904938795e-07, + "loss": 0.6996, + "step": 14934 + }, + { + "epoch": 0.9168482764971301, + "grad_norm": 1.1073647642848587, + "learning_rate": 3.6022027308159735e-07, + "loss": 0.7372, + "step": 14935 + }, + { + "epoch": 0.9169096657355965, + "grad_norm": 1.0942836520211339, + "learning_rate": 3.596915982258564e-07, + "loss": 0.7458, + "step": 14936 + }, + { + "epoch": 0.9169710549740631, + "grad_norm": 0.9983214618721049, + "learning_rate": 3.591633045030662e-07, + "loss": 0.7447, + "step": 14937 + }, + { + "epoch": 0.9170324442125295, + "grad_norm": 0.9715727870179817, + "learning_rate": 3.5863539193411344e-07, + "loss": 0.7025, + "step": 14938 + }, + { + "epoch": 0.917093833450996, + "grad_norm": 0.9808263587188631, + "learning_rate": 3.5810786053987025e-07, + "loss": 0.6992, + "step": 14939 + }, + { + "epoch": 0.9171552226894626, + "grad_norm": 1.0567309004877805, + "learning_rate": 3.57580710341191e-07, + "loss": 0.7221, + "step": 14940 + }, + { + "epoch": 0.917216611927929, + "grad_norm": 1.0542647256027058, + "learning_rate": 3.570539413589169e-07, + "loss": 0.7176, + "step": 14941 + }, + { + "epoch": 0.9172780011663956, + "grad_norm": 1.0622996909896905, + "learning_rate": 3.565275536138757e-07, + "loss": 0.7398, + "step": 14942 + }, + { + "epoch": 0.917339390404862, + "grad_norm": 1.146078563688209, + "learning_rate": 3.560015471268774e-07, + "loss": 0.7743, + "step": 14943 + }, + { + "epoch": 0.9174007796433286, + "grad_norm": 1.0329617863144431, + "learning_rate": 3.554759219187165e-07, + "loss": 0.7804, + "step": 14944 + }, + { + "epoch": 0.917462168881795, + "grad_norm": 0.9159889137019851, + "learning_rate": 3.5495067801017526e-07, + "loss": 0.7186, + "step": 14945 + }, + { + "epoch": 0.9175235581202615, + "grad_norm": 1.0479549248774362, + "learning_rate": 3.544258154220193e-07, + "loss": 0.7737, + "step": 14946 + }, + { + "epoch": 0.917584947358728, + "grad_norm": 1.137962162431415, + "learning_rate": 3.5390133417499974e-07, + "loss": 0.7456, + "step": 14947 + }, + { + "epoch": 0.9176463365971945, + "grad_norm": 0.9834454748387853, + "learning_rate": 3.5337723428985005e-07, + "loss": 0.7247, + "step": 14948 + }, + { + "epoch": 0.917707725835661, + "grad_norm": 1.0716682306899423, + "learning_rate": 3.5285351578729254e-07, + "loss": 0.7934, + "step": 14949 + }, + { + "epoch": 0.9177691150741275, + "grad_norm": 1.1846282014786036, + "learning_rate": 3.523301786880329e-07, + "loss": 0.7031, + "step": 14950 + }, + { + "epoch": 0.917830504312594, + "grad_norm": 0.9919199532776984, + "learning_rate": 3.5180722301276003e-07, + "loss": 0.7158, + "step": 14951 + }, + { + "epoch": 0.9178918935510605, + "grad_norm": 0.9694680652351351, + "learning_rate": 3.512846487821497e-07, + "loss": 0.7246, + "step": 14952 + }, + { + "epoch": 0.917953282789527, + "grad_norm": 1.103874956006416, + "learning_rate": 3.507624560168621e-07, + "loss": 0.7518, + "step": 14953 + }, + { + "epoch": 0.9180146720279935, + "grad_norm": 1.1138371251989754, + "learning_rate": 3.502406447375428e-07, + "loss": 0.695, + "step": 14954 + }, + { + "epoch": 0.91807606126646, + "grad_norm": 1.0299281113739638, + "learning_rate": 3.4971921496482097e-07, + "loss": 0.6865, + "step": 14955 + }, + { + "epoch": 0.9181374505049265, + "grad_norm": 1.1183287032293163, + "learning_rate": 3.4919816671931117e-07, + "loss": 0.7247, + "step": 14956 + }, + { + "epoch": 0.918198839743393, + "grad_norm": 1.060082106370807, + "learning_rate": 3.486775000216158e-07, + "loss": 0.7245, + "step": 14957 + }, + { + "epoch": 0.9182602289818594, + "grad_norm": 0.5916579436694706, + "learning_rate": 3.4815721489231736e-07, + "loss": 0.6319, + "step": 14958 + }, + { + "epoch": 0.918321618220326, + "grad_norm": 1.0067963090217273, + "learning_rate": 3.4763731135198374e-07, + "loss": 0.7328, + "step": 14959 + }, + { + "epoch": 0.9183830074587924, + "grad_norm": 1.0244523723590901, + "learning_rate": 3.47117789421173e-07, + "loss": 0.7157, + "step": 14960 + }, + { + "epoch": 0.918444396697259, + "grad_norm": 0.9794061227250145, + "learning_rate": 3.465986491204243e-07, + "loss": 0.6903, + "step": 14961 + }, + { + "epoch": 0.9185057859357255, + "grad_norm": 0.906416117366447, + "learning_rate": 3.4607989047026005e-07, + "loss": 0.706, + "step": 14962 + }, + { + "epoch": 0.918567175174192, + "grad_norm": 1.276849918526205, + "learning_rate": 3.455615134911905e-07, + "loss": 0.7162, + "step": 14963 + }, + { + "epoch": 0.9186285644126585, + "grad_norm": 0.9553360916751525, + "learning_rate": 3.450435182037104e-07, + "loss": 0.7008, + "step": 14964 + }, + { + "epoch": 0.9186899536511249, + "grad_norm": 1.0267302373942349, + "learning_rate": 3.445259046282978e-07, + "loss": 0.7645, + "step": 14965 + }, + { + "epoch": 0.9187513428895915, + "grad_norm": 1.112281306982086, + "learning_rate": 3.440086727854175e-07, + "loss": 0.7124, + "step": 14966 + }, + { + "epoch": 0.9188127321280579, + "grad_norm": 1.112538968396919, + "learning_rate": 3.434918226955186e-07, + "loss": 0.7094, + "step": 14967 + }, + { + "epoch": 0.9188741213665245, + "grad_norm": 0.979618868203516, + "learning_rate": 3.4297535437903486e-07, + "loss": 0.6944, + "step": 14968 + }, + { + "epoch": 0.9189355106049909, + "grad_norm": 1.025879563664869, + "learning_rate": 3.424592678563843e-07, + "loss": 0.7475, + "step": 14969 + }, + { + "epoch": 0.9189968998434574, + "grad_norm": 1.0893143086303676, + "learning_rate": 3.419435631479695e-07, + "loss": 0.7368, + "step": 14970 + }, + { + "epoch": 0.9190582890819239, + "grad_norm": 1.1164509201380401, + "learning_rate": 3.41428240274182e-07, + "loss": 0.688, + "step": 14971 + }, + { + "epoch": 0.9191196783203904, + "grad_norm": 1.0204837888763163, + "learning_rate": 3.409132992553954e-07, + "loss": 0.7242, + "step": 14972 + }, + { + "epoch": 0.919181067558857, + "grad_norm": 1.0255373968666317, + "learning_rate": 3.403987401119635e-07, + "loss": 0.7275, + "step": 14973 + }, + { + "epoch": 0.9192424567973234, + "grad_norm": 1.0629131464758363, + "learning_rate": 3.398845628642344e-07, + "loss": 0.6778, + "step": 14974 + }, + { + "epoch": 0.91930384603579, + "grad_norm": 0.9510700533424972, + "learning_rate": 3.393707675325342e-07, + "loss": 0.7352, + "step": 14975 + }, + { + "epoch": 0.9193652352742564, + "grad_norm": 1.1014578397948958, + "learning_rate": 3.3885735413717644e-07, + "loss": 0.7605, + "step": 14976 + }, + { + "epoch": 0.919426624512723, + "grad_norm": 0.9973115020017905, + "learning_rate": 3.383443226984584e-07, + "loss": 0.6822, + "step": 14977 + }, + { + "epoch": 0.9194880137511894, + "grad_norm": 1.018728548857509, + "learning_rate": 3.378316732366638e-07, + "loss": 0.7152, + "step": 14978 + }, + { + "epoch": 0.9195494029896559, + "grad_norm": 1.0494513685749256, + "learning_rate": 3.373194057720597e-07, + "loss": 0.7663, + "step": 14979 + }, + { + "epoch": 0.9196107922281224, + "grad_norm": 1.1955803540550327, + "learning_rate": 3.368075203248988e-07, + "loss": 0.7193, + "step": 14980 + }, + { + "epoch": 0.9196721814665889, + "grad_norm": 1.1181749537089436, + "learning_rate": 3.362960169154195e-07, + "loss": 0.7584, + "step": 14981 + }, + { + "epoch": 0.9197335707050555, + "grad_norm": 1.1062017438481786, + "learning_rate": 3.357848955638443e-07, + "loss": 0.7464, + "step": 14982 + }, + { + "epoch": 0.9197949599435219, + "grad_norm": 0.9339686010926928, + "learning_rate": 3.352741562903794e-07, + "loss": 0.7795, + "step": 14983 + }, + { + "epoch": 0.9198563491819884, + "grad_norm": 1.1121821639394835, + "learning_rate": 3.3476379911521753e-07, + "loss": 0.7199, + "step": 14984 + }, + { + "epoch": 0.9199177384204549, + "grad_norm": 1.0309435656380805, + "learning_rate": 3.3425382405853577e-07, + "loss": 0.7113, + "step": 14985 + }, + { + "epoch": 0.9199791276589214, + "grad_norm": 0.9539320029860979, + "learning_rate": 3.3374423114049706e-07, + "loss": 0.6647, + "step": 14986 + }, + { + "epoch": 0.9200405168973879, + "grad_norm": 0.9573946563695547, + "learning_rate": 3.3323502038124733e-07, + "loss": 0.7259, + "step": 14987 + }, + { + "epoch": 0.9201019061358544, + "grad_norm": 1.0002372814767542, + "learning_rate": 3.3272619180091946e-07, + "loss": 0.7108, + "step": 14988 + }, + { + "epoch": 0.9201632953743208, + "grad_norm": 1.0276721362473247, + "learning_rate": 3.322177454196285e-07, + "loss": 0.7018, + "step": 14989 + }, + { + "epoch": 0.9202246846127874, + "grad_norm": 1.0716548431534882, + "learning_rate": 3.317096812574783e-07, + "loss": 0.7267, + "step": 14990 + }, + { + "epoch": 0.9202860738512538, + "grad_norm": 1.126322408984818, + "learning_rate": 3.3120199933455276e-07, + "loss": 0.6704, + "step": 14991 + }, + { + "epoch": 0.9203474630897204, + "grad_norm": 1.017384821356142, + "learning_rate": 3.3069469967092485e-07, + "loss": 0.737, + "step": 14992 + }, + { + "epoch": 0.9204088523281869, + "grad_norm": 1.0060494334493733, + "learning_rate": 3.301877822866506e-07, + "loss": 0.7534, + "step": 14993 + }, + { + "epoch": 0.9204702415666534, + "grad_norm": 1.0796164055757251, + "learning_rate": 3.2968124720177187e-07, + "loss": 0.8013, + "step": 14994 + }, + { + "epoch": 0.9205316308051199, + "grad_norm": 1.1151647948864425, + "learning_rate": 3.2917509443631147e-07, + "loss": 0.7328, + "step": 14995 + }, + { + "epoch": 0.9205930200435863, + "grad_norm": 1.0624522580570472, + "learning_rate": 3.286693240102856e-07, + "loss": 0.7166, + "step": 14996 + }, + { + "epoch": 0.9206544092820529, + "grad_norm": 1.020306265537892, + "learning_rate": 3.281639359436872e-07, + "loss": 0.6668, + "step": 14997 + }, + { + "epoch": 0.9207157985205193, + "grad_norm": 1.1264472119865458, + "learning_rate": 3.2765893025649475e-07, + "loss": 0.7601, + "step": 14998 + }, + { + "epoch": 0.9207771877589859, + "grad_norm": 1.027934442734944, + "learning_rate": 3.271543069686778e-07, + "loss": 0.7318, + "step": 14999 + }, + { + "epoch": 0.9208385769974523, + "grad_norm": 0.9863379152678851, + "learning_rate": 3.266500661001848e-07, + "loss": 0.7158, + "step": 15000 + }, + { + "epoch": 0.9208999662359189, + "grad_norm": 1.1125270574048538, + "learning_rate": 3.2614620767095094e-07, + "loss": 0.6926, + "step": 15001 + }, + { + "epoch": 0.9209613554743853, + "grad_norm": 0.9803206745467882, + "learning_rate": 3.25642731700897e-07, + "loss": 0.7067, + "step": 15002 + }, + { + "epoch": 0.9210227447128518, + "grad_norm": 1.0430229176984807, + "learning_rate": 3.251396382099281e-07, + "loss": 0.7618, + "step": 15003 + }, + { + "epoch": 0.9210841339513184, + "grad_norm": 1.1074838055322005, + "learning_rate": 3.2463692721793506e-07, + "loss": 0.762, + "step": 15004 + }, + { + "epoch": 0.9211455231897848, + "grad_norm": 1.1876270717824728, + "learning_rate": 3.241345987447908e-07, + "loss": 0.7467, + "step": 15005 + }, + { + "epoch": 0.9212069124282514, + "grad_norm": 1.1830453734620303, + "learning_rate": 3.236326528103562e-07, + "loss": 0.6948, + "step": 15006 + }, + { + "epoch": 0.9212683016667178, + "grad_norm": 1.1260014470547421, + "learning_rate": 3.2313108943447527e-07, + "loss": 0.7849, + "step": 15007 + }, + { + "epoch": 0.9213296909051844, + "grad_norm": 1.1460523958535005, + "learning_rate": 3.2262990863697884e-07, + "loss": 0.7571, + "step": 15008 + }, + { + "epoch": 0.9213910801436508, + "grad_norm": 0.9240977879941282, + "learning_rate": 3.221291104376789e-07, + "loss": 0.7331, + "step": 15009 + }, + { + "epoch": 0.9214524693821173, + "grad_norm": 0.931959202511246, + "learning_rate": 3.216286948563763e-07, + "loss": 0.7053, + "step": 15010 + }, + { + "epoch": 0.9215138586205838, + "grad_norm": 1.124815026048801, + "learning_rate": 3.211286619128573e-07, + "loss": 0.7362, + "step": 15011 + }, + { + "epoch": 0.9215752478590503, + "grad_norm": 0.9842494156122624, + "learning_rate": 3.206290116268862e-07, + "loss": 0.7258, + "step": 15012 + }, + { + "epoch": 0.9216366370975168, + "grad_norm": 1.0481779279163106, + "learning_rate": 3.201297440182194e-07, + "loss": 0.6801, + "step": 15013 + }, + { + "epoch": 0.9216980263359833, + "grad_norm": 1.114703672207004, + "learning_rate": 3.196308591065966e-07, + "loss": 0.7051, + "step": 15014 + }, + { + "epoch": 0.9217594155744498, + "grad_norm": 1.1176689611599755, + "learning_rate": 3.1913235691173885e-07, + "loss": 0.7364, + "step": 15015 + }, + { + "epoch": 0.9218208048129163, + "grad_norm": 1.001303777559471, + "learning_rate": 3.1863423745335687e-07, + "loss": 0.7707, + "step": 15016 + }, + { + "epoch": 0.9218821940513828, + "grad_norm": 0.9006146950011475, + "learning_rate": 3.1813650075114275e-07, + "loss": 0.7003, + "step": 15017 + }, + { + "epoch": 0.9219435832898493, + "grad_norm": 1.1173937700754943, + "learning_rate": 3.1763914682477525e-07, + "loss": 0.7167, + "step": 15018 + }, + { + "epoch": 0.9220049725283158, + "grad_norm": 1.1131580224638, + "learning_rate": 3.171421756939164e-07, + "loss": 0.7176, + "step": 15019 + }, + { + "epoch": 0.9220663617667822, + "grad_norm": 1.0128334304242397, + "learning_rate": 3.166455873782148e-07, + "loss": 0.7231, + "step": 15020 + }, + { + "epoch": 0.9221277510052488, + "grad_norm": 1.1400219140696424, + "learning_rate": 3.1614938189730495e-07, + "loss": 0.7921, + "step": 15021 + }, + { + "epoch": 0.9221891402437152, + "grad_norm": 1.0448636420908002, + "learning_rate": 3.156535592708021e-07, + "loss": 0.7359, + "step": 15022 + }, + { + "epoch": 0.9222505294821818, + "grad_norm": 1.0641342661799116, + "learning_rate": 3.1515811951830844e-07, + "loss": 0.776, + "step": 15023 + }, + { + "epoch": 0.9223119187206482, + "grad_norm": 1.0058201102951776, + "learning_rate": 3.146630626594138e-07, + "loss": 0.7106, + "step": 15024 + }, + { + "epoch": 0.9223733079591148, + "grad_norm": 1.0032413167491927, + "learning_rate": 3.1416838871368925e-07, + "loss": 0.6606, + "step": 15025 + }, + { + "epoch": 0.9224346971975813, + "grad_norm": 1.1689065503182698, + "learning_rate": 3.1367409770069134e-07, + "loss": 0.8018, + "step": 15026 + }, + { + "epoch": 0.9224960864360477, + "grad_norm": 1.1791685213255196, + "learning_rate": 3.1318018963996224e-07, + "loss": 0.7077, + "step": 15027 + }, + { + "epoch": 0.9225574756745143, + "grad_norm": 1.0201051324587773, + "learning_rate": 3.126866645510296e-07, + "loss": 0.706, + "step": 15028 + }, + { + "epoch": 0.9226188649129807, + "grad_norm": 1.089099285612158, + "learning_rate": 3.121935224534034e-07, + "loss": 0.6895, + "step": 15029 + }, + { + "epoch": 0.9226802541514473, + "grad_norm": 1.0036372831227263, + "learning_rate": 3.117007633665825e-07, + "loss": 0.7176, + "step": 15030 + }, + { + "epoch": 0.9227416433899137, + "grad_norm": 1.177199956163755, + "learning_rate": 3.112083873100469e-07, + "loss": 0.741, + "step": 15031 + }, + { + "epoch": 0.9228030326283803, + "grad_norm": 1.0635921401541, + "learning_rate": 3.1071639430326206e-07, + "loss": 0.7345, + "step": 15032 + }, + { + "epoch": 0.9228644218668467, + "grad_norm": 0.9074800040186145, + "learning_rate": 3.1022478436568135e-07, + "loss": 0.696, + "step": 15033 + }, + { + "epoch": 0.9229258111053132, + "grad_norm": 0.9466536396638022, + "learning_rate": 3.0973355751673816e-07, + "loss": 0.7027, + "step": 15034 + }, + { + "epoch": 0.9229872003437798, + "grad_norm": 1.1337310467630537, + "learning_rate": 3.092427137758547e-07, + "loss": 0.7288, + "step": 15035 + }, + { + "epoch": 0.9230485895822462, + "grad_norm": 1.0444430099374362, + "learning_rate": 3.087522531624387e-07, + "loss": 0.7197, + "step": 15036 + }, + { + "epoch": 0.9231099788207128, + "grad_norm": 0.9519908071224256, + "learning_rate": 3.0826217569587593e-07, + "loss": 0.7092, + "step": 15037 + }, + { + "epoch": 0.9231713680591792, + "grad_norm": 1.0541501162983835, + "learning_rate": 3.077724813955463e-07, + "loss": 0.7165, + "step": 15038 + }, + { + "epoch": 0.9232327572976458, + "grad_norm": 1.0998068836121442, + "learning_rate": 3.0728317028080656e-07, + "loss": 0.7283, + "step": 15039 + }, + { + "epoch": 0.9232941465361122, + "grad_norm": 1.0175438921753324, + "learning_rate": 3.0679424237100466e-07, + "loss": 0.7179, + "step": 15040 + }, + { + "epoch": 0.9233555357745787, + "grad_norm": 1.0987631697671507, + "learning_rate": 3.0630569768546946e-07, + "loss": 0.7559, + "step": 15041 + }, + { + "epoch": 0.9234169250130452, + "grad_norm": 1.0038658587122604, + "learning_rate": 3.0581753624351454e-07, + "loss": 0.716, + "step": 15042 + }, + { + "epoch": 0.9234783142515117, + "grad_norm": 1.2208820319841207, + "learning_rate": 3.0532975806444096e-07, + "loss": 0.7266, + "step": 15043 + }, + { + "epoch": 0.9235397034899782, + "grad_norm": 0.9713737276245078, + "learning_rate": 3.0484236316753345e-07, + "loss": 0.7193, + "step": 15044 + }, + { + "epoch": 0.9236010927284447, + "grad_norm": 1.0511888856826657, + "learning_rate": 3.0435535157205877e-07, + "loss": 0.7603, + "step": 15045 + }, + { + "epoch": 0.9236624819669113, + "grad_norm": 1.088658989885853, + "learning_rate": 3.038687232972748e-07, + "loss": 0.7023, + "step": 15046 + }, + { + "epoch": 0.9237238712053777, + "grad_norm": 1.1124516264953959, + "learning_rate": 3.033824783624184e-07, + "loss": 0.7176, + "step": 15047 + }, + { + "epoch": 0.9237852604438442, + "grad_norm": 1.1502833767489677, + "learning_rate": 3.0289661678671314e-07, + "loss": 0.779, + "step": 15048 + }, + { + "epoch": 0.9238466496823107, + "grad_norm": 1.075569498560874, + "learning_rate": 3.024111385893691e-07, + "loss": 0.7352, + "step": 15049 + }, + { + "epoch": 0.9239080389207772, + "grad_norm": 1.0341891163834822, + "learning_rate": 3.019260437895788e-07, + "loss": 0.734, + "step": 15050 + }, + { + "epoch": 0.9239694281592437, + "grad_norm": 1.14232446750066, + "learning_rate": 3.0144133240652017e-07, + "loss": 0.7739, + "step": 15051 + }, + { + "epoch": 0.9240308173977102, + "grad_norm": 1.0755161169629839, + "learning_rate": 3.0095700445935793e-07, + "loss": 0.6875, + "step": 15052 + }, + { + "epoch": 0.9240922066361766, + "grad_norm": 1.0355325733579823, + "learning_rate": 3.004730599672401e-07, + "loss": 0.6933, + "step": 15053 + }, + { + "epoch": 0.9241535958746432, + "grad_norm": 1.0668445554395058, + "learning_rate": 2.9998949894929794e-07, + "loss": 0.6986, + "step": 15054 + }, + { + "epoch": 0.9242149851131096, + "grad_norm": 0.9802293901096881, + "learning_rate": 2.9950632142464965e-07, + "loss": 0.7147, + "step": 15055 + }, + { + "epoch": 0.9242763743515762, + "grad_norm": 1.093705507941567, + "learning_rate": 2.9902352741240094e-07, + "loss": 0.6863, + "step": 15056 + }, + { + "epoch": 0.9243377635900427, + "grad_norm": 1.1251363015323088, + "learning_rate": 2.9854111693163544e-07, + "loss": 0.696, + "step": 15057 + }, + { + "epoch": 0.9243991528285092, + "grad_norm": 0.8890705853819764, + "learning_rate": 2.9805909000142576e-07, + "loss": 0.7478, + "step": 15058 + }, + { + "epoch": 0.9244605420669757, + "grad_norm": 1.0366617110920708, + "learning_rate": 2.9757744664082875e-07, + "loss": 0.7157, + "step": 15059 + }, + { + "epoch": 0.9245219313054421, + "grad_norm": 1.0533091359679916, + "learning_rate": 2.970961868688893e-07, + "loss": 0.7421, + "step": 15060 + }, + { + "epoch": 0.9245833205439087, + "grad_norm": 1.0096268740607957, + "learning_rate": 2.966153107046332e-07, + "loss": 0.7664, + "step": 15061 + }, + { + "epoch": 0.9246447097823751, + "grad_norm": 1.0194784932453784, + "learning_rate": 2.961348181670698e-07, + "loss": 0.703, + "step": 15062 + }, + { + "epoch": 0.9247060990208417, + "grad_norm": 0.9284500154249973, + "learning_rate": 2.9565470927519715e-07, + "loss": 0.7292, + "step": 15063 + }, + { + "epoch": 0.9247674882593081, + "grad_norm": 1.193278070159097, + "learning_rate": 2.9517498404799674e-07, + "loss": 0.6864, + "step": 15064 + }, + { + "epoch": 0.9248288774977746, + "grad_norm": 0.9939818822064005, + "learning_rate": 2.946956425044334e-07, + "loss": 0.7198, + "step": 15065 + }, + { + "epoch": 0.9248902667362411, + "grad_norm": 1.0674061120943041, + "learning_rate": 2.9421668466345977e-07, + "loss": 0.7215, + "step": 15066 + }, + { + "epoch": 0.9249516559747076, + "grad_norm": 1.0318361475584634, + "learning_rate": 2.937381105440107e-07, + "loss": 0.7047, + "step": 15067 + }, + { + "epoch": 0.9250130452131742, + "grad_norm": 1.0194628080599526, + "learning_rate": 2.932599201650066e-07, + "loss": 0.7254, + "step": 15068 + }, + { + "epoch": 0.9250744344516406, + "grad_norm": 1.19395945303069, + "learning_rate": 2.927821135453535e-07, + "loss": 0.6951, + "step": 15069 + }, + { + "epoch": 0.9251358236901072, + "grad_norm": 1.2048157384512868, + "learning_rate": 2.923046907039395e-07, + "loss": 0.73, + "step": 15070 + }, + { + "epoch": 0.9251972129285736, + "grad_norm": 0.5957806557713798, + "learning_rate": 2.918276516596441e-07, + "loss": 0.6234, + "step": 15071 + }, + { + "epoch": 0.9252586021670401, + "grad_norm": 1.064146333409255, + "learning_rate": 2.9135099643132436e-07, + "loss": 0.7356, + "step": 15072 + }, + { + "epoch": 0.9253199914055066, + "grad_norm": 1.1415479337971528, + "learning_rate": 2.90874725037823e-07, + "loss": 0.7335, + "step": 15073 + }, + { + "epoch": 0.9253813806439731, + "grad_norm": 1.0594713139979646, + "learning_rate": 2.903988374979738e-07, + "loss": 0.733, + "step": 15074 + }, + { + "epoch": 0.9254427698824396, + "grad_norm": 1.0475888148801613, + "learning_rate": 2.8992333383058956e-07, + "loss": 0.7355, + "step": 15075 + }, + { + "epoch": 0.9255041591209061, + "grad_norm": 1.003187502519398, + "learning_rate": 2.894482140544663e-07, + "loss": 0.6834, + "step": 15076 + }, + { + "epoch": 0.9255655483593725, + "grad_norm": 1.0632613613632567, + "learning_rate": 2.889734781883935e-07, + "loss": 0.7149, + "step": 15077 + }, + { + "epoch": 0.9256269375978391, + "grad_norm": 1.0066141658697858, + "learning_rate": 2.884991262511361e-07, + "loss": 0.7393, + "step": 15078 + }, + { + "epoch": 0.9256883268363056, + "grad_norm": 1.0237060063084071, + "learning_rate": 2.8802515826144903e-07, + "loss": 0.6791, + "step": 15079 + }, + { + "epoch": 0.9257497160747721, + "grad_norm": 1.087394912515432, + "learning_rate": 2.875515742380708e-07, + "loss": 0.7476, + "step": 15080 + }, + { + "epoch": 0.9258111053132386, + "grad_norm": 1.14872999032015, + "learning_rate": 2.8707837419972516e-07, + "loss": 0.758, + "step": 15081 + }, + { + "epoch": 0.9258724945517051, + "grad_norm": 1.0464644375632048, + "learning_rate": 2.8660555816511947e-07, + "loss": 0.7247, + "step": 15082 + }, + { + "epoch": 0.9259338837901716, + "grad_norm": 1.0779813132975302, + "learning_rate": 2.861331261529476e-07, + "loss": 0.7625, + "step": 15083 + }, + { + "epoch": 0.925995273028638, + "grad_norm": 1.0330002532158031, + "learning_rate": 2.8566107818188473e-07, + "loss": 0.7628, + "step": 15084 + }, + { + "epoch": 0.9260566622671046, + "grad_norm": 1.0130789308901238, + "learning_rate": 2.85189414270598e-07, + "loss": 0.724, + "step": 15085 + }, + { + "epoch": 0.926118051505571, + "grad_norm": 0.9970712435923825, + "learning_rate": 2.8471813443773035e-07, + "loss": 0.725, + "step": 15086 + }, + { + "epoch": 0.9261794407440376, + "grad_norm": 0.9531277597259377, + "learning_rate": 2.842472387019157e-07, + "loss": 0.7382, + "step": 15087 + }, + { + "epoch": 0.9262408299825041, + "grad_norm": 1.036765866779637, + "learning_rate": 2.837767270817715e-07, + "loss": 0.7293, + "step": 15088 + }, + { + "epoch": 0.9263022192209706, + "grad_norm": 0.8879186375190757, + "learning_rate": 2.8330659959589944e-07, + "loss": 0.7621, + "step": 15089 + }, + { + "epoch": 0.9263636084594371, + "grad_norm": 1.0153497882460831, + "learning_rate": 2.8283685626288693e-07, + "loss": 0.6951, + "step": 15090 + }, + { + "epoch": 0.9264249976979035, + "grad_norm": 1.0592412773952202, + "learning_rate": 2.8236749710130353e-07, + "loss": 0.7274, + "step": 15091 + }, + { + "epoch": 0.9264863869363701, + "grad_norm": 1.053909172714821, + "learning_rate": 2.8189852212970657e-07, + "loss": 0.7201, + "step": 15092 + }, + { + "epoch": 0.9265477761748365, + "grad_norm": 0.9465563094781902, + "learning_rate": 2.81429931366638e-07, + "loss": 0.7618, + "step": 15093 + }, + { + "epoch": 0.9266091654133031, + "grad_norm": 0.5778983330225346, + "learning_rate": 2.809617248306207e-07, + "loss": 0.6574, + "step": 15094 + }, + { + "epoch": 0.9266705546517695, + "grad_norm": 0.9651374504856358, + "learning_rate": 2.8049390254016986e-07, + "loss": 0.7004, + "step": 15095 + }, + { + "epoch": 0.926731943890236, + "grad_norm": 1.0668871848019148, + "learning_rate": 2.8002646451377846e-07, + "loss": 0.6864, + "step": 15096 + }, + { + "epoch": 0.9267933331287025, + "grad_norm": 1.1164965910679499, + "learning_rate": 2.795594107699262e-07, + "loss": 0.7096, + "step": 15097 + }, + { + "epoch": 0.926854722367169, + "grad_norm": 1.1059566963063385, + "learning_rate": 2.790927413270783e-07, + "loss": 0.6694, + "step": 15098 + }, + { + "epoch": 0.9269161116056356, + "grad_norm": 1.0989473507240897, + "learning_rate": 2.7862645620368555e-07, + "loss": 0.776, + "step": 15099 + }, + { + "epoch": 0.926977500844102, + "grad_norm": 1.0362259257345787, + "learning_rate": 2.781605554181843e-07, + "loss": 0.7112, + "step": 15100 + }, + { + "epoch": 0.9270388900825686, + "grad_norm": 1.0093190160260714, + "learning_rate": 2.7769503898898985e-07, + "loss": 0.7317, + "step": 15101 + }, + { + "epoch": 0.927100279321035, + "grad_norm": 0.5969873781687914, + "learning_rate": 2.772299069345108e-07, + "loss": 0.654, + "step": 15102 + }, + { + "epoch": 0.9271616685595016, + "grad_norm": 1.1312444369005714, + "learning_rate": 2.7676515927313464e-07, + "loss": 0.7554, + "step": 15103 + }, + { + "epoch": 0.927223057797968, + "grad_norm": 1.0210418664872696, + "learning_rate": 2.7630079602323447e-07, + "loss": 0.7463, + "step": 15104 + }, + { + "epoch": 0.9272844470364345, + "grad_norm": 1.0533477015691879, + "learning_rate": 2.7583681720317e-07, + "loss": 0.7382, + "step": 15105 + }, + { + "epoch": 0.927345836274901, + "grad_norm": 1.0337912553474766, + "learning_rate": 2.7537322283128443e-07, + "loss": 0.7511, + "step": 15106 + }, + { + "epoch": 0.9274072255133675, + "grad_norm": 0.9957436246193009, + "learning_rate": 2.7491001292590745e-07, + "loss": 0.7169, + "step": 15107 + }, + { + "epoch": 0.927468614751834, + "grad_norm": 1.0329384753801742, + "learning_rate": 2.7444718750535006e-07, + "loss": 0.7242, + "step": 15108 + }, + { + "epoch": 0.9275300039903005, + "grad_norm": 1.0634256437329168, + "learning_rate": 2.739847465879097e-07, + "loss": 0.7399, + "step": 15109 + }, + { + "epoch": 0.927591393228767, + "grad_norm": 1.1279367245043574, + "learning_rate": 2.735226901918742e-07, + "loss": 0.7698, + "step": 15110 + }, + { + "epoch": 0.9276527824672335, + "grad_norm": 1.0532855315224317, + "learning_rate": 2.730610183355054e-07, + "loss": 0.7018, + "step": 15111 + }, + { + "epoch": 0.9277141717057, + "grad_norm": 1.0541153163053079, + "learning_rate": 2.725997310370576e-07, + "loss": 0.7287, + "step": 15112 + }, + { + "epoch": 0.9277755609441665, + "grad_norm": 1.1464197480741947, + "learning_rate": 2.7213882831476966e-07, + "loss": 0.7192, + "step": 15113 + }, + { + "epoch": 0.927836950182633, + "grad_norm": 1.1693709297435013, + "learning_rate": 2.716783101868614e-07, + "loss": 0.6826, + "step": 15114 + }, + { + "epoch": 0.9278983394210994, + "grad_norm": 1.0709589715367591, + "learning_rate": 2.712181766715394e-07, + "loss": 0.7663, + "step": 15115 + }, + { + "epoch": 0.927959728659566, + "grad_norm": 1.0176764221674182, + "learning_rate": 2.707584277869979e-07, + "loss": 0.7, + "step": 15116 + }, + { + "epoch": 0.9280211178980324, + "grad_norm": 1.0182975886056704, + "learning_rate": 2.702990635514102e-07, + "loss": 0.7143, + "step": 15117 + }, + { + "epoch": 0.928082507136499, + "grad_norm": 1.0287281206144891, + "learning_rate": 2.698400839829385e-07, + "loss": 0.6869, + "step": 15118 + }, + { + "epoch": 0.9281438963749654, + "grad_norm": 1.1698457694853894, + "learning_rate": 2.6938148909972817e-07, + "loss": 0.7383, + "step": 15119 + }, + { + "epoch": 0.928205285613432, + "grad_norm": 0.9951393796186917, + "learning_rate": 2.6892327891991254e-07, + "loss": 0.7634, + "step": 15120 + }, + { + "epoch": 0.9282666748518985, + "grad_norm": 1.0332448652416628, + "learning_rate": 2.684654534616049e-07, + "loss": 0.7645, + "step": 15121 + }, + { + "epoch": 0.928328064090365, + "grad_norm": 1.0417878059339372, + "learning_rate": 2.6800801274290525e-07, + "loss": 0.6978, + "step": 15122 + }, + { + "epoch": 0.9283894533288315, + "grad_norm": 1.0271598501372772, + "learning_rate": 2.675509567818979e-07, + "loss": 0.7211, + "step": 15123 + }, + { + "epoch": 0.9284508425672979, + "grad_norm": 1.1154533906700168, + "learning_rate": 2.6709428559665517e-07, + "loss": 0.7523, + "step": 15124 + }, + { + "epoch": 0.9285122318057645, + "grad_norm": 1.00088071781449, + "learning_rate": 2.666379992052315e-07, + "loss": 0.6803, + "step": 15125 + }, + { + "epoch": 0.9285736210442309, + "grad_norm": 1.0150366026668745, + "learning_rate": 2.661820976256635e-07, + "loss": 0.7429, + "step": 15126 + }, + { + "epoch": 0.9286350102826975, + "grad_norm": 1.1456225028918863, + "learning_rate": 2.6572658087597794e-07, + "loss": 0.7658, + "step": 15127 + }, + { + "epoch": 0.9286963995211639, + "grad_norm": 0.9176164109225946, + "learning_rate": 2.6527144897418366e-07, + "loss": 0.694, + "step": 15128 + }, + { + "epoch": 0.9287577887596304, + "grad_norm": 1.1491628594079675, + "learning_rate": 2.6481670193827413e-07, + "loss": 0.7411, + "step": 15129 + }, + { + "epoch": 0.9288191779980969, + "grad_norm": 1.0394633828824338, + "learning_rate": 2.643623397862272e-07, + "loss": 0.7353, + "step": 15130 + }, + { + "epoch": 0.9288805672365634, + "grad_norm": 0.9891562703893777, + "learning_rate": 2.639083625360073e-07, + "loss": 0.7272, + "step": 15131 + }, + { + "epoch": 0.92894195647503, + "grad_norm": 1.015789800239814, + "learning_rate": 2.6345477020556233e-07, + "loss": 0.7145, + "step": 15132 + }, + { + "epoch": 0.9290033457134964, + "grad_norm": 0.9768831086341668, + "learning_rate": 2.630015628128235e-07, + "loss": 0.7464, + "step": 15133 + }, + { + "epoch": 0.929064734951963, + "grad_norm": 1.0014486723963092, + "learning_rate": 2.62548740375711e-07, + "loss": 0.7234, + "step": 15134 + }, + { + "epoch": 0.9291261241904294, + "grad_norm": 0.985377243675784, + "learning_rate": 2.620963029121271e-07, + "loss": 0.7288, + "step": 15135 + }, + { + "epoch": 0.9291875134288959, + "grad_norm": 1.1643756609571612, + "learning_rate": 2.6164425043995856e-07, + "loss": 0.7661, + "step": 15136 + }, + { + "epoch": 0.9292489026673624, + "grad_norm": 1.057098436087726, + "learning_rate": 2.611925829770745e-07, + "loss": 0.7179, + "step": 15137 + }, + { + "epoch": 0.9293102919058289, + "grad_norm": 1.0967059401691264, + "learning_rate": 2.6074130054133616e-07, + "loss": 0.7499, + "step": 15138 + }, + { + "epoch": 0.9293716811442954, + "grad_norm": 0.9963405927024336, + "learning_rate": 2.6029040315058487e-07, + "loss": 0.6903, + "step": 15139 + }, + { + "epoch": 0.9294330703827619, + "grad_norm": 1.0709786329744844, + "learning_rate": 2.5983989082264295e-07, + "loss": 0.6843, + "step": 15140 + }, + { + "epoch": 0.9294944596212285, + "grad_norm": 1.1253179145362142, + "learning_rate": 2.593897635753262e-07, + "loss": 0.7329, + "step": 15141 + }, + { + "epoch": 0.9295558488596949, + "grad_norm": 1.1073305099285842, + "learning_rate": 2.5894002142642813e-07, + "loss": 0.7549, + "step": 15142 + }, + { + "epoch": 0.9296172380981614, + "grad_norm": 0.9546668490136921, + "learning_rate": 2.5849066439372903e-07, + "loss": 0.7105, + "step": 15143 + }, + { + "epoch": 0.9296786273366279, + "grad_norm": 0.949642666569323, + "learning_rate": 2.580416924949958e-07, + "loss": 0.7182, + "step": 15144 + }, + { + "epoch": 0.9297400165750944, + "grad_norm": 1.006775648975269, + "learning_rate": 2.575931057479786e-07, + "loss": 0.7179, + "step": 15145 + }, + { + "epoch": 0.9298014058135609, + "grad_norm": 1.1489158746842691, + "learning_rate": 2.5714490417041105e-07, + "loss": 0.7399, + "step": 15146 + }, + { + "epoch": 0.9298627950520274, + "grad_norm": 1.1025463936008417, + "learning_rate": 2.5669708778001457e-07, + "loss": 0.7516, + "step": 15147 + }, + { + "epoch": 0.9299241842904938, + "grad_norm": 1.0672679852858549, + "learning_rate": 2.562496565944916e-07, + "loss": 0.7063, + "step": 15148 + }, + { + "epoch": 0.9299855735289604, + "grad_norm": 0.9608578504637758, + "learning_rate": 2.558026106315348e-07, + "loss": 0.6889, + "step": 15149 + }, + { + "epoch": 0.9300469627674268, + "grad_norm": 1.0992770862777494, + "learning_rate": 2.5535594990881654e-07, + "loss": 0.7237, + "step": 15150 + }, + { + "epoch": 0.9301083520058934, + "grad_norm": 1.0279251528332012, + "learning_rate": 2.5490967444399273e-07, + "loss": 0.6758, + "step": 15151 + }, + { + "epoch": 0.9301697412443599, + "grad_norm": 1.147915031971484, + "learning_rate": 2.5446378425471263e-07, + "loss": 0.7266, + "step": 15152 + }, + { + "epoch": 0.9302311304828264, + "grad_norm": 1.0004751013254005, + "learning_rate": 2.5401827935860103e-07, + "loss": 0.7189, + "step": 15153 + }, + { + "epoch": 0.9302925197212929, + "grad_norm": 1.059286765344427, + "learning_rate": 2.5357315977327267e-07, + "loss": 0.7081, + "step": 15154 + }, + { + "epoch": 0.9303539089597593, + "grad_norm": 1.0030065941917359, + "learning_rate": 2.5312842551632465e-07, + "loss": 0.6854, + "step": 15155 + }, + { + "epoch": 0.9304152981982259, + "grad_norm": 1.0715608441140327, + "learning_rate": 2.5268407660533953e-07, + "loss": 0.7218, + "step": 15156 + }, + { + "epoch": 0.9304766874366923, + "grad_norm": 1.0375560500314278, + "learning_rate": 2.522401130578855e-07, + "loss": 0.6992, + "step": 15157 + }, + { + "epoch": 0.9305380766751589, + "grad_norm": 1.203860162454124, + "learning_rate": 2.51796534891513e-07, + "loss": 0.7033, + "step": 15158 + }, + { + "epoch": 0.9305994659136253, + "grad_norm": 1.0503467384953489, + "learning_rate": 2.513533421237635e-07, + "loss": 0.7966, + "step": 15159 + }, + { + "epoch": 0.9306608551520918, + "grad_norm": 1.0882000957174431, + "learning_rate": 2.509105347721541e-07, + "loss": 0.7543, + "step": 15160 + }, + { + "epoch": 0.9307222443905583, + "grad_norm": 1.1476155999112292, + "learning_rate": 2.5046811285419305e-07, + "loss": 0.7446, + "step": 15161 + }, + { + "epoch": 0.9307836336290248, + "grad_norm": 1.111056697951285, + "learning_rate": 2.5002607638737075e-07, + "loss": 0.7222, + "step": 15162 + }, + { + "epoch": 0.9308450228674914, + "grad_norm": 0.9572940600343692, + "learning_rate": 2.4958442538916436e-07, + "loss": 0.705, + "step": 15163 + }, + { + "epoch": 0.9309064121059578, + "grad_norm": 1.0215787439192583, + "learning_rate": 2.4914315987703664e-07, + "loss": 0.6908, + "step": 15164 + }, + { + "epoch": 0.9309678013444244, + "grad_norm": 1.0945066454769103, + "learning_rate": 2.487022798684291e-07, + "loss": 0.7372, + "step": 15165 + }, + { + "epoch": 0.9310291905828908, + "grad_norm": 1.0207596344743495, + "learning_rate": 2.482617853807745e-07, + "loss": 0.7144, + "step": 15166 + }, + { + "epoch": 0.9310905798213573, + "grad_norm": 1.0790293269006392, + "learning_rate": 2.478216764314878e-07, + "loss": 0.7652, + "step": 15167 + }, + { + "epoch": 0.9311519690598238, + "grad_norm": 1.102676767616597, + "learning_rate": 2.4738195303796844e-07, + "loss": 0.6566, + "step": 15168 + }, + { + "epoch": 0.9312133582982903, + "grad_norm": 1.1253612938746114, + "learning_rate": 2.469426152176013e-07, + "loss": 0.7443, + "step": 15169 + }, + { + "epoch": 0.9312747475367568, + "grad_norm": 1.1208644459842347, + "learning_rate": 2.4650366298775486e-07, + "loss": 0.736, + "step": 15170 + }, + { + "epoch": 0.9313361367752233, + "grad_norm": 1.1491234140958237, + "learning_rate": 2.460650963657851e-07, + "loss": 0.7197, + "step": 15171 + }, + { + "epoch": 0.9313975260136897, + "grad_norm": 0.9970228024387876, + "learning_rate": 2.456269153690294e-07, + "loss": 0.7727, + "step": 15172 + }, + { + "epoch": 0.9314589152521563, + "grad_norm": 0.9632121312627105, + "learning_rate": 2.4518912001481045e-07, + "loss": 0.6833, + "step": 15173 + }, + { + "epoch": 0.9315203044906228, + "grad_norm": 1.064924370243293, + "learning_rate": 2.4475171032044e-07, + "loss": 0.7495, + "step": 15174 + }, + { + "epoch": 0.9315816937290893, + "grad_norm": 1.0009061797957033, + "learning_rate": 2.443146863032086e-07, + "loss": 0.7768, + "step": 15175 + }, + { + "epoch": 0.9316430829675558, + "grad_norm": 1.1780537813326537, + "learning_rate": 2.438780479803937e-07, + "loss": 0.7814, + "step": 15176 + }, + { + "epoch": 0.9317044722060223, + "grad_norm": 1.0293749119873548, + "learning_rate": 2.4344179536925916e-07, + "loss": 0.7198, + "step": 15177 + }, + { + "epoch": 0.9317658614444888, + "grad_norm": 1.0155278125972849, + "learning_rate": 2.430059284870534e-07, + "loss": 0.6719, + "step": 15178 + }, + { + "epoch": 0.9318272506829552, + "grad_norm": 1.0556062630938268, + "learning_rate": 2.425704473510071e-07, + "loss": 0.7123, + "step": 15179 + }, + { + "epoch": 0.9318886399214218, + "grad_norm": 1.145592247462845, + "learning_rate": 2.421353519783365e-07, + "loss": 0.7776, + "step": 15180 + }, + { + "epoch": 0.9319500291598882, + "grad_norm": 1.1013058567099352, + "learning_rate": 2.417006423862445e-07, + "loss": 0.7498, + "step": 15181 + }, + { + "epoch": 0.9320114183983548, + "grad_norm": 1.0670152526658352, + "learning_rate": 2.412663185919173e-07, + "loss": 0.741, + "step": 15182 + }, + { + "epoch": 0.9320728076368212, + "grad_norm": 0.9929629227323713, + "learning_rate": 2.4083238061252565e-07, + "loss": 0.7627, + "step": 15183 + }, + { + "epoch": 0.9321341968752878, + "grad_norm": 1.0704896380580697, + "learning_rate": 2.40398828465227e-07, + "loss": 0.7685, + "step": 15184 + }, + { + "epoch": 0.9321955861137543, + "grad_norm": 1.0532276954873583, + "learning_rate": 2.3996566216715977e-07, + "loss": 0.7424, + "step": 15185 + }, + { + "epoch": 0.9322569753522207, + "grad_norm": 1.0834733062582664, + "learning_rate": 2.3953288173545033e-07, + "loss": 0.7754, + "step": 15186 + }, + { + "epoch": 0.9323183645906873, + "grad_norm": 0.9196064209099644, + "learning_rate": 2.3910048718720713e-07, + "loss": 0.7483, + "step": 15187 + }, + { + "epoch": 0.9323797538291537, + "grad_norm": 0.9425218612775511, + "learning_rate": 2.386684785395288e-07, + "loss": 0.7197, + "step": 15188 + }, + { + "epoch": 0.9324411430676203, + "grad_norm": 1.0055424355024507, + "learning_rate": 2.3823685580949273e-07, + "loss": 0.7517, + "step": 15189 + }, + { + "epoch": 0.9325025323060867, + "grad_norm": 1.1146133468214625, + "learning_rate": 2.37805619014162e-07, + "loss": 0.6995, + "step": 15190 + }, + { + "epoch": 0.9325639215445533, + "grad_norm": 1.0360166387684278, + "learning_rate": 2.3737476817058735e-07, + "loss": 0.7152, + "step": 15191 + }, + { + "epoch": 0.9326253107830197, + "grad_norm": 1.0539589736064219, + "learning_rate": 2.3694430329580298e-07, + "loss": 0.728, + "step": 15192 + }, + { + "epoch": 0.9326867000214862, + "grad_norm": 0.9937564678524629, + "learning_rate": 2.3651422440682637e-07, + "loss": 0.719, + "step": 15193 + }, + { + "epoch": 0.9327480892599528, + "grad_norm": 1.1270192064284, + "learning_rate": 2.3608453152066057e-07, + "loss": 0.7122, + "step": 15194 + }, + { + "epoch": 0.9328094784984192, + "grad_norm": 1.0750531437475488, + "learning_rate": 2.3565522465429536e-07, + "loss": 0.7497, + "step": 15195 + }, + { + "epoch": 0.9328708677368858, + "grad_norm": 1.056720158632465, + "learning_rate": 2.3522630382470268e-07, + "loss": 0.7808, + "step": 15196 + }, + { + "epoch": 0.9329322569753522, + "grad_norm": 1.051982049426024, + "learning_rate": 2.347977690488379e-07, + "loss": 0.7344, + "step": 15197 + }, + { + "epoch": 0.9329936462138188, + "grad_norm": 0.9893597148969464, + "learning_rate": 2.343696203436474e-07, + "loss": 0.7059, + "step": 15198 + }, + { + "epoch": 0.9330550354522852, + "grad_norm": 1.1063027604318239, + "learning_rate": 2.339418577260566e-07, + "loss": 0.7488, + "step": 15199 + }, + { + "epoch": 0.9331164246907517, + "grad_norm": 1.1677910765243846, + "learning_rate": 2.3351448121297527e-07, + "loss": 0.6683, + "step": 15200 + }, + { + "epoch": 0.9331778139292182, + "grad_norm": 1.2922915887236275, + "learning_rate": 2.33087490821301e-07, + "loss": 0.7359, + "step": 15201 + }, + { + "epoch": 0.9332392031676847, + "grad_norm": 0.9945711731534015, + "learning_rate": 2.3266088656791585e-07, + "loss": 0.6753, + "step": 15202 + }, + { + "epoch": 0.9333005924061512, + "grad_norm": 1.0613573929299163, + "learning_rate": 2.3223466846968634e-07, + "loss": 0.7089, + "step": 15203 + }, + { + "epoch": 0.9333619816446177, + "grad_norm": 0.8627344916506245, + "learning_rate": 2.318088365434601e-07, + "loss": 0.7187, + "step": 15204 + }, + { + "epoch": 0.9334233708830842, + "grad_norm": 0.5988497726523518, + "learning_rate": 2.3138339080607585e-07, + "loss": 0.6343, + "step": 15205 + }, + { + "epoch": 0.9334847601215507, + "grad_norm": 0.9290091793111912, + "learning_rate": 2.3095833127435242e-07, + "loss": 0.7258, + "step": 15206 + }, + { + "epoch": 0.9335461493600172, + "grad_norm": 1.0234557112737692, + "learning_rate": 2.3053365796509408e-07, + "loss": 0.7536, + "step": 15207 + }, + { + "epoch": 0.9336075385984837, + "grad_norm": 1.1216067943087178, + "learning_rate": 2.3010937089509188e-07, + "loss": 0.7679, + "step": 15208 + }, + { + "epoch": 0.9336689278369502, + "grad_norm": 0.8051599253159633, + "learning_rate": 2.2968547008111796e-07, + "loss": 0.6692, + "step": 15209 + }, + { + "epoch": 0.9337303170754166, + "grad_norm": 1.0475687064137382, + "learning_rate": 2.2926195553993334e-07, + "loss": 0.6913, + "step": 15210 + }, + { + "epoch": 0.9337917063138832, + "grad_norm": 1.0848595710188305, + "learning_rate": 2.2883882728828243e-07, + "loss": 0.7084, + "step": 15211 + }, + { + "epoch": 0.9338530955523496, + "grad_norm": 1.0830474012748927, + "learning_rate": 2.2841608534288962e-07, + "loss": 0.7506, + "step": 15212 + }, + { + "epoch": 0.9339144847908162, + "grad_norm": 1.0407591312456461, + "learning_rate": 2.2799372972047372e-07, + "loss": 0.683, + "step": 15213 + }, + { + "epoch": 0.9339758740292826, + "grad_norm": 1.0207825595481703, + "learning_rate": 2.275717604377292e-07, + "loss": 0.7729, + "step": 15214 + }, + { + "epoch": 0.9340372632677492, + "grad_norm": 1.0821228129153322, + "learning_rate": 2.271501775113394e-07, + "loss": 0.757, + "step": 15215 + }, + { + "epoch": 0.9340986525062157, + "grad_norm": 1.0603699181254618, + "learning_rate": 2.2672898095797203e-07, + "loss": 0.7603, + "step": 15216 + }, + { + "epoch": 0.9341600417446821, + "grad_norm": 1.0654275976503167, + "learning_rate": 2.2630817079427936e-07, + "loss": 0.7532, + "step": 15217 + }, + { + "epoch": 0.9342214309831487, + "grad_norm": 1.141385316527281, + "learning_rate": 2.2588774703689808e-07, + "loss": 0.7681, + "step": 15218 + }, + { + "epoch": 0.9342828202216151, + "grad_norm": 1.1014571280916952, + "learning_rate": 2.2546770970244937e-07, + "loss": 0.748, + "step": 15219 + }, + { + "epoch": 0.9343442094600817, + "grad_norm": 0.9252228042929709, + "learning_rate": 2.25048058807541e-07, + "loss": 0.7217, + "step": 15220 + }, + { + "epoch": 0.9344055986985481, + "grad_norm": 1.1411178437193428, + "learning_rate": 2.2462879436876195e-07, + "loss": 0.7358, + "step": 15221 + }, + { + "epoch": 0.9344669879370147, + "grad_norm": 1.0156650759434402, + "learning_rate": 2.2420991640268897e-07, + "loss": 0.6909, + "step": 15222 + }, + { + "epoch": 0.9345283771754811, + "grad_norm": 1.0017871703590753, + "learning_rate": 2.2379142492588324e-07, + "loss": 0.728, + "step": 15223 + }, + { + "epoch": 0.9345897664139476, + "grad_norm": 1.02958106550671, + "learning_rate": 2.2337331995488932e-07, + "loss": 0.6966, + "step": 15224 + }, + { + "epoch": 0.9346511556524141, + "grad_norm": 0.999726171834699, + "learning_rate": 2.229556015062373e-07, + "loss": 0.6514, + "step": 15225 + }, + { + "epoch": 0.9347125448908806, + "grad_norm": 1.1528525722798066, + "learning_rate": 2.2253826959643955e-07, + "loss": 0.7892, + "step": 15226 + }, + { + "epoch": 0.9347739341293472, + "grad_norm": 1.0766635400391613, + "learning_rate": 2.221213242419995e-07, + "loss": 0.7274, + "step": 15227 + }, + { + "epoch": 0.9348353233678136, + "grad_norm": 1.1714661540021982, + "learning_rate": 2.2170476545940066e-07, + "loss": 0.7236, + "step": 15228 + }, + { + "epoch": 0.9348967126062802, + "grad_norm": 1.1928988205951307, + "learning_rate": 2.2128859326510765e-07, + "loss": 0.6667, + "step": 15229 + }, + { + "epoch": 0.9349581018447466, + "grad_norm": 1.0157061682087796, + "learning_rate": 2.208728076755773e-07, + "loss": 0.7277, + "step": 15230 + }, + { + "epoch": 0.9350194910832131, + "grad_norm": 1.044050390216836, + "learning_rate": 2.2045740870724863e-07, + "loss": 0.7327, + "step": 15231 + }, + { + "epoch": 0.9350808803216796, + "grad_norm": 1.0035637221415594, + "learning_rate": 2.200423963765419e-07, + "loss": 0.7101, + "step": 15232 + }, + { + "epoch": 0.9351422695601461, + "grad_norm": 1.2086183149559664, + "learning_rate": 2.196277706998673e-07, + "loss": 0.7005, + "step": 15233 + }, + { + "epoch": 0.9352036587986126, + "grad_norm": 0.998925628559404, + "learning_rate": 2.1921353169361616e-07, + "loss": 0.7549, + "step": 15234 + }, + { + "epoch": 0.9352650480370791, + "grad_norm": 1.127610794220254, + "learning_rate": 2.1879967937416423e-07, + "loss": 0.7163, + "step": 15235 + }, + { + "epoch": 0.9353264372755455, + "grad_norm": 1.0014534546547555, + "learning_rate": 2.1838621375787406e-07, + "loss": 0.7409, + "step": 15236 + }, + { + "epoch": 0.9353878265140121, + "grad_norm": 1.1284575460883342, + "learning_rate": 2.1797313486109361e-07, + "loss": 0.7142, + "step": 15237 + }, + { + "epoch": 0.9354492157524786, + "grad_norm": 1.1270590744612055, + "learning_rate": 2.175604427001543e-07, + "loss": 0.7309, + "step": 15238 + }, + { + "epoch": 0.9355106049909451, + "grad_norm": 0.8952533657404576, + "learning_rate": 2.1714813729136975e-07, + "loss": 0.7386, + "step": 15239 + }, + { + "epoch": 0.9355719942294116, + "grad_norm": 1.1225225003647423, + "learning_rate": 2.1673621865104023e-07, + "loss": 0.7769, + "step": 15240 + }, + { + "epoch": 0.935633383467878, + "grad_norm": 1.0604314319708152, + "learning_rate": 2.1632468679545494e-07, + "loss": 0.6753, + "step": 15241 + }, + { + "epoch": 0.9356947727063446, + "grad_norm": 1.2148398310058077, + "learning_rate": 2.1591354174087975e-07, + "loss": 0.7649, + "step": 15242 + }, + { + "epoch": 0.935756161944811, + "grad_norm": 1.094445058683731, + "learning_rate": 2.155027835035728e-07, + "loss": 0.7193, + "step": 15243 + }, + { + "epoch": 0.9358175511832776, + "grad_norm": 1.042744054160001, + "learning_rate": 2.1509241209977105e-07, + "loss": 0.7643, + "step": 15244 + }, + { + "epoch": 0.935878940421744, + "grad_norm": 1.1535134411795893, + "learning_rate": 2.1468242754569934e-07, + "loss": 0.7599, + "step": 15245 + }, + { + "epoch": 0.9359403296602106, + "grad_norm": 0.9269505360564754, + "learning_rate": 2.1427282985756804e-07, + "loss": 0.6968, + "step": 15246 + }, + { + "epoch": 0.9360017188986771, + "grad_norm": 1.105325661518733, + "learning_rate": 2.138636190515675e-07, + "loss": 0.7724, + "step": 15247 + }, + { + "epoch": 0.9360631081371436, + "grad_norm": 1.043113272552803, + "learning_rate": 2.1345479514388035e-07, + "loss": 0.7363, + "step": 15248 + }, + { + "epoch": 0.9361244973756101, + "grad_norm": 1.1011758093739552, + "learning_rate": 2.1304635815066587e-07, + "loss": 0.7229, + "step": 15249 + }, + { + "epoch": 0.9361858866140765, + "grad_norm": 1.1682260219316085, + "learning_rate": 2.1263830808807452e-07, + "loss": 0.6967, + "step": 15250 + }, + { + "epoch": 0.9362472758525431, + "grad_norm": 1.0624567272769097, + "learning_rate": 2.1223064497223444e-07, + "loss": 0.7461, + "step": 15251 + }, + { + "epoch": 0.9363086650910095, + "grad_norm": 1.0709210504623958, + "learning_rate": 2.1182336881926836e-07, + "loss": 0.7553, + "step": 15252 + }, + { + "epoch": 0.9363700543294761, + "grad_norm": 0.9865168482403384, + "learning_rate": 2.1141647964527556e-07, + "loss": 0.7067, + "step": 15253 + }, + { + "epoch": 0.9364314435679425, + "grad_norm": 1.0370629259398314, + "learning_rate": 2.110099774663399e-07, + "loss": 0.7099, + "step": 15254 + }, + { + "epoch": 0.936492832806409, + "grad_norm": 1.082816623527986, + "learning_rate": 2.1060386229853623e-07, + "loss": 0.7572, + "step": 15255 + }, + { + "epoch": 0.9365542220448755, + "grad_norm": 1.0700885192532477, + "learning_rate": 2.1019813415791958e-07, + "loss": 0.7163, + "step": 15256 + }, + { + "epoch": 0.936615611283342, + "grad_norm": 1.0494952768437729, + "learning_rate": 2.0979279306053035e-07, + "loss": 0.7242, + "step": 15257 + }, + { + "epoch": 0.9366770005218086, + "grad_norm": 1.1185348110609084, + "learning_rate": 2.0938783902239356e-07, + "loss": 0.746, + "step": 15258 + }, + { + "epoch": 0.936738389760275, + "grad_norm": 1.026170765087999, + "learning_rate": 2.0898327205951973e-07, + "loss": 0.7215, + "step": 15259 + }, + { + "epoch": 0.9367997789987416, + "grad_norm": 0.993130547200763, + "learning_rate": 2.0857909218790274e-07, + "loss": 0.6921, + "step": 15260 + }, + { + "epoch": 0.936861168237208, + "grad_norm": 0.6459596304567418, + "learning_rate": 2.081752994235209e-07, + "loss": 0.6974, + "step": 15261 + }, + { + "epoch": 0.9369225574756745, + "grad_norm": 1.132771803683124, + "learning_rate": 2.077718937823414e-07, + "loss": 0.8387, + "step": 15262 + }, + { + "epoch": 0.936983946714141, + "grad_norm": 1.0967861043738942, + "learning_rate": 2.073688752803127e-07, + "loss": 0.7409, + "step": 15263 + }, + { + "epoch": 0.9370453359526075, + "grad_norm": 1.163002395508877, + "learning_rate": 2.069662439333664e-07, + "loss": 0.7026, + "step": 15264 + }, + { + "epoch": 0.937106725191074, + "grad_norm": 0.9939500660423528, + "learning_rate": 2.0656399975741982e-07, + "loss": 0.7583, + "step": 15265 + }, + { + "epoch": 0.9371681144295405, + "grad_norm": 1.0109739370113267, + "learning_rate": 2.0616214276837797e-07, + "loss": 0.7426, + "step": 15266 + }, + { + "epoch": 0.937229503668007, + "grad_norm": 1.1473071174899232, + "learning_rate": 2.057606729821282e-07, + "loss": 0.7662, + "step": 15267 + }, + { + "epoch": 0.9372908929064735, + "grad_norm": 0.9223725278173969, + "learning_rate": 2.0535959041454224e-07, + "loss": 0.6944, + "step": 15268 + }, + { + "epoch": 0.93735228214494, + "grad_norm": 1.0103723773008035, + "learning_rate": 2.0495889508147625e-07, + "loss": 0.7623, + "step": 15269 + }, + { + "epoch": 0.9374136713834065, + "grad_norm": 1.1775551539729576, + "learning_rate": 2.045585869987732e-07, + "loss": 0.7337, + "step": 15270 + }, + { + "epoch": 0.937475060621873, + "grad_norm": 0.9698741983060161, + "learning_rate": 2.041586661822592e-07, + "loss": 0.7381, + "step": 15271 + }, + { + "epoch": 0.9375364498603395, + "grad_norm": 1.1017347962020585, + "learning_rate": 2.0375913264774504e-07, + "loss": 0.6893, + "step": 15272 + }, + { + "epoch": 0.937597839098806, + "grad_norm": 1.1430117301999725, + "learning_rate": 2.0335998641102583e-07, + "loss": 0.722, + "step": 15273 + }, + { + "epoch": 0.9376592283372724, + "grad_norm": 1.158757676489854, + "learning_rate": 2.0296122748788337e-07, + "loss": 0.7603, + "step": 15274 + }, + { + "epoch": 0.937720617575739, + "grad_norm": 1.085535576044165, + "learning_rate": 2.0256285589408064e-07, + "loss": 0.7683, + "step": 15275 + }, + { + "epoch": 0.9377820068142054, + "grad_norm": 1.0696110815924458, + "learning_rate": 2.0216487164536834e-07, + "loss": 0.7252, + "step": 15276 + }, + { + "epoch": 0.937843396052672, + "grad_norm": 1.0983178037399615, + "learning_rate": 2.0176727475748282e-07, + "loss": 0.7339, + "step": 15277 + }, + { + "epoch": 0.9379047852911384, + "grad_norm": 1.0097816828774775, + "learning_rate": 2.0137006524614145e-07, + "loss": 0.7214, + "step": 15278 + }, + { + "epoch": 0.937966174529605, + "grad_norm": 1.1843340750663376, + "learning_rate": 2.0097324312704614e-07, + "loss": 0.7168, + "step": 15279 + }, + { + "epoch": 0.9380275637680715, + "grad_norm": 1.0200160786208943, + "learning_rate": 2.0057680841588878e-07, + "loss": 0.7363, + "step": 15280 + }, + { + "epoch": 0.9380889530065379, + "grad_norm": 1.036313753700982, + "learning_rate": 2.0018076112834128e-07, + "loss": 0.7038, + "step": 15281 + }, + { + "epoch": 0.9381503422450045, + "grad_norm": 1.0733194775586772, + "learning_rate": 1.9978510128006113e-07, + "loss": 0.7202, + "step": 15282 + }, + { + "epoch": 0.9382117314834709, + "grad_norm": 0.9900568751377218, + "learning_rate": 1.9938982888669135e-07, + "loss": 0.7563, + "step": 15283 + }, + { + "epoch": 0.9382731207219375, + "grad_norm": 0.9959037478495446, + "learning_rate": 1.9899494396385943e-07, + "loss": 0.694, + "step": 15284 + }, + { + "epoch": 0.9383345099604039, + "grad_norm": 1.0746978735847872, + "learning_rate": 1.9860044652717625e-07, + "loss": 0.7714, + "step": 15285 + }, + { + "epoch": 0.9383958991988705, + "grad_norm": 1.0418897983122146, + "learning_rate": 1.982063365922382e-07, + "loss": 0.7084, + "step": 15286 + }, + { + "epoch": 0.9384572884373369, + "grad_norm": 1.1222853452836612, + "learning_rate": 1.978126141746295e-07, + "loss": 0.7742, + "step": 15287 + }, + { + "epoch": 0.9385186776758034, + "grad_norm": 1.048638595760647, + "learning_rate": 1.9741927928991212e-07, + "loss": 0.7378, + "step": 15288 + }, + { + "epoch": 0.93858006691427, + "grad_norm": 0.9433161564789265, + "learning_rate": 1.9702633195363918e-07, + "loss": 0.7083, + "step": 15289 + }, + { + "epoch": 0.9386414561527364, + "grad_norm": 0.9542743653585263, + "learning_rate": 1.9663377218134494e-07, + "loss": 0.6968, + "step": 15290 + }, + { + "epoch": 0.938702845391203, + "grad_norm": 1.0588153016935697, + "learning_rate": 1.962415999885492e-07, + "loss": 0.7754, + "step": 15291 + }, + { + "epoch": 0.9387642346296694, + "grad_norm": 0.9947354560022075, + "learning_rate": 1.9584981539075953e-07, + "loss": 0.7648, + "step": 15292 + }, + { + "epoch": 0.938825623868136, + "grad_norm": 0.6033347493729073, + "learning_rate": 1.9545841840346025e-07, + "loss": 0.6071, + "step": 15293 + }, + { + "epoch": 0.9388870131066024, + "grad_norm": 1.032439677205935, + "learning_rate": 1.9506740904212894e-07, + "loss": 0.7302, + "step": 15294 + }, + { + "epoch": 0.9389484023450689, + "grad_norm": 0.9061881434006355, + "learning_rate": 1.946767873222244e-07, + "loss": 0.7078, + "step": 15295 + }, + { + "epoch": 0.9390097915835354, + "grad_norm": 0.9587300051442823, + "learning_rate": 1.9428655325918866e-07, + "loss": 0.7125, + "step": 15296 + }, + { + "epoch": 0.9390711808220019, + "grad_norm": 1.0744114139534877, + "learning_rate": 1.938967068684494e-07, + "loss": 0.7575, + "step": 15297 + }, + { + "epoch": 0.9391325700604684, + "grad_norm": 1.0633734653730815, + "learning_rate": 1.93507248165421e-07, + "loss": 0.7309, + "step": 15298 + }, + { + "epoch": 0.9391939592989349, + "grad_norm": 1.0628940208169448, + "learning_rate": 1.9311817716549886e-07, + "loss": 0.7513, + "step": 15299 + }, + { + "epoch": 0.9392553485374014, + "grad_norm": 1.0396062636745504, + "learning_rate": 1.9272949388406514e-07, + "loss": 0.6911, + "step": 15300 + }, + { + "epoch": 0.9393167377758679, + "grad_norm": 1.0621166152488595, + "learning_rate": 1.9234119833648979e-07, + "loss": 0.741, + "step": 15301 + }, + { + "epoch": 0.9393781270143344, + "grad_norm": 0.9770908703600474, + "learning_rate": 1.919532905381216e-07, + "loss": 0.7166, + "step": 15302 + }, + { + "epoch": 0.9394395162528009, + "grad_norm": 1.1385141619396009, + "learning_rate": 1.9156577050429615e-07, + "loss": 0.7655, + "step": 15303 + }, + { + "epoch": 0.9395009054912674, + "grad_norm": 1.0559346822567481, + "learning_rate": 1.9117863825033445e-07, + "loss": 0.6965, + "step": 15304 + }, + { + "epoch": 0.9395622947297338, + "grad_norm": 1.0033691244191352, + "learning_rate": 1.9079189379154317e-07, + "loss": 0.6673, + "step": 15305 + }, + { + "epoch": 0.9396236839682004, + "grad_norm": 1.000335315819198, + "learning_rate": 1.904055371432123e-07, + "loss": 0.7399, + "step": 15306 + }, + { + "epoch": 0.9396850732066668, + "grad_norm": 1.0710805537558816, + "learning_rate": 1.9001956832061518e-07, + "loss": 0.7236, + "step": 15307 + }, + { + "epoch": 0.9397464624451334, + "grad_norm": 1.1305005167122764, + "learning_rate": 1.8963398733901183e-07, + "loss": 0.7403, + "step": 15308 + }, + { + "epoch": 0.9398078516835998, + "grad_norm": 1.0820012367189509, + "learning_rate": 1.8924879421364672e-07, + "loss": 0.7373, + "step": 15309 + }, + { + "epoch": 0.9398692409220664, + "grad_norm": 1.0936418755061486, + "learning_rate": 1.8886398895974879e-07, + "loss": 0.697, + "step": 15310 + }, + { + "epoch": 0.9399306301605329, + "grad_norm": 1.2034928635224722, + "learning_rate": 1.884795715925303e-07, + "loss": 0.7125, + "step": 15311 + }, + { + "epoch": 0.9399920193989993, + "grad_norm": 1.195529737460754, + "learning_rate": 1.8809554212719129e-07, + "loss": 0.7861, + "step": 15312 + }, + { + "epoch": 0.9400534086374659, + "grad_norm": 1.0763144442831334, + "learning_rate": 1.8771190057891186e-07, + "loss": 0.7364, + "step": 15313 + }, + { + "epoch": 0.9401147978759323, + "grad_norm": 1.1422726312688507, + "learning_rate": 1.87328646962861e-07, + "loss": 0.6355, + "step": 15314 + }, + { + "epoch": 0.9401761871143989, + "grad_norm": 1.0486852586632398, + "learning_rate": 1.8694578129419104e-07, + "loss": 0.7203, + "step": 15315 + }, + { + "epoch": 0.9402375763528653, + "grad_norm": 1.07910209207434, + "learning_rate": 1.8656330358803766e-07, + "loss": 0.758, + "step": 15316 + }, + { + "epoch": 0.9402989655913319, + "grad_norm": 0.5683911627998521, + "learning_rate": 1.8618121385952424e-07, + "loss": 0.6214, + "step": 15317 + }, + { + "epoch": 0.9403603548297983, + "grad_norm": 0.9433710295398886, + "learning_rate": 1.8579951212375325e-07, + "loss": 0.7163, + "step": 15318 + }, + { + "epoch": 0.9404217440682648, + "grad_norm": 1.044685919377016, + "learning_rate": 1.8541819839581921e-07, + "loss": 0.7303, + "step": 15319 + }, + { + "epoch": 0.9404831333067313, + "grad_norm": 1.0906916123462842, + "learning_rate": 1.8503727269079563e-07, + "loss": 0.7416, + "step": 15320 + }, + { + "epoch": 0.9405445225451978, + "grad_norm": 1.1630438719443168, + "learning_rate": 1.846567350237427e-07, + "loss": 0.7564, + "step": 15321 + }, + { + "epoch": 0.9406059117836644, + "grad_norm": 1.052075491182692, + "learning_rate": 1.8427658540970505e-07, + "loss": 0.7404, + "step": 15322 + }, + { + "epoch": 0.9406673010221308, + "grad_norm": 1.1126372466447134, + "learning_rate": 1.8389682386371178e-07, + "loss": 0.7132, + "step": 15323 + }, + { + "epoch": 0.9407286902605974, + "grad_norm": 0.9901186244641895, + "learning_rate": 1.8351745040077862e-07, + "loss": 0.7315, + "step": 15324 + }, + { + "epoch": 0.9407900794990638, + "grad_norm": 1.047276501140827, + "learning_rate": 1.8313846503590028e-07, + "loss": 0.7025, + "step": 15325 + }, + { + "epoch": 0.9408514687375303, + "grad_norm": 1.1030366438427346, + "learning_rate": 1.8275986778406473e-07, + "loss": 0.7169, + "step": 15326 + }, + { + "epoch": 0.9409128579759968, + "grad_norm": 1.0000296598784102, + "learning_rate": 1.8238165866023894e-07, + "loss": 0.7765, + "step": 15327 + }, + { + "epoch": 0.9409742472144633, + "grad_norm": 1.0386567292107962, + "learning_rate": 1.8200383767937314e-07, + "loss": 0.7439, + "step": 15328 + }, + { + "epoch": 0.9410356364529298, + "grad_norm": 1.1878115036517787, + "learning_rate": 1.8162640485640425e-07, + "loss": 0.7358, + "step": 15329 + }, + { + "epoch": 0.9410970256913963, + "grad_norm": 1.1419859517178288, + "learning_rate": 1.8124936020625815e-07, + "loss": 0.6939, + "step": 15330 + }, + { + "epoch": 0.9411584149298627, + "grad_norm": 1.0744199146248523, + "learning_rate": 1.8087270374383846e-07, + "loss": 0.6874, + "step": 15331 + }, + { + "epoch": 0.9412198041683293, + "grad_norm": 1.1045022826481796, + "learning_rate": 1.804964354840377e-07, + "loss": 0.7345, + "step": 15332 + }, + { + "epoch": 0.9412811934067958, + "grad_norm": 1.0978459957903035, + "learning_rate": 1.8012055544173068e-07, + "loss": 0.7277, + "step": 15333 + }, + { + "epoch": 0.9413425826452623, + "grad_norm": 1.0364614036990065, + "learning_rate": 1.7974506363177878e-07, + "loss": 0.7367, + "step": 15334 + }, + { + "epoch": 0.9414039718837288, + "grad_norm": 1.1120102920382229, + "learning_rate": 1.7936996006902684e-07, + "loss": 0.7068, + "step": 15335 + }, + { + "epoch": 0.9414653611221953, + "grad_norm": 0.9812989813135224, + "learning_rate": 1.789952447683052e-07, + "loss": 0.7368, + "step": 15336 + }, + { + "epoch": 0.9415267503606618, + "grad_norm": 0.9739812587579989, + "learning_rate": 1.7862091774442757e-07, + "loss": 0.6985, + "step": 15337 + }, + { + "epoch": 0.9415881395991282, + "grad_norm": 1.094330932600422, + "learning_rate": 1.7824697901219322e-07, + "loss": 0.7717, + "step": 15338 + }, + { + "epoch": 0.9416495288375948, + "grad_norm": 0.959863392818698, + "learning_rate": 1.7787342858638589e-07, + "loss": 0.6935, + "step": 15339 + }, + { + "epoch": 0.9417109180760612, + "grad_norm": 1.013214206724649, + "learning_rate": 1.7750026648177488e-07, + "loss": 0.6841, + "step": 15340 + }, + { + "epoch": 0.9417723073145278, + "grad_norm": 0.9602552655665149, + "learning_rate": 1.7712749271311392e-07, + "loss": 0.6935, + "step": 15341 + }, + { + "epoch": 0.9418336965529943, + "grad_norm": 1.128465466349811, + "learning_rate": 1.76755107295139e-07, + "loss": 0.7136, + "step": 15342 + }, + { + "epoch": 0.9418950857914608, + "grad_norm": 0.9649621633242037, + "learning_rate": 1.763831102425717e-07, + "loss": 0.7107, + "step": 15343 + }, + { + "epoch": 0.9419564750299273, + "grad_norm": 1.1197911727669443, + "learning_rate": 1.7601150157012138e-07, + "loss": 0.7507, + "step": 15344 + }, + { + "epoch": 0.9420178642683937, + "grad_norm": 1.012219664337814, + "learning_rate": 1.7564028129247846e-07, + "loss": 0.7034, + "step": 15345 + }, + { + "epoch": 0.9420792535068603, + "grad_norm": 1.075098810240466, + "learning_rate": 1.7526944942432012e-07, + "loss": 0.7725, + "step": 15346 + }, + { + "epoch": 0.9421406427453267, + "grad_norm": 0.6022259331380215, + "learning_rate": 1.7489900598030683e-07, + "loss": 0.6911, + "step": 15347 + }, + { + "epoch": 0.9422020319837933, + "grad_norm": 0.9453758311410789, + "learning_rate": 1.745289509750836e-07, + "loss": 0.7426, + "step": 15348 + }, + { + "epoch": 0.9422634212222597, + "grad_norm": 0.9695911923000313, + "learning_rate": 1.74159284423282e-07, + "loss": 0.7501, + "step": 15349 + }, + { + "epoch": 0.9423248104607262, + "grad_norm": 1.102962103430156, + "learning_rate": 1.737900063395148e-07, + "loss": 0.7035, + "step": 15350 + }, + { + "epoch": 0.9423861996991927, + "grad_norm": 1.0492564534959103, + "learning_rate": 1.734211167383848e-07, + "loss": 0.7494, + "step": 15351 + }, + { + "epoch": 0.9424475889376592, + "grad_norm": 1.104675029001202, + "learning_rate": 1.7305261563447362e-07, + "loss": 0.693, + "step": 15352 + }, + { + "epoch": 0.9425089781761258, + "grad_norm": 1.023842016515357, + "learning_rate": 1.7268450304234962e-07, + "loss": 0.7482, + "step": 15353 + }, + { + "epoch": 0.9425703674145922, + "grad_norm": 1.134067571929764, + "learning_rate": 1.7231677897656785e-07, + "loss": 0.7106, + "step": 15354 + }, + { + "epoch": 0.9426317566530588, + "grad_norm": 1.1251614579196334, + "learning_rate": 1.7194944345166665e-07, + "loss": 0.7858, + "step": 15355 + }, + { + "epoch": 0.9426931458915252, + "grad_norm": 1.1007945615970685, + "learning_rate": 1.7158249648216885e-07, + "loss": 0.7071, + "step": 15356 + }, + { + "epoch": 0.9427545351299917, + "grad_norm": 1.1503913277059123, + "learning_rate": 1.712159380825784e-07, + "loss": 0.7207, + "step": 15357 + }, + { + "epoch": 0.9428159243684582, + "grad_norm": 1.0828146484709684, + "learning_rate": 1.7084976826739152e-07, + "loss": 0.7293, + "step": 15358 + }, + { + "epoch": 0.9428773136069247, + "grad_norm": 0.9744562537139098, + "learning_rate": 1.7048398705108327e-07, + "loss": 0.7416, + "step": 15359 + }, + { + "epoch": 0.9429387028453912, + "grad_norm": 0.641747162208359, + "learning_rate": 1.701185944481154e-07, + "loss": 0.7014, + "step": 15360 + }, + { + "epoch": 0.9430000920838577, + "grad_norm": 1.1001190128292246, + "learning_rate": 1.6975359047293306e-07, + "loss": 0.7464, + "step": 15361 + }, + { + "epoch": 0.9430614813223241, + "grad_norm": 1.0588707538285784, + "learning_rate": 1.6938897513996687e-07, + "loss": 0.7154, + "step": 15362 + }, + { + "epoch": 0.9431228705607907, + "grad_norm": 1.2639117778513231, + "learning_rate": 1.6902474846363315e-07, + "loss": 0.7236, + "step": 15363 + }, + { + "epoch": 0.9431842597992572, + "grad_norm": 1.0859873591726037, + "learning_rate": 1.6866091045832923e-07, + "loss": 0.7643, + "step": 15364 + }, + { + "epoch": 0.9432456490377237, + "grad_norm": 1.0805236269405898, + "learning_rate": 1.6829746113844247e-07, + "loss": 0.7199, + "step": 15365 + }, + { + "epoch": 0.9433070382761902, + "grad_norm": 1.0368105304467146, + "learning_rate": 1.679344005183414e-07, + "loss": 0.7291, + "step": 15366 + }, + { + "epoch": 0.9433684275146567, + "grad_norm": 1.1097063462746277, + "learning_rate": 1.675717286123779e-07, + "loss": 0.7204, + "step": 15367 + }, + { + "epoch": 0.9434298167531232, + "grad_norm": 1.0692206204055763, + "learning_rate": 1.6720944543489048e-07, + "loss": 0.7852, + "step": 15368 + }, + { + "epoch": 0.9434912059915896, + "grad_norm": 1.1410070893181807, + "learning_rate": 1.6684755100020435e-07, + "loss": 0.7501, + "step": 15369 + }, + { + "epoch": 0.9435525952300562, + "grad_norm": 1.1434178517963298, + "learning_rate": 1.664860453226258e-07, + "loss": 0.7099, + "step": 15370 + }, + { + "epoch": 0.9436139844685226, + "grad_norm": 1.0926942526822685, + "learning_rate": 1.661249284164479e-07, + "loss": 0.6918, + "step": 15371 + }, + { + "epoch": 0.9436753737069892, + "grad_norm": 1.118267825751814, + "learning_rate": 1.6576420029594586e-07, + "loss": 0.7507, + "step": 15372 + }, + { + "epoch": 0.9437367629454556, + "grad_norm": 1.0221528037249177, + "learning_rate": 1.6540386097538275e-07, + "loss": 0.7384, + "step": 15373 + }, + { + "epoch": 0.9437981521839222, + "grad_norm": 1.0798745296687944, + "learning_rate": 1.650439104690038e-07, + "loss": 0.7915, + "step": 15374 + }, + { + "epoch": 0.9438595414223887, + "grad_norm": 1.0480749285778375, + "learning_rate": 1.646843487910399e-07, + "loss": 0.7258, + "step": 15375 + }, + { + "epoch": 0.9439209306608551, + "grad_norm": 1.0433743841928536, + "learning_rate": 1.6432517595570742e-07, + "loss": 0.7085, + "step": 15376 + }, + { + "epoch": 0.9439823198993217, + "grad_norm": 1.1244446659641374, + "learning_rate": 1.639663919772061e-07, + "loss": 0.7598, + "step": 15377 + }, + { + "epoch": 0.9440437091377881, + "grad_norm": 1.2255106125054482, + "learning_rate": 1.6360799686971795e-07, + "loss": 0.7162, + "step": 15378 + }, + { + "epoch": 0.9441050983762547, + "grad_norm": 1.1616559188894282, + "learning_rate": 1.6324999064741608e-07, + "loss": 0.7619, + "step": 15379 + }, + { + "epoch": 0.9441664876147211, + "grad_norm": 1.0521965185098434, + "learning_rate": 1.628923733244525e-07, + "loss": 0.7442, + "step": 15380 + }, + { + "epoch": 0.9442278768531877, + "grad_norm": 1.0468992878577976, + "learning_rate": 1.625351449149659e-07, + "loss": 0.6861, + "step": 15381 + }, + { + "epoch": 0.9442892660916541, + "grad_norm": 1.0439011502902522, + "learning_rate": 1.6217830543307943e-07, + "loss": 0.7536, + "step": 15382 + }, + { + "epoch": 0.9443506553301206, + "grad_norm": 1.0372541085276563, + "learning_rate": 1.6182185489290069e-07, + "loss": 0.722, + "step": 15383 + }, + { + "epoch": 0.9444120445685871, + "grad_norm": 1.1106013227757174, + "learning_rate": 1.6146579330852173e-07, + "loss": 0.7044, + "step": 15384 + }, + { + "epoch": 0.9444734338070536, + "grad_norm": 1.068023412663459, + "learning_rate": 1.6111012069402132e-07, + "loss": 0.6845, + "step": 15385 + }, + { + "epoch": 0.9445348230455202, + "grad_norm": 0.9638731771140865, + "learning_rate": 1.607548370634593e-07, + "loss": 0.7409, + "step": 15386 + }, + { + "epoch": 0.9445962122839866, + "grad_norm": 0.9582286963884276, + "learning_rate": 1.603999424308833e-07, + "loss": 0.7436, + "step": 15387 + }, + { + "epoch": 0.9446576015224531, + "grad_norm": 1.037485590945332, + "learning_rate": 1.6004543681032214e-07, + "loss": 0.7342, + "step": 15388 + }, + { + "epoch": 0.9447189907609196, + "grad_norm": 1.0748983535189083, + "learning_rate": 1.5969132021579347e-07, + "loss": 0.7582, + "step": 15389 + }, + { + "epoch": 0.9447803799993861, + "grad_norm": 1.1367918969597963, + "learning_rate": 1.5933759266129611e-07, + "loss": 0.6261, + "step": 15390 + }, + { + "epoch": 0.9448417692378526, + "grad_norm": 0.9670291174527262, + "learning_rate": 1.5898425416081665e-07, + "loss": 0.6908, + "step": 15391 + }, + { + "epoch": 0.9449031584763191, + "grad_norm": 0.9576422434647968, + "learning_rate": 1.5863130472832165e-07, + "loss": 0.7697, + "step": 15392 + }, + { + "epoch": 0.9449645477147856, + "grad_norm": 1.1030782154194025, + "learning_rate": 1.582787443777667e-07, + "loss": 0.7101, + "step": 15393 + }, + { + "epoch": 0.9450259369532521, + "grad_norm": 1.0467741944031226, + "learning_rate": 1.5792657312309056e-07, + "loss": 0.7343, + "step": 15394 + }, + { + "epoch": 0.9450873261917186, + "grad_norm": 0.9458599057462933, + "learning_rate": 1.575747909782155e-07, + "loss": 0.7308, + "step": 15395 + }, + { + "epoch": 0.9451487154301851, + "grad_norm": 1.0298069642359602, + "learning_rate": 1.5722339795705142e-07, + "loss": 0.7241, + "step": 15396 + }, + { + "epoch": 0.9452101046686516, + "grad_norm": 1.1433629547455744, + "learning_rate": 1.568723940734873e-07, + "loss": 0.7494, + "step": 15397 + }, + { + "epoch": 0.9452714939071181, + "grad_norm": 1.080851524565502, + "learning_rate": 1.5652177934140422e-07, + "loss": 0.7149, + "step": 15398 + }, + { + "epoch": 0.9453328831455846, + "grad_norm": 1.0817460175804712, + "learning_rate": 1.5617155377466e-07, + "loss": 0.7315, + "step": 15399 + }, + { + "epoch": 0.945394272384051, + "grad_norm": 1.0243448597382343, + "learning_rate": 1.558217173871035e-07, + "loss": 0.6974, + "step": 15400 + }, + { + "epoch": 0.9454556616225176, + "grad_norm": 1.0882881873116323, + "learning_rate": 1.5547227019256596e-07, + "loss": 0.7385, + "step": 15401 + }, + { + "epoch": 0.945517050860984, + "grad_norm": 1.0053787819056628, + "learning_rate": 1.551232122048607e-07, + "loss": 0.7535, + "step": 15402 + }, + { + "epoch": 0.9455784400994506, + "grad_norm": 1.012563188389572, + "learning_rate": 1.5477454343778786e-07, + "loss": 0.6794, + "step": 15403 + }, + { + "epoch": 0.945639829337917, + "grad_norm": 1.1459266650136757, + "learning_rate": 1.5442626390513415e-07, + "loss": 0.7436, + "step": 15404 + }, + { + "epoch": 0.9457012185763836, + "grad_norm": 1.0583754162560155, + "learning_rate": 1.5407837362066968e-07, + "loss": 0.7033, + "step": 15405 + }, + { + "epoch": 0.9457626078148501, + "grad_norm": 1.0869926249649653, + "learning_rate": 1.5373087259814568e-07, + "loss": 0.7225, + "step": 15406 + }, + { + "epoch": 0.9458239970533165, + "grad_norm": 1.0689966096277324, + "learning_rate": 1.5338376085130114e-07, + "loss": 0.7388, + "step": 15407 + }, + { + "epoch": 0.9458853862917831, + "grad_norm": 1.0609252710263366, + "learning_rate": 1.5303703839385952e-07, + "loss": 0.7052, + "step": 15408 + }, + { + "epoch": 0.9459467755302495, + "grad_norm": 0.9114103448870254, + "learning_rate": 1.52690705239531e-07, + "loss": 0.7405, + "step": 15409 + }, + { + "epoch": 0.9460081647687161, + "grad_norm": 1.0990454318913436, + "learning_rate": 1.523447614020046e-07, + "loss": 0.7594, + "step": 15410 + }, + { + "epoch": 0.9460695540071825, + "grad_norm": 1.1906437361185647, + "learning_rate": 1.5199920689495938e-07, + "loss": 0.7573, + "step": 15411 + }, + { + "epoch": 0.9461309432456491, + "grad_norm": 1.0706639742869355, + "learning_rate": 1.5165404173205556e-07, + "loss": 0.6869, + "step": 15412 + }, + { + "epoch": 0.9461923324841155, + "grad_norm": 0.9362466261557659, + "learning_rate": 1.5130926592694106e-07, + "loss": 0.7563, + "step": 15413 + }, + { + "epoch": 0.946253721722582, + "grad_norm": 1.1348332967475603, + "learning_rate": 1.50964879493245e-07, + "loss": 0.7496, + "step": 15414 + }, + { + "epoch": 0.9463151109610485, + "grad_norm": 1.0372917164416484, + "learning_rate": 1.5062088244458428e-07, + "loss": 0.7185, + "step": 15415 + }, + { + "epoch": 0.946376500199515, + "grad_norm": 1.0000905032946334, + "learning_rate": 1.5027727479455802e-07, + "loss": 0.7611, + "step": 15416 + }, + { + "epoch": 0.9464378894379816, + "grad_norm": 1.1359807768216823, + "learning_rate": 1.4993405655674974e-07, + "loss": 0.729, + "step": 15417 + }, + { + "epoch": 0.946499278676448, + "grad_norm": 1.132620800953218, + "learning_rate": 1.49591227744732e-07, + "loss": 0.7149, + "step": 15418 + }, + { + "epoch": 0.9465606679149146, + "grad_norm": 1.2496375838236404, + "learning_rate": 1.4924878837205614e-07, + "loss": 0.7415, + "step": 15419 + }, + { + "epoch": 0.946622057153381, + "grad_norm": 1.0559118988796772, + "learning_rate": 1.4890673845226133e-07, + "loss": 0.714, + "step": 15420 + }, + { + "epoch": 0.9466834463918475, + "grad_norm": 1.0234577453577531, + "learning_rate": 1.485650779988701e-07, + "loss": 0.7278, + "step": 15421 + }, + { + "epoch": 0.946744835630314, + "grad_norm": 1.0835617344406878, + "learning_rate": 1.4822380702539053e-07, + "loss": 0.7392, + "step": 15422 + }, + { + "epoch": 0.9468062248687805, + "grad_norm": 0.9890275906066927, + "learning_rate": 1.4788292554531515e-07, + "loss": 0.7296, + "step": 15423 + }, + { + "epoch": 0.946867614107247, + "grad_norm": 1.0785713385573528, + "learning_rate": 1.4754243357211985e-07, + "loss": 0.7364, + "step": 15424 + }, + { + "epoch": 0.9469290033457135, + "grad_norm": 1.0981207710414271, + "learning_rate": 1.4720233111926828e-07, + "loss": 0.7356, + "step": 15425 + }, + { + "epoch": 0.9469903925841799, + "grad_norm": 1.0441637679328892, + "learning_rate": 1.468626182002042e-07, + "loss": 0.7153, + "step": 15426 + }, + { + "epoch": 0.9470517818226465, + "grad_norm": 1.0774916633757539, + "learning_rate": 1.4652329482835902e-07, + "loss": 0.6952, + "step": 15427 + }, + { + "epoch": 0.947113171061113, + "grad_norm": 1.012555481272181, + "learning_rate": 1.461843610171465e-07, + "loss": 0.7025, + "step": 15428 + }, + { + "epoch": 0.9471745602995795, + "grad_norm": 1.0410685776984718, + "learning_rate": 1.4584581677997035e-07, + "loss": 0.7568, + "step": 15429 + }, + { + "epoch": 0.947235949538046, + "grad_norm": 1.0292529168266236, + "learning_rate": 1.4550766213021316e-07, + "loss": 0.7249, + "step": 15430 + }, + { + "epoch": 0.9472973387765125, + "grad_norm": 1.0224866623363686, + "learning_rate": 1.4516989708124207e-07, + "loss": 0.718, + "step": 15431 + }, + { + "epoch": 0.947358728014979, + "grad_norm": 1.2122345821776523, + "learning_rate": 1.4483252164641192e-07, + "loss": 0.7509, + "step": 15432 + }, + { + "epoch": 0.9474201172534454, + "grad_norm": 1.2609103862863178, + "learning_rate": 1.4449553583906317e-07, + "loss": 0.7597, + "step": 15433 + }, + { + "epoch": 0.947481506491912, + "grad_norm": 1.1160357459383154, + "learning_rate": 1.4415893967251515e-07, + "loss": 0.7753, + "step": 15434 + }, + { + "epoch": 0.9475428957303784, + "grad_norm": 1.0694759653012562, + "learning_rate": 1.4382273316007834e-07, + "loss": 0.6862, + "step": 15435 + }, + { + "epoch": 0.947604284968845, + "grad_norm": 1.038123467933756, + "learning_rate": 1.4348691631504208e-07, + "loss": 0.7132, + "step": 15436 + }, + { + "epoch": 0.9476656742073114, + "grad_norm": 1.096712469132552, + "learning_rate": 1.4315148915068577e-07, + "loss": 0.7404, + "step": 15437 + }, + { + "epoch": 0.947727063445778, + "grad_norm": 1.1047413817947997, + "learning_rate": 1.428164516802688e-07, + "loss": 0.7839, + "step": 15438 + }, + { + "epoch": 0.9477884526842445, + "grad_norm": 1.0410821436505922, + "learning_rate": 1.4248180391703614e-07, + "loss": 0.7589, + "step": 15439 + }, + { + "epoch": 0.9478498419227109, + "grad_norm": 1.1725882002856227, + "learning_rate": 1.4214754587422165e-07, + "loss": 0.7132, + "step": 15440 + }, + { + "epoch": 0.9479112311611775, + "grad_norm": 0.9026558970324986, + "learning_rate": 1.4181367756503693e-07, + "loss": 0.7117, + "step": 15441 + }, + { + "epoch": 0.9479726203996439, + "grad_norm": 1.0550555653450904, + "learning_rate": 1.414801990026815e-07, + "loss": 0.7841, + "step": 15442 + }, + { + "epoch": 0.9480340096381105, + "grad_norm": 0.9980737617179175, + "learning_rate": 1.4114711020034255e-07, + "loss": 0.717, + "step": 15443 + }, + { + "epoch": 0.9480953988765769, + "grad_norm": 0.9543607773929987, + "learning_rate": 1.4081441117118733e-07, + "loss": 0.6761, + "step": 15444 + }, + { + "epoch": 0.9481567881150434, + "grad_norm": 1.0984476357998225, + "learning_rate": 1.4048210192836865e-07, + "loss": 0.6788, + "step": 15445 + }, + { + "epoch": 0.9482181773535099, + "grad_norm": 0.9146149040001819, + "learning_rate": 1.4015018248502488e-07, + "loss": 0.7138, + "step": 15446 + }, + { + "epoch": 0.9482795665919764, + "grad_norm": 1.0830074516880543, + "learning_rate": 1.3981865285427886e-07, + "loss": 0.7498, + "step": 15447 + }, + { + "epoch": 0.948340955830443, + "grad_norm": 1.0008541123902228, + "learning_rate": 1.394875130492368e-07, + "loss": 0.7429, + "step": 15448 + }, + { + "epoch": 0.9484023450689094, + "grad_norm": 0.570645357100726, + "learning_rate": 1.3915676308299154e-07, + "loss": 0.6408, + "step": 15449 + }, + { + "epoch": 0.948463734307376, + "grad_norm": 1.1333498097344268, + "learning_rate": 1.3882640296861926e-07, + "loss": 0.7254, + "step": 15450 + }, + { + "epoch": 0.9485251235458424, + "grad_norm": 1.0356561113037743, + "learning_rate": 1.3849643271917957e-07, + "loss": 0.682, + "step": 15451 + }, + { + "epoch": 0.9485865127843089, + "grad_norm": 0.9848805983709574, + "learning_rate": 1.3816685234771977e-07, + "loss": 0.6989, + "step": 15452 + }, + { + "epoch": 0.9486479020227754, + "grad_norm": 0.9936795728072223, + "learning_rate": 1.3783766186726833e-07, + "loss": 0.7102, + "step": 15453 + }, + { + "epoch": 0.9487092912612419, + "grad_norm": 0.6081017000185638, + "learning_rate": 1.375088612908404e-07, + "loss": 0.664, + "step": 15454 + }, + { + "epoch": 0.9487706804997084, + "grad_norm": 1.042741839836383, + "learning_rate": 1.3718045063143782e-07, + "loss": 0.7092, + "step": 15455 + }, + { + "epoch": 0.9488320697381749, + "grad_norm": 0.9576655163659534, + "learning_rate": 1.3685242990203906e-07, + "loss": 0.727, + "step": 15456 + }, + { + "epoch": 0.9488934589766413, + "grad_norm": 1.0849481043934743, + "learning_rate": 1.365247991156171e-07, + "loss": 0.7278, + "step": 15457 + }, + { + "epoch": 0.9489548482151079, + "grad_norm": 1.285966132711669, + "learning_rate": 1.361975582851238e-07, + "loss": 0.7219, + "step": 15458 + }, + { + "epoch": 0.9490162374535744, + "grad_norm": 1.036129841895939, + "learning_rate": 1.3587070742349552e-07, + "loss": 0.7406, + "step": 15459 + }, + { + "epoch": 0.9490776266920409, + "grad_norm": 1.0271554364698414, + "learning_rate": 1.3554424654365627e-07, + "loss": 0.7363, + "step": 15460 + }, + { + "epoch": 0.9491390159305074, + "grad_norm": 1.072366791243573, + "learning_rate": 1.3521817565851027e-07, + "loss": 0.7297, + "step": 15461 + }, + { + "epoch": 0.9492004051689739, + "grad_norm": 1.0111591902233834, + "learning_rate": 1.3489249478095157e-07, + "loss": 0.7553, + "step": 15462 + }, + { + "epoch": 0.9492617944074404, + "grad_norm": 0.5789612246525381, + "learning_rate": 1.3456720392385437e-07, + "loss": 0.6128, + "step": 15463 + }, + { + "epoch": 0.9493231836459068, + "grad_norm": 0.8922859095812588, + "learning_rate": 1.3424230310007946e-07, + "loss": 0.6864, + "step": 15464 + }, + { + "epoch": 0.9493845728843734, + "grad_norm": 0.9167557239745256, + "learning_rate": 1.3391779232247326e-07, + "loss": 0.7021, + "step": 15465 + }, + { + "epoch": 0.9494459621228398, + "grad_norm": 0.9891951358901918, + "learning_rate": 1.3359367160386328e-07, + "loss": 0.741, + "step": 15466 + }, + { + "epoch": 0.9495073513613064, + "grad_norm": 0.988980232081188, + "learning_rate": 1.332699409570637e-07, + "loss": 0.7628, + "step": 15467 + }, + { + "epoch": 0.9495687405997728, + "grad_norm": 1.0986894143921717, + "learning_rate": 1.329466003948754e-07, + "loss": 0.6969, + "step": 15468 + }, + { + "epoch": 0.9496301298382394, + "grad_norm": 1.059992339198879, + "learning_rate": 1.3262364993008146e-07, + "loss": 0.7148, + "step": 15469 + }, + { + "epoch": 0.9496915190767059, + "grad_norm": 1.1742174468696858, + "learning_rate": 1.323010895754484e-07, + "loss": 0.7519, + "step": 15470 + }, + { + "epoch": 0.9497529083151723, + "grad_norm": 0.9834583082236658, + "learning_rate": 1.319789193437293e-07, + "loss": 0.708, + "step": 15471 + }, + { + "epoch": 0.9498142975536389, + "grad_norm": 1.0432676126622, + "learning_rate": 1.3165713924766065e-07, + "loss": 0.7467, + "step": 15472 + }, + { + "epoch": 0.9498756867921053, + "grad_norm": 0.5894478289836038, + "learning_rate": 1.3133574929996673e-07, + "loss": 0.6335, + "step": 15473 + }, + { + "epoch": 0.9499370760305719, + "grad_norm": 0.9964875245047803, + "learning_rate": 1.310147495133507e-07, + "loss": 0.74, + "step": 15474 + }, + { + "epoch": 0.9499984652690383, + "grad_norm": 1.0235826388443943, + "learning_rate": 1.3069413990050462e-07, + "loss": 0.7083, + "step": 15475 + }, + { + "epoch": 0.9500598545075049, + "grad_norm": 0.9809270652694325, + "learning_rate": 1.303739204741039e-07, + "loss": 0.7572, + "step": 15476 + }, + { + "epoch": 0.9501212437459713, + "grad_norm": 1.0981123367086516, + "learning_rate": 1.3005409124680957e-07, + "loss": 0.7393, + "step": 15477 + }, + { + "epoch": 0.9501826329844378, + "grad_norm": 1.1352089227661741, + "learning_rate": 1.2973465223126368e-07, + "loss": 0.7421, + "step": 15478 + }, + { + "epoch": 0.9502440222229043, + "grad_norm": 1.051206794522219, + "learning_rate": 1.294156034400984e-07, + "loss": 0.689, + "step": 15479 + }, + { + "epoch": 0.9503054114613708, + "grad_norm": 1.0714051330257233, + "learning_rate": 1.2909694488592583e-07, + "loss": 0.7372, + "step": 15480 + }, + { + "epoch": 0.9503668006998374, + "grad_norm": 1.0306401675747474, + "learning_rate": 1.2877867658134257e-07, + "loss": 0.7032, + "step": 15481 + }, + { + "epoch": 0.9504281899383038, + "grad_norm": 1.0931922590498186, + "learning_rate": 1.2846079853893412e-07, + "loss": 0.7123, + "step": 15482 + }, + { + "epoch": 0.9504895791767703, + "grad_norm": 1.0122142623133843, + "learning_rate": 1.2814331077126818e-07, + "loss": 0.7374, + "step": 15483 + }, + { + "epoch": 0.9505509684152368, + "grad_norm": 1.1499890285457912, + "learning_rate": 1.2782621329089473e-07, + "loss": 0.7597, + "step": 15484 + }, + { + "epoch": 0.9506123576537033, + "grad_norm": 0.9754921241756629, + "learning_rate": 1.275095061103504e-07, + "loss": 0.7198, + "step": 15485 + }, + { + "epoch": 0.9506737468921698, + "grad_norm": 1.151919510368032, + "learning_rate": 1.271931892421585e-07, + "loss": 0.734, + "step": 15486 + }, + { + "epoch": 0.9507351361306363, + "grad_norm": 1.046872697802079, + "learning_rate": 1.2687726269882238e-07, + "loss": 0.6811, + "step": 15487 + }, + { + "epoch": 0.9507965253691028, + "grad_norm": 1.0768122290488968, + "learning_rate": 1.2656172649283315e-07, + "loss": 0.7415, + "step": 15488 + }, + { + "epoch": 0.9508579146075693, + "grad_norm": 1.1364290156701227, + "learning_rate": 1.262465806366664e-07, + "loss": 0.6912, + "step": 15489 + }, + { + "epoch": 0.9509193038460357, + "grad_norm": 1.0206546340848013, + "learning_rate": 1.2593182514277992e-07, + "loss": 0.6908, + "step": 15490 + }, + { + "epoch": 0.9509806930845023, + "grad_norm": 1.0695252917152254, + "learning_rate": 1.256174600236193e-07, + "loss": 0.6788, + "step": 15491 + }, + { + "epoch": 0.9510420823229688, + "grad_norm": 0.9483879163461775, + "learning_rate": 1.253034852916124e-07, + "loss": 0.692, + "step": 15492 + }, + { + "epoch": 0.9511034715614353, + "grad_norm": 1.0980715812523214, + "learning_rate": 1.2498990095917152e-07, + "loss": 0.6978, + "step": 15493 + }, + { + "epoch": 0.9511648607999018, + "grad_norm": 0.9577533519713787, + "learning_rate": 1.2467670703869672e-07, + "loss": 0.7333, + "step": 15494 + }, + { + "epoch": 0.9512262500383682, + "grad_norm": 1.0086469983449902, + "learning_rate": 1.24363903542567e-07, + "loss": 0.6992, + "step": 15495 + }, + { + "epoch": 0.9512876392768348, + "grad_norm": 0.9343213702464626, + "learning_rate": 1.2405149048315136e-07, + "loss": 0.6902, + "step": 15496 + }, + { + "epoch": 0.9513490285153012, + "grad_norm": 1.023092750004902, + "learning_rate": 1.23739467872801e-07, + "loss": 0.7386, + "step": 15497 + }, + { + "epoch": 0.9514104177537678, + "grad_norm": 1.095561529912954, + "learning_rate": 1.2342783572385164e-07, + "loss": 0.7064, + "step": 15498 + }, + { + "epoch": 0.9514718069922342, + "grad_norm": 0.9550060340192874, + "learning_rate": 1.231165940486234e-07, + "loss": 0.7041, + "step": 15499 + }, + { + "epoch": 0.9515331962307008, + "grad_norm": 1.023673538782785, + "learning_rate": 1.2280574285942092e-07, + "loss": 0.7537, + "step": 15500 + }, + { + "epoch": 0.9515945854691673, + "grad_norm": 1.0715348974723629, + "learning_rate": 1.2249528216853433e-07, + "loss": 0.7136, + "step": 15501 + }, + { + "epoch": 0.9516559747076337, + "grad_norm": 0.9566011165470912, + "learning_rate": 1.221852119882383e-07, + "loss": 0.7421, + "step": 15502 + }, + { + "epoch": 0.9517173639461003, + "grad_norm": 0.8667089541841457, + "learning_rate": 1.2187553233079074e-07, + "loss": 0.668, + "step": 15503 + }, + { + "epoch": 0.9517787531845667, + "grad_norm": 1.0598545879782377, + "learning_rate": 1.2156624320843636e-07, + "loss": 0.7397, + "step": 15504 + }, + { + "epoch": 0.9518401424230333, + "grad_norm": 1.1378053802153332, + "learning_rate": 1.2125734463340088e-07, + "loss": 0.7046, + "step": 15505 + }, + { + "epoch": 0.9519015316614997, + "grad_norm": 1.0060356834615929, + "learning_rate": 1.209488366178968e-07, + "loss": 0.7455, + "step": 15506 + }, + { + "epoch": 0.9519629208999663, + "grad_norm": 1.0188650749944332, + "learning_rate": 1.2064071917412323e-07, + "loss": 0.732, + "step": 15507 + }, + { + "epoch": 0.9520243101384327, + "grad_norm": 1.1326662966394745, + "learning_rate": 1.2033299231426155e-07, + "loss": 0.7464, + "step": 15508 + }, + { + "epoch": 0.9520856993768992, + "grad_norm": 1.076846785084191, + "learning_rate": 1.2002565605047646e-07, + "loss": 0.7775, + "step": 15509 + }, + { + "epoch": 0.9521470886153657, + "grad_norm": 1.1532548501616018, + "learning_rate": 1.1971871039491823e-07, + "loss": 0.7219, + "step": 15510 + }, + { + "epoch": 0.9522084778538322, + "grad_norm": 0.9331341129333315, + "learning_rate": 1.1941215535972273e-07, + "loss": 0.7281, + "step": 15511 + }, + { + "epoch": 0.9522698670922988, + "grad_norm": 1.0135383762784902, + "learning_rate": 1.1910599095701025e-07, + "loss": 0.737, + "step": 15512 + }, + { + "epoch": 0.9523312563307652, + "grad_norm": 0.9389710168493496, + "learning_rate": 1.1880021719888446e-07, + "loss": 0.6948, + "step": 15513 + }, + { + "epoch": 0.9523926455692318, + "grad_norm": 1.0326696827962643, + "learning_rate": 1.1849483409743457e-07, + "loss": 0.7699, + "step": 15514 + }, + { + "epoch": 0.9524540348076982, + "grad_norm": 1.1176792056539466, + "learning_rate": 1.1818984166473425e-07, + "loss": 0.7807, + "step": 15515 + }, + { + "epoch": 0.9525154240461647, + "grad_norm": 0.9866128454572709, + "learning_rate": 1.178852399128405e-07, + "loss": 0.7082, + "step": 15516 + }, + { + "epoch": 0.9525768132846312, + "grad_norm": 0.9680901614602517, + "learning_rate": 1.1758102885379597e-07, + "loss": 0.7541, + "step": 15517 + }, + { + "epoch": 0.9526382025230977, + "grad_norm": 1.0543159466364245, + "learning_rate": 1.1727720849962987e-07, + "loss": 0.7285, + "step": 15518 + }, + { + "epoch": 0.9526995917615642, + "grad_norm": 0.9710016835180738, + "learning_rate": 1.169737788623515e-07, + "loss": 0.7154, + "step": 15519 + }, + { + "epoch": 0.9527609810000307, + "grad_norm": 1.0318204178952417, + "learning_rate": 1.1667073995395795e-07, + "loss": 0.7431, + "step": 15520 + }, + { + "epoch": 0.9528223702384971, + "grad_norm": 1.0903444172725243, + "learning_rate": 1.163680917864296e-07, + "loss": 0.7333, + "step": 15521 + }, + { + "epoch": 0.9528837594769637, + "grad_norm": 1.0643332730393555, + "learning_rate": 1.1606583437173136e-07, + "loss": 0.7015, + "step": 15522 + }, + { + "epoch": 0.9529451487154302, + "grad_norm": 1.156470821463812, + "learning_rate": 1.1576396772181475e-07, + "loss": 0.6725, + "step": 15523 + }, + { + "epoch": 0.9530065379538967, + "grad_norm": 1.004727472736763, + "learning_rate": 1.1546249184861246e-07, + "loss": 0.7413, + "step": 15524 + }, + { + "epoch": 0.9530679271923632, + "grad_norm": 0.9873182389509415, + "learning_rate": 1.1516140676404497e-07, + "loss": 0.7018, + "step": 15525 + }, + { + "epoch": 0.9531293164308297, + "grad_norm": 1.015629778204346, + "learning_rate": 1.1486071248001385e-07, + "loss": 0.6948, + "step": 15526 + }, + { + "epoch": 0.9531907056692962, + "grad_norm": 1.11696202428528, + "learning_rate": 1.1456040900840849e-07, + "loss": 0.7672, + "step": 15527 + }, + { + "epoch": 0.9532520949077626, + "grad_norm": 1.1199016073258001, + "learning_rate": 1.1426049636110049e-07, + "loss": 0.7227, + "step": 15528 + }, + { + "epoch": 0.9533134841462292, + "grad_norm": 1.053767597450975, + "learning_rate": 1.1396097454994925e-07, + "loss": 0.7317, + "step": 15529 + }, + { + "epoch": 0.9533748733846956, + "grad_norm": 1.2266356916800591, + "learning_rate": 1.1366184358679421e-07, + "loss": 0.6842, + "step": 15530 + }, + { + "epoch": 0.9534362626231622, + "grad_norm": 1.1401931282128472, + "learning_rate": 1.1336310348346258e-07, + "loss": 0.7145, + "step": 15531 + }, + { + "epoch": 0.9534976518616286, + "grad_norm": 0.6612516905412738, + "learning_rate": 1.1306475425176377e-07, + "loss": 0.6985, + "step": 15532 + }, + { + "epoch": 0.9535590411000952, + "grad_norm": 0.995676610215867, + "learning_rate": 1.1276679590349615e-07, + "loss": 0.7178, + "step": 15533 + }, + { + "epoch": 0.9536204303385617, + "grad_norm": 1.1126921511287051, + "learning_rate": 1.1246922845043584e-07, + "loss": 0.7442, + "step": 15534 + }, + { + "epoch": 0.9536818195770281, + "grad_norm": 1.1684700064712923, + "learning_rate": 1.121720519043501e-07, + "loss": 0.7481, + "step": 15535 + }, + { + "epoch": 0.9537432088154947, + "grad_norm": 1.1906718468881954, + "learning_rate": 1.118752662769873e-07, + "loss": 0.7008, + "step": 15536 + }, + { + "epoch": 0.9538045980539611, + "grad_norm": 1.1658261566141292, + "learning_rate": 1.115788715800803e-07, + "loss": 0.73, + "step": 15537 + }, + { + "epoch": 0.9538659872924277, + "grad_norm": 1.2440394832675359, + "learning_rate": 1.1128286782534747e-07, + "loss": 0.7315, + "step": 15538 + }, + { + "epoch": 0.9539273765308941, + "grad_norm": 1.0624516692234174, + "learning_rate": 1.109872550244917e-07, + "loss": 0.7242, + "step": 15539 + }, + { + "epoch": 0.9539887657693606, + "grad_norm": 1.1423577183847595, + "learning_rate": 1.106920331892003e-07, + "loss": 0.7364, + "step": 15540 + }, + { + "epoch": 0.9540501550078271, + "grad_norm": 1.0220771916120872, + "learning_rate": 1.1039720233114393e-07, + "loss": 0.661, + "step": 15541 + }, + { + "epoch": 0.9541115442462936, + "grad_norm": 1.0872866087945625, + "learning_rate": 1.1010276246197882e-07, + "loss": 0.7512, + "step": 15542 + }, + { + "epoch": 0.9541729334847601, + "grad_norm": 1.0476906550186906, + "learning_rate": 1.0980871359334788e-07, + "loss": 0.7717, + "step": 15543 + }, + { + "epoch": 0.9542343227232266, + "grad_norm": 0.9481931018324591, + "learning_rate": 1.0951505573687405e-07, + "loss": 0.6643, + "step": 15544 + }, + { + "epoch": 0.9542957119616932, + "grad_norm": 1.050015322890819, + "learning_rate": 1.092217889041669e-07, + "loss": 0.7273, + "step": 15545 + }, + { + "epoch": 0.9543571012001596, + "grad_norm": 1.1333293992280664, + "learning_rate": 1.0892891310682385e-07, + "loss": 0.7449, + "step": 15546 + }, + { + "epoch": 0.9544184904386261, + "grad_norm": 1.0019888308560283, + "learning_rate": 1.0863642835642119e-07, + "loss": 0.6989, + "step": 15547 + }, + { + "epoch": 0.9544798796770926, + "grad_norm": 1.0945358979267015, + "learning_rate": 1.083443346645241e-07, + "loss": 0.7166, + "step": 15548 + }, + { + "epoch": 0.9545412689155591, + "grad_norm": 0.9601178437717185, + "learning_rate": 1.080526320426789e-07, + "loss": 0.7068, + "step": 15549 + }, + { + "epoch": 0.9546026581540256, + "grad_norm": 1.0129518516916505, + "learning_rate": 1.0776132050241971e-07, + "loss": 0.7351, + "step": 15550 + }, + { + "epoch": 0.9546640473924921, + "grad_norm": 0.9829870996433915, + "learning_rate": 1.0747040005526177e-07, + "loss": 0.692, + "step": 15551 + }, + { + "epoch": 0.9547254366309585, + "grad_norm": 0.9854535882327619, + "learning_rate": 1.071798707127092e-07, + "loss": 0.7217, + "step": 15552 + }, + { + "epoch": 0.9547868258694251, + "grad_norm": 1.1602460205604233, + "learning_rate": 1.0688973248624613e-07, + "loss": 0.7588, + "step": 15553 + }, + { + "epoch": 0.9548482151078916, + "grad_norm": 1.0292868403649367, + "learning_rate": 1.065999853873445e-07, + "loss": 0.718, + "step": 15554 + }, + { + "epoch": 0.9549096043463581, + "grad_norm": 0.8631408812027199, + "learning_rate": 1.0631062942745851e-07, + "loss": 0.7179, + "step": 15555 + }, + { + "epoch": 0.9549709935848246, + "grad_norm": 0.989360192449547, + "learning_rate": 1.0602166461802787e-07, + "loss": 0.6932, + "step": 15556 + }, + { + "epoch": 0.9550323828232911, + "grad_norm": 0.9685974800520627, + "learning_rate": 1.0573309097047902e-07, + "loss": 0.7361, + "step": 15557 + }, + { + "epoch": 0.9550937720617576, + "grad_norm": 1.0036825326958514, + "learning_rate": 1.0544490849621947e-07, + "loss": 0.7451, + "step": 15558 + }, + { + "epoch": 0.955155161300224, + "grad_norm": 0.644745765831545, + "learning_rate": 1.0515711720664124e-07, + "loss": 0.7067, + "step": 15559 + }, + { + "epoch": 0.9552165505386906, + "grad_norm": 1.005493101699296, + "learning_rate": 1.048697171131241e-07, + "loss": 0.7073, + "step": 15560 + }, + { + "epoch": 0.955277939777157, + "grad_norm": 1.1479087918799054, + "learning_rate": 1.045827082270301e-07, + "loss": 0.7456, + "step": 15561 + }, + { + "epoch": 0.9553393290156236, + "grad_norm": 1.0248380522287368, + "learning_rate": 1.0429609055970569e-07, + "loss": 0.6944, + "step": 15562 + }, + { + "epoch": 0.95540071825409, + "grad_norm": 1.0331938457114258, + "learning_rate": 1.0400986412248292e-07, + "loss": 0.7109, + "step": 15563 + }, + { + "epoch": 0.9554621074925566, + "grad_norm": 1.0531013278812673, + "learning_rate": 1.0372402892667721e-07, + "loss": 0.711, + "step": 15564 + }, + { + "epoch": 0.9555234967310231, + "grad_norm": 1.0731729884199483, + "learning_rate": 1.0343858498359061e-07, + "loss": 0.6789, + "step": 15565 + }, + { + "epoch": 0.9555848859694895, + "grad_norm": 1.0979374776860504, + "learning_rate": 1.0315353230450631e-07, + "loss": 0.6864, + "step": 15566 + }, + { + "epoch": 0.9556462752079561, + "grad_norm": 1.0080404193220485, + "learning_rate": 1.028688709006953e-07, + "loss": 0.6949, + "step": 15567 + }, + { + "epoch": 0.9557076644464225, + "grad_norm": 0.940911612237639, + "learning_rate": 1.0258460078341193e-07, + "loss": 0.737, + "step": 15568 + }, + { + "epoch": 0.9557690536848891, + "grad_norm": 0.977433780078965, + "learning_rate": 1.0230072196389384e-07, + "loss": 0.6853, + "step": 15569 + }, + { + "epoch": 0.9558304429233555, + "grad_norm": 1.1919636786212398, + "learning_rate": 1.0201723445336431e-07, + "loss": 0.7495, + "step": 15570 + }, + { + "epoch": 0.955891832161822, + "grad_norm": 1.0873622095744377, + "learning_rate": 1.0173413826303213e-07, + "loss": 0.6772, + "step": 15571 + }, + { + "epoch": 0.9559532214002885, + "grad_norm": 1.1023965697219003, + "learning_rate": 1.0145143340408948e-07, + "loss": 0.7288, + "step": 15572 + }, + { + "epoch": 0.956014610638755, + "grad_norm": 1.1691145285513644, + "learning_rate": 1.0116911988771294e-07, + "loss": 0.7381, + "step": 15573 + }, + { + "epoch": 0.9560759998772215, + "grad_norm": 1.0438335344631566, + "learning_rate": 1.0088719772506361e-07, + "loss": 0.7482, + "step": 15574 + }, + { + "epoch": 0.956137389115688, + "grad_norm": 0.9774295265436932, + "learning_rate": 1.0060566692728702e-07, + "loss": 0.6952, + "step": 15575 + }, + { + "epoch": 0.9561987783541546, + "grad_norm": 1.0262179344517677, + "learning_rate": 1.0032452750551425e-07, + "loss": 0.7163, + "step": 15576 + }, + { + "epoch": 0.956260167592621, + "grad_norm": 1.146470998472874, + "learning_rate": 1.0004377947086086e-07, + "loss": 0.6828, + "step": 15577 + }, + { + "epoch": 0.9563215568310875, + "grad_norm": 1.028114458985242, + "learning_rate": 9.976342283442464e-08, + "loss": 0.7254, + "step": 15578 + }, + { + "epoch": 0.956382946069554, + "grad_norm": 1.0791193736302196, + "learning_rate": 9.948345760729117e-08, + "loss": 0.7692, + "step": 15579 + }, + { + "epoch": 0.9564443353080205, + "grad_norm": 1.0155489036759844, + "learning_rate": 9.920388380052715e-08, + "loss": 0.7299, + "step": 15580 + }, + { + "epoch": 0.956505724546487, + "grad_norm": 1.1315621327270786, + "learning_rate": 9.892470142518707e-08, + "loss": 0.698, + "step": 15581 + }, + { + "epoch": 0.9565671137849535, + "grad_norm": 1.1530622448843069, + "learning_rate": 9.864591049230876e-08, + "loss": 0.7398, + "step": 15582 + }, + { + "epoch": 0.95662850302342, + "grad_norm": 1.0608715955209123, + "learning_rate": 9.836751101291452e-08, + "loss": 0.74, + "step": 15583 + }, + { + "epoch": 0.9566898922618865, + "grad_norm": 1.0806345613408888, + "learning_rate": 9.80895029980089e-08, + "loss": 0.7489, + "step": 15584 + }, + { + "epoch": 0.9567512815003529, + "grad_norm": 1.0912073178068142, + "learning_rate": 9.78118864585853e-08, + "loss": 0.7345, + "step": 15585 + }, + { + "epoch": 0.9568126707388195, + "grad_norm": 1.1325820168885756, + "learning_rate": 9.753466140561829e-08, + "loss": 0.7698, + "step": 15586 + }, + { + "epoch": 0.956874059977286, + "grad_norm": 1.1056182510534849, + "learning_rate": 9.725782785006799e-08, + "loss": 0.7083, + "step": 15587 + }, + { + "epoch": 0.9569354492157525, + "grad_norm": 1.0394873737722177, + "learning_rate": 9.698138580287897e-08, + "loss": 0.694, + "step": 15588 + }, + { + "epoch": 0.956996838454219, + "grad_norm": 1.1056285471741816, + "learning_rate": 9.670533527498139e-08, + "loss": 0.7179, + "step": 15589 + }, + { + "epoch": 0.9570582276926854, + "grad_norm": 1.1940890633597188, + "learning_rate": 9.642967627728872e-08, + "loss": 0.7411, + "step": 15590 + }, + { + "epoch": 0.957119616931152, + "grad_norm": 1.1861103021092734, + "learning_rate": 9.615440882069782e-08, + "loss": 0.7554, + "step": 15591 + }, + { + "epoch": 0.9571810061696184, + "grad_norm": 1.0991497755684148, + "learning_rate": 9.587953291609331e-08, + "loss": 0.7063, + "step": 15592 + }, + { + "epoch": 0.957242395408085, + "grad_norm": 1.008955642150588, + "learning_rate": 9.560504857434205e-08, + "loss": 0.7163, + "step": 15593 + }, + { + "epoch": 0.9573037846465514, + "grad_norm": 0.6275999238789914, + "learning_rate": 9.533095580629536e-08, + "loss": 0.6727, + "step": 15594 + }, + { + "epoch": 0.957365173885018, + "grad_norm": 0.5765561851805099, + "learning_rate": 9.505725462279014e-08, + "loss": 0.662, + "step": 15595 + }, + { + "epoch": 0.9574265631234845, + "grad_norm": 1.023932383478259, + "learning_rate": 9.478394503464661e-08, + "loss": 0.6978, + "step": 15596 + }, + { + "epoch": 0.957487952361951, + "grad_norm": 0.9957892382076535, + "learning_rate": 9.451102705267057e-08, + "loss": 0.6867, + "step": 15597 + }, + { + "epoch": 0.9575493416004175, + "grad_norm": 1.1153719708410537, + "learning_rate": 9.423850068765228e-08, + "loss": 0.7413, + "step": 15598 + }, + { + "epoch": 0.9576107308388839, + "grad_norm": 1.0368914997430558, + "learning_rate": 9.396636595036535e-08, + "loss": 0.7718, + "step": 15599 + }, + { + "epoch": 0.9576721200773505, + "grad_norm": 1.1871552052200425, + "learning_rate": 9.369462285157005e-08, + "loss": 0.7161, + "step": 15600 + }, + { + "epoch": 0.9577335093158169, + "grad_norm": 1.0549293867679823, + "learning_rate": 9.34232714020078e-08, + "loss": 0.7259, + "step": 15601 + }, + { + "epoch": 0.9577948985542835, + "grad_norm": 1.1398437847735543, + "learning_rate": 9.31523116124089e-08, + "loss": 0.765, + "step": 15602 + }, + { + "epoch": 0.9578562877927499, + "grad_norm": 1.0546388816056846, + "learning_rate": 9.288174349348366e-08, + "loss": 0.6889, + "step": 15603 + }, + { + "epoch": 0.9579176770312164, + "grad_norm": 0.9410564583118503, + "learning_rate": 9.261156705593022e-08, + "loss": 0.6806, + "step": 15604 + }, + { + "epoch": 0.9579790662696829, + "grad_norm": 1.0773850450115707, + "learning_rate": 9.234178231043e-08, + "loss": 0.7287, + "step": 15605 + }, + { + "epoch": 0.9580404555081494, + "grad_norm": 1.032655532808019, + "learning_rate": 9.207238926764894e-08, + "loss": 0.729, + "step": 15606 + }, + { + "epoch": 0.958101844746616, + "grad_norm": 1.1326672008243044, + "learning_rate": 9.180338793823851e-08, + "loss": 0.8169, + "step": 15607 + }, + { + "epoch": 0.9581632339850824, + "grad_norm": 1.0661103562418557, + "learning_rate": 9.153477833283242e-08, + "loss": 0.6962, + "step": 15608 + }, + { + "epoch": 0.958224623223549, + "grad_norm": 1.245457752432954, + "learning_rate": 9.126656046204996e-08, + "loss": 0.7382, + "step": 15609 + }, + { + "epoch": 0.9582860124620154, + "grad_norm": 1.092299464487363, + "learning_rate": 9.099873433649708e-08, + "loss": 0.6641, + "step": 15610 + }, + { + "epoch": 0.9583474017004819, + "grad_norm": 1.0285129969090412, + "learning_rate": 9.073129996676089e-08, + "loss": 0.7222, + "step": 15611 + }, + { + "epoch": 0.9584087909389484, + "grad_norm": 1.0577818329103623, + "learning_rate": 9.046425736341513e-08, + "loss": 0.7814, + "step": 15612 + }, + { + "epoch": 0.9584701801774149, + "grad_norm": 1.0688584625226518, + "learning_rate": 9.019760653701693e-08, + "loss": 0.7174, + "step": 15613 + }, + { + "epoch": 0.9585315694158814, + "grad_norm": 0.9580957355424611, + "learning_rate": 8.993134749810895e-08, + "loss": 0.7423, + "step": 15614 + }, + { + "epoch": 0.9585929586543479, + "grad_norm": 1.027812633160439, + "learning_rate": 8.966548025721722e-08, + "loss": 0.68, + "step": 15615 + }, + { + "epoch": 0.9586543478928143, + "grad_norm": 1.0133624574981142, + "learning_rate": 8.940000482485333e-08, + "loss": 0.7078, + "step": 15616 + }, + { + "epoch": 0.9587157371312809, + "grad_norm": 1.0714662088329698, + "learning_rate": 8.913492121151335e-08, + "loss": 0.6921, + "step": 15617 + }, + { + "epoch": 0.9587771263697474, + "grad_norm": 1.0405985152773525, + "learning_rate": 8.887022942767665e-08, + "loss": 0.7426, + "step": 15618 + }, + { + "epoch": 0.9588385156082139, + "grad_norm": 0.9604337438541299, + "learning_rate": 8.86059294838082e-08, + "loss": 0.742, + "step": 15619 + }, + { + "epoch": 0.9588999048466804, + "grad_norm": 0.9867280273324157, + "learning_rate": 8.83420213903563e-08, + "loss": 0.706, + "step": 15620 + }, + { + "epoch": 0.9589612940851469, + "grad_norm": 0.9862896836654391, + "learning_rate": 8.807850515775706e-08, + "loss": 0.7229, + "step": 15621 + }, + { + "epoch": 0.9590226833236134, + "grad_norm": 0.9602875259954409, + "learning_rate": 8.781538079642659e-08, + "loss": 0.7117, + "step": 15622 + }, + { + "epoch": 0.9590840725620798, + "grad_norm": 0.9920508772895608, + "learning_rate": 8.755264831676769e-08, + "loss": 0.7036, + "step": 15623 + }, + { + "epoch": 0.9591454618005464, + "grad_norm": 1.1564311868291999, + "learning_rate": 8.72903077291687e-08, + "loss": 0.6984, + "step": 15624 + }, + { + "epoch": 0.9592068510390128, + "grad_norm": 0.9227460490307149, + "learning_rate": 8.70283590440002e-08, + "loss": 0.7426, + "step": 15625 + }, + { + "epoch": 0.9592682402774794, + "grad_norm": 0.9423412035577947, + "learning_rate": 8.676680227161949e-08, + "loss": 0.7347, + "step": 15626 + }, + { + "epoch": 0.9593296295159458, + "grad_norm": 1.1530468875501192, + "learning_rate": 8.650563742236717e-08, + "loss": 0.7369, + "step": 15627 + }, + { + "epoch": 0.9593910187544124, + "grad_norm": 1.1069469049962115, + "learning_rate": 8.624486450656722e-08, + "loss": 0.7148, + "step": 15628 + }, + { + "epoch": 0.9594524079928789, + "grad_norm": 1.0719308041802966, + "learning_rate": 8.598448353453137e-08, + "loss": 0.7494, + "step": 15629 + }, + { + "epoch": 0.9595137972313453, + "grad_norm": 1.1702613225948857, + "learning_rate": 8.572449451655141e-08, + "loss": 0.7281, + "step": 15630 + }, + { + "epoch": 0.9595751864698119, + "grad_norm": 0.9151956015223679, + "learning_rate": 8.546489746290798e-08, + "loss": 0.733, + "step": 15631 + }, + { + "epoch": 0.9596365757082783, + "grad_norm": 1.0725721397769388, + "learning_rate": 8.520569238386511e-08, + "loss": 0.7408, + "step": 15632 + }, + { + "epoch": 0.9596979649467449, + "grad_norm": 1.1599969541167028, + "learning_rate": 8.494687928966794e-08, + "loss": 0.6924, + "step": 15633 + }, + { + "epoch": 0.9597593541852113, + "grad_norm": 1.1948859168717134, + "learning_rate": 8.468845819054938e-08, + "loss": 0.7504, + "step": 15634 + }, + { + "epoch": 0.9598207434236778, + "grad_norm": 1.0491462257873085, + "learning_rate": 8.443042909672794e-08, + "loss": 0.7328, + "step": 15635 + }, + { + "epoch": 0.9598821326621443, + "grad_norm": 0.9912523245631634, + "learning_rate": 8.417279201840323e-08, + "loss": 0.7077, + "step": 15636 + }, + { + "epoch": 0.9599435219006108, + "grad_norm": 1.1233156547480612, + "learning_rate": 8.391554696576266e-08, + "loss": 0.7003, + "step": 15637 + }, + { + "epoch": 0.9600049111390773, + "grad_norm": 1.0824614187556485, + "learning_rate": 8.365869394897475e-08, + "loss": 0.7098, + "step": 15638 + }, + { + "epoch": 0.9600663003775438, + "grad_norm": 1.1192377768383341, + "learning_rate": 8.340223297819472e-08, + "loss": 0.7207, + "step": 15639 + }, + { + "epoch": 0.9601276896160104, + "grad_norm": 0.9854279896692836, + "learning_rate": 8.314616406356223e-08, + "loss": 0.6611, + "step": 15640 + }, + { + "epoch": 0.9601890788544768, + "grad_norm": 0.9519869898393165, + "learning_rate": 8.289048721520143e-08, + "loss": 0.6865, + "step": 15641 + }, + { + "epoch": 0.9602504680929433, + "grad_norm": 1.0563192423959007, + "learning_rate": 8.263520244321976e-08, + "loss": 0.7028, + "step": 15642 + }, + { + "epoch": 0.9603118573314098, + "grad_norm": 0.9438798384628118, + "learning_rate": 8.238030975771028e-08, + "loss": 0.7131, + "step": 15643 + }, + { + "epoch": 0.9603732465698763, + "grad_norm": 1.1626449216507049, + "learning_rate": 8.212580916875046e-08, + "loss": 0.7605, + "step": 15644 + }, + { + "epoch": 0.9604346358083428, + "grad_norm": 1.1421986309934122, + "learning_rate": 8.187170068640227e-08, + "loss": 0.7254, + "step": 15645 + }, + { + "epoch": 0.9604960250468093, + "grad_norm": 1.1109625006680641, + "learning_rate": 8.161798432071099e-08, + "loss": 0.716, + "step": 15646 + }, + { + "epoch": 0.9605574142852757, + "grad_norm": 1.0322029522155696, + "learning_rate": 8.136466008170862e-08, + "loss": 0.7285, + "step": 15647 + }, + { + "epoch": 0.9606188035237423, + "grad_norm": 1.153258552867205, + "learning_rate": 8.111172797940935e-08, + "loss": 0.7896, + "step": 15648 + }, + { + "epoch": 0.9606801927622088, + "grad_norm": 1.019238711001777, + "learning_rate": 8.085918802381298e-08, + "loss": 0.7043, + "step": 15649 + }, + { + "epoch": 0.9607415820006753, + "grad_norm": 1.0839488495564158, + "learning_rate": 8.060704022490484e-08, + "loss": 0.717, + "step": 15650 + }, + { + "epoch": 0.9608029712391418, + "grad_norm": 1.12856099708141, + "learning_rate": 8.035528459265363e-08, + "loss": 0.7149, + "step": 15651 + }, + { + "epoch": 0.9608643604776083, + "grad_norm": 1.0115400124326879, + "learning_rate": 8.010392113701137e-08, + "loss": 0.7307, + "step": 15652 + }, + { + "epoch": 0.9609257497160748, + "grad_norm": 1.0171111083983968, + "learning_rate": 7.985294986791569e-08, + "loss": 0.6951, + "step": 15653 + }, + { + "epoch": 0.9609871389545412, + "grad_norm": 1.057023882749008, + "learning_rate": 7.960237079529087e-08, + "loss": 0.747, + "step": 15654 + }, + { + "epoch": 0.9610485281930078, + "grad_norm": 1.0526834305089048, + "learning_rate": 7.935218392904232e-08, + "loss": 0.7371, + "step": 15655 + }, + { + "epoch": 0.9611099174314742, + "grad_norm": 1.036127434916489, + "learning_rate": 7.910238927905989e-08, + "loss": 0.7114, + "step": 15656 + }, + { + "epoch": 0.9611713066699408, + "grad_norm": 1.1102810897431639, + "learning_rate": 7.885298685522235e-08, + "loss": 0.8072, + "step": 15657 + }, + { + "epoch": 0.9612326959084072, + "grad_norm": 1.1511226393962957, + "learning_rate": 7.86039766673874e-08, + "loss": 0.7526, + "step": 15658 + }, + { + "epoch": 0.9612940851468738, + "grad_norm": 1.0289151470024873, + "learning_rate": 7.835535872540045e-08, + "loss": 0.707, + "step": 15659 + }, + { + "epoch": 0.9613554743853403, + "grad_norm": 1.0706643238599929, + "learning_rate": 7.810713303909034e-08, + "loss": 0.6695, + "step": 15660 + }, + { + "epoch": 0.9614168636238067, + "grad_norm": 1.0766199571805857, + "learning_rate": 7.785929961827254e-08, + "loss": 0.7515, + "step": 15661 + }, + { + "epoch": 0.9614782528622733, + "grad_norm": 1.0074048579090498, + "learning_rate": 7.761185847274367e-08, + "loss": 0.716, + "step": 15662 + }, + { + "epoch": 0.9615396421007397, + "grad_norm": 1.0782816494524763, + "learning_rate": 7.736480961228588e-08, + "loss": 0.7247, + "step": 15663 + }, + { + "epoch": 0.9616010313392063, + "grad_norm": 1.0315998434076428, + "learning_rate": 7.711815304666804e-08, + "loss": 0.6772, + "step": 15664 + }, + { + "epoch": 0.9616624205776727, + "grad_norm": 0.9870470364791584, + "learning_rate": 7.687188878564122e-08, + "loss": 0.7218, + "step": 15665 + }, + { + "epoch": 0.9617238098161393, + "grad_norm": 0.5887799637926969, + "learning_rate": 7.662601683893988e-08, + "loss": 0.6309, + "step": 15666 + }, + { + "epoch": 0.9617851990546057, + "grad_norm": 1.0186265029745343, + "learning_rate": 7.638053721628735e-08, + "loss": 0.663, + "step": 15667 + }, + { + "epoch": 0.9618465882930722, + "grad_norm": 1.0742837590624863, + "learning_rate": 7.613544992738697e-08, + "loss": 0.7065, + "step": 15668 + }, + { + "epoch": 0.9619079775315387, + "grad_norm": 1.0620283703474795, + "learning_rate": 7.589075498192878e-08, + "loss": 0.6805, + "step": 15669 + }, + { + "epoch": 0.9619693667700052, + "grad_norm": 0.9803478820200178, + "learning_rate": 7.564645238958612e-08, + "loss": 0.7097, + "step": 15670 + }, + { + "epoch": 0.9620307560084718, + "grad_norm": 1.0241253458491546, + "learning_rate": 7.540254216002019e-08, + "loss": 0.7585, + "step": 15671 + }, + { + "epoch": 0.9620921452469382, + "grad_norm": 1.0327251845447456, + "learning_rate": 7.515902430287103e-08, + "loss": 0.6929, + "step": 15672 + }, + { + "epoch": 0.9621535344854047, + "grad_norm": 1.0907447934187509, + "learning_rate": 7.491589882776761e-08, + "loss": 0.7276, + "step": 15673 + }, + { + "epoch": 0.9622149237238712, + "grad_norm": 0.9055961837144219, + "learning_rate": 7.467316574432115e-08, + "loss": 0.7028, + "step": 15674 + }, + { + "epoch": 0.9622763129623377, + "grad_norm": 1.04114798437702, + "learning_rate": 7.443082506212951e-08, + "loss": 0.7814, + "step": 15675 + }, + { + "epoch": 0.9623377022008042, + "grad_norm": 1.0655989473898528, + "learning_rate": 7.41888767907728e-08, + "loss": 0.7829, + "step": 15676 + }, + { + "epoch": 0.9623990914392707, + "grad_norm": 1.0676178084078312, + "learning_rate": 7.394732093981783e-08, + "loss": 0.7237, + "step": 15677 + }, + { + "epoch": 0.9624604806777372, + "grad_norm": 0.9497763218874387, + "learning_rate": 7.37061575188125e-08, + "loss": 0.7475, + "step": 15678 + }, + { + "epoch": 0.9625218699162037, + "grad_norm": 1.058774149103415, + "learning_rate": 7.346538653729252e-08, + "loss": 0.7269, + "step": 15679 + }, + { + "epoch": 0.9625832591546701, + "grad_norm": 1.1445435298947615, + "learning_rate": 7.322500800477583e-08, + "loss": 0.7678, + "step": 15680 + }, + { + "epoch": 0.9626446483931367, + "grad_norm": 1.2190561011103267, + "learning_rate": 7.298502193076817e-08, + "loss": 0.7539, + "step": 15681 + }, + { + "epoch": 0.9627060376316032, + "grad_norm": 1.2198213603654562, + "learning_rate": 7.274542832475529e-08, + "loss": 0.7289, + "step": 15682 + }, + { + "epoch": 0.9627674268700697, + "grad_norm": 1.1137493707566577, + "learning_rate": 7.250622719620959e-08, + "loss": 0.7741, + "step": 15683 + }, + { + "epoch": 0.9628288161085362, + "grad_norm": 1.0872876421117381, + "learning_rate": 7.226741855458908e-08, + "loss": 0.733, + "step": 15684 + }, + { + "epoch": 0.9628902053470026, + "grad_norm": 0.971197552918387, + "learning_rate": 7.202900240933507e-08, + "loss": 0.7856, + "step": 15685 + }, + { + "epoch": 0.9629515945854692, + "grad_norm": 1.2212724568261175, + "learning_rate": 7.17909787698745e-08, + "loss": 0.7233, + "step": 15686 + }, + { + "epoch": 0.9630129838239356, + "grad_norm": 1.0864296309979866, + "learning_rate": 7.155334764561428e-08, + "loss": 0.7639, + "step": 15687 + }, + { + "epoch": 0.9630743730624022, + "grad_norm": 1.1339260186845965, + "learning_rate": 7.131610904595133e-08, + "loss": 0.7298, + "step": 15688 + }, + { + "epoch": 0.9631357623008686, + "grad_norm": 1.0924491092764281, + "learning_rate": 7.10792629802659e-08, + "loss": 0.7344, + "step": 15689 + }, + { + "epoch": 0.9631971515393352, + "grad_norm": 0.9604830026418466, + "learning_rate": 7.084280945792055e-08, + "loss": 0.7901, + "step": 15690 + }, + { + "epoch": 0.9632585407778016, + "grad_norm": 0.994067253057223, + "learning_rate": 7.060674848826332e-08, + "loss": 0.7047, + "step": 15691 + }, + { + "epoch": 0.9633199300162681, + "grad_norm": 0.9720217605840225, + "learning_rate": 7.037108008062788e-08, + "loss": 0.7136, + "step": 15692 + }, + { + "epoch": 0.9633813192547347, + "grad_norm": 1.0049110480764725, + "learning_rate": 7.01358042443312e-08, + "loss": 0.6635, + "step": 15693 + }, + { + "epoch": 0.9634427084932011, + "grad_norm": 1.0198391167742582, + "learning_rate": 6.990092098867474e-08, + "loss": 0.7371, + "step": 15694 + }, + { + "epoch": 0.9635040977316677, + "grad_norm": 1.0907420664163339, + "learning_rate": 6.96664303229444e-08, + "loss": 0.7164, + "step": 15695 + }, + { + "epoch": 0.9635654869701341, + "grad_norm": 1.1465231496840307, + "learning_rate": 6.943233225641167e-08, + "loss": 0.7647, + "step": 15696 + }, + { + "epoch": 0.9636268762086007, + "grad_norm": 1.0983818330722803, + "learning_rate": 6.919862679833134e-08, + "loss": 0.7237, + "step": 15697 + }, + { + "epoch": 0.9636882654470671, + "grad_norm": 1.0778881032065608, + "learning_rate": 6.89653139579427e-08, + "loss": 0.6921, + "step": 15698 + }, + { + "epoch": 0.9637496546855336, + "grad_norm": 1.0108048243613894, + "learning_rate": 6.873239374446949e-08, + "loss": 0.7223, + "step": 15699 + }, + { + "epoch": 0.9638110439240001, + "grad_norm": 1.105641052103067, + "learning_rate": 6.849986616712212e-08, + "loss": 0.741, + "step": 15700 + }, + { + "epoch": 0.9638724331624666, + "grad_norm": 1.0804144245911758, + "learning_rate": 6.826773123509212e-08, + "loss": 0.7805, + "step": 15701 + }, + { + "epoch": 0.9639338224009332, + "grad_norm": 1.0545432017502516, + "learning_rate": 6.803598895755658e-08, + "loss": 0.7358, + "step": 15702 + }, + { + "epoch": 0.9639952116393996, + "grad_norm": 1.048603763813843, + "learning_rate": 6.780463934367931e-08, + "loss": 0.7353, + "step": 15703 + }, + { + "epoch": 0.9640566008778662, + "grad_norm": 1.0142904187142832, + "learning_rate": 6.757368240260521e-08, + "loss": 0.7461, + "step": 15704 + }, + { + "epoch": 0.9641179901163326, + "grad_norm": 1.092638279441023, + "learning_rate": 6.734311814346472e-08, + "loss": 0.6883, + "step": 15705 + }, + { + "epoch": 0.9641793793547991, + "grad_norm": 1.1236765659191035, + "learning_rate": 6.711294657537614e-08, + "loss": 0.6805, + "step": 15706 + }, + { + "epoch": 0.9642407685932656, + "grad_norm": 1.1085381526287297, + "learning_rate": 6.688316770743664e-08, + "loss": 0.7321, + "step": 15707 + }, + { + "epoch": 0.9643021578317321, + "grad_norm": 1.1127206845974822, + "learning_rate": 6.665378154873225e-08, + "loss": 0.7398, + "step": 15708 + }, + { + "epoch": 0.9643635470701986, + "grad_norm": 1.1052720654407233, + "learning_rate": 6.642478810833019e-08, + "loss": 0.7199, + "step": 15709 + }, + { + "epoch": 0.9644249363086651, + "grad_norm": 1.1279239730716375, + "learning_rate": 6.619618739528544e-08, + "loss": 0.738, + "step": 15710 + }, + { + "epoch": 0.9644863255471315, + "grad_norm": 0.9161599872773456, + "learning_rate": 6.59679794186352e-08, + "loss": 0.7154, + "step": 15711 + }, + { + "epoch": 0.9645477147855981, + "grad_norm": 1.0921193175129111, + "learning_rate": 6.574016418740115e-08, + "loss": 0.7168, + "step": 15712 + }, + { + "epoch": 0.9646091040240646, + "grad_norm": 1.0406044824340757, + "learning_rate": 6.551274171059052e-08, + "loss": 0.6998, + "step": 15713 + }, + { + "epoch": 0.9646704932625311, + "grad_norm": 1.1456914710659911, + "learning_rate": 6.528571199719502e-08, + "loss": 0.7472, + "step": 15714 + }, + { + "epoch": 0.9647318825009976, + "grad_norm": 1.0970997208094393, + "learning_rate": 6.505907505618969e-08, + "loss": 0.7156, + "step": 15715 + }, + { + "epoch": 0.964793271739464, + "grad_norm": 1.0293659429351087, + "learning_rate": 6.483283089653514e-08, + "loss": 0.6855, + "step": 15716 + }, + { + "epoch": 0.9648546609779306, + "grad_norm": 1.0245357448054253, + "learning_rate": 6.460697952717531e-08, + "loss": 0.7078, + "step": 15717 + }, + { + "epoch": 0.964916050216397, + "grad_norm": 1.1290512231935965, + "learning_rate": 6.438152095704087e-08, + "loss": 0.7549, + "step": 15718 + }, + { + "epoch": 0.9649774394548636, + "grad_norm": 1.1244103501914557, + "learning_rate": 6.415645519504354e-08, + "loss": 0.7403, + "step": 15719 + }, + { + "epoch": 0.96503882869333, + "grad_norm": 1.0555619907857976, + "learning_rate": 6.393178225008179e-08, + "loss": 0.6837, + "step": 15720 + }, + { + "epoch": 0.9651002179317966, + "grad_norm": 1.108450275290086, + "learning_rate": 6.37075021310396e-08, + "loss": 0.7013, + "step": 15721 + }, + { + "epoch": 0.965161607170263, + "grad_norm": 0.9787899281593173, + "learning_rate": 6.348361484678211e-08, + "loss": 0.6614, + "step": 15722 + }, + { + "epoch": 0.9652229964087295, + "grad_norm": 1.1050552029939422, + "learning_rate": 6.326012040616114e-08, + "loss": 0.666, + "step": 15723 + }, + { + "epoch": 0.9652843856471961, + "grad_norm": 0.9834185203587303, + "learning_rate": 6.303701881801404e-08, + "loss": 0.7226, + "step": 15724 + }, + { + "epoch": 0.9653457748856625, + "grad_norm": 1.0158261771540777, + "learning_rate": 6.281431009115935e-08, + "loss": 0.7508, + "step": 15725 + }, + { + "epoch": 0.9654071641241291, + "grad_norm": 1.0955724937301576, + "learning_rate": 6.259199423440332e-08, + "loss": 0.7373, + "step": 15726 + }, + { + "epoch": 0.9654685533625955, + "grad_norm": 1.1725344309756347, + "learning_rate": 6.237007125653449e-08, + "loss": 0.747, + "step": 15727 + }, + { + "epoch": 0.9655299426010621, + "grad_norm": 1.0363478493963905, + "learning_rate": 6.214854116632696e-08, + "loss": 0.7123, + "step": 15728 + }, + { + "epoch": 0.9655913318395285, + "grad_norm": 1.286455908035628, + "learning_rate": 6.192740397253926e-08, + "loss": 0.7457, + "step": 15729 + }, + { + "epoch": 0.965652721077995, + "grad_norm": 1.134586188415311, + "learning_rate": 6.170665968391332e-08, + "loss": 0.7161, + "step": 15730 + }, + { + "epoch": 0.9657141103164615, + "grad_norm": 1.1621479192011128, + "learning_rate": 6.148630830917768e-08, + "loss": 0.7935, + "step": 15731 + }, + { + "epoch": 0.965775499554928, + "grad_norm": 1.1606510458832946, + "learning_rate": 6.126634985704205e-08, + "loss": 0.7178, + "step": 15732 + }, + { + "epoch": 0.9658368887933945, + "grad_norm": 1.022266688186474, + "learning_rate": 6.104678433620503e-08, + "loss": 0.7389, + "step": 15733 + }, + { + "epoch": 0.965898278031861, + "grad_norm": 0.9455973647696537, + "learning_rate": 6.082761175534413e-08, + "loss": 0.6988, + "step": 15734 + }, + { + "epoch": 0.9659596672703276, + "grad_norm": 1.206603016147461, + "learning_rate": 6.060883212312796e-08, + "loss": 0.7485, + "step": 15735 + }, + { + "epoch": 0.966021056508794, + "grad_norm": 1.0331094885141736, + "learning_rate": 6.039044544820404e-08, + "loss": 0.6973, + "step": 15736 + }, + { + "epoch": 0.9660824457472605, + "grad_norm": 1.1427705409531825, + "learning_rate": 6.01724517392055e-08, + "loss": 0.7288, + "step": 15737 + }, + { + "epoch": 0.966143834985727, + "grad_norm": 1.200291181229402, + "learning_rate": 5.995485100475207e-08, + "loss": 0.737, + "step": 15738 + }, + { + "epoch": 0.9662052242241935, + "grad_norm": 1.0589842957598916, + "learning_rate": 5.973764325344689e-08, + "loss": 0.7913, + "step": 15739 + }, + { + "epoch": 0.96626661346266, + "grad_norm": 1.218470621596955, + "learning_rate": 5.9520828493876416e-08, + "loss": 0.7294, + "step": 15740 + }, + { + "epoch": 0.9663280027011265, + "grad_norm": 1.1072880933052909, + "learning_rate": 5.93044067346138e-08, + "loss": 0.6898, + "step": 15741 + }, + { + "epoch": 0.966389391939593, + "grad_norm": 1.1200267881774606, + "learning_rate": 5.9088377984214404e-08, + "loss": 0.7053, + "step": 15742 + }, + { + "epoch": 0.9664507811780595, + "grad_norm": 1.0041078129235106, + "learning_rate": 5.8872742251219197e-08, + "loss": 0.7224, + "step": 15743 + }, + { + "epoch": 0.9665121704165259, + "grad_norm": 0.9931493377511595, + "learning_rate": 5.865749954415245e-08, + "loss": 0.6982, + "step": 15744 + }, + { + "epoch": 0.9665735596549925, + "grad_norm": 1.0047655250576202, + "learning_rate": 5.8442649871526255e-08, + "loss": 0.7444, + "step": 15745 + }, + { + "epoch": 0.966634948893459, + "grad_norm": 1.0583491553243334, + "learning_rate": 5.82281932418316e-08, + "loss": 0.7594, + "step": 15746 + }, + { + "epoch": 0.9666963381319255, + "grad_norm": 1.0581042932441864, + "learning_rate": 5.801412966355058e-08, + "loss": 0.7254, + "step": 15747 + }, + { + "epoch": 0.966757727370392, + "grad_norm": 1.1261317300667826, + "learning_rate": 5.78004591451431e-08, + "loss": 0.7413, + "step": 15748 + }, + { + "epoch": 0.9668191166088584, + "grad_norm": 0.9279541480614024, + "learning_rate": 5.7587181695057945e-08, + "loss": 0.7502, + "step": 15749 + }, + { + "epoch": 0.966880505847325, + "grad_norm": 1.1154463121957376, + "learning_rate": 5.737429732172839e-08, + "loss": 0.6876, + "step": 15750 + }, + { + "epoch": 0.9669418950857914, + "grad_norm": 1.110770840835162, + "learning_rate": 5.71618060335688e-08, + "loss": 0.7202, + "step": 15751 + }, + { + "epoch": 0.967003284324258, + "grad_norm": 0.976731225560377, + "learning_rate": 5.694970783898246e-08, + "loss": 0.7458, + "step": 15752 + }, + { + "epoch": 0.9670646735627244, + "grad_norm": 1.0682325424797967, + "learning_rate": 5.673800274635266e-08, + "loss": 0.7687, + "step": 15753 + }, + { + "epoch": 0.967126062801191, + "grad_norm": 1.0953417987407674, + "learning_rate": 5.6526690764049375e-08, + "loss": 0.7008, + "step": 15754 + }, + { + "epoch": 0.9671874520396575, + "grad_norm": 1.1592686681128064, + "learning_rate": 5.631577190042814e-08, + "loss": 0.72, + "step": 15755 + }, + { + "epoch": 0.9672488412781239, + "grad_norm": 0.9605859398492143, + "learning_rate": 5.610524616382562e-08, + "loss": 0.6762, + "step": 15756 + }, + { + "epoch": 0.9673102305165905, + "grad_norm": 1.1093864683938803, + "learning_rate": 5.5895113562567386e-08, + "loss": 0.7796, + "step": 15757 + }, + { + "epoch": 0.9673716197550569, + "grad_norm": 1.0655407005755935, + "learning_rate": 5.568537410496122e-08, + "loss": 0.7047, + "step": 15758 + }, + { + "epoch": 0.9674330089935235, + "grad_norm": 0.9941305470584763, + "learning_rate": 5.547602779929606e-08, + "loss": 0.7428, + "step": 15759 + }, + { + "epoch": 0.9674943982319899, + "grad_norm": 1.003333655344818, + "learning_rate": 5.526707465385195e-08, + "loss": 0.6947, + "step": 15760 + }, + { + "epoch": 0.9675557874704565, + "grad_norm": 0.9926921402009039, + "learning_rate": 5.5058514676888944e-08, + "loss": 0.7337, + "step": 15761 + }, + { + "epoch": 0.9676171767089229, + "grad_norm": 1.0990735380561116, + "learning_rate": 5.4850347876650446e-08, + "loss": 0.7016, + "step": 15762 + }, + { + "epoch": 0.9676785659473894, + "grad_norm": 1.041924404197872, + "learning_rate": 5.464257426136876e-08, + "loss": 0.6911, + "step": 15763 + }, + { + "epoch": 0.9677399551858559, + "grad_norm": 1.0479109640233084, + "learning_rate": 5.443519383925844e-08, + "loss": 0.7251, + "step": 15764 + }, + { + "epoch": 0.9678013444243224, + "grad_norm": 1.0192589988333665, + "learning_rate": 5.4228206618516243e-08, + "loss": 0.7089, + "step": 15765 + }, + { + "epoch": 0.967862733662789, + "grad_norm": 1.0703972210013557, + "learning_rate": 5.402161260732786e-08, + "loss": 0.7202, + "step": 15766 + }, + { + "epoch": 0.9679241229012554, + "grad_norm": 1.0556176666119321, + "learning_rate": 5.381541181386008e-08, + "loss": 0.7405, + "step": 15767 + }, + { + "epoch": 0.967985512139722, + "grad_norm": 1.0209358604463994, + "learning_rate": 5.3609604246264157e-08, + "loss": 0.7204, + "step": 15768 + }, + { + "epoch": 0.9680469013781884, + "grad_norm": 1.0527654073128065, + "learning_rate": 5.340418991267804e-08, + "loss": 0.7586, + "step": 15769 + }, + { + "epoch": 0.9681082906166549, + "grad_norm": 0.9355580394921231, + "learning_rate": 5.3199168821223e-08, + "loss": 0.6957, + "step": 15770 + }, + { + "epoch": 0.9681696798551214, + "grad_norm": 0.9805393885694428, + "learning_rate": 5.299454098000256e-08, + "loss": 0.7291, + "step": 15771 + }, + { + "epoch": 0.9682310690935879, + "grad_norm": 1.062672095982512, + "learning_rate": 5.279030639710914e-08, + "loss": 0.7393, + "step": 15772 + }, + { + "epoch": 0.9682924583320544, + "grad_norm": 1.0145091342620454, + "learning_rate": 5.2586465080616266e-08, + "loss": 0.7577, + "step": 15773 + }, + { + "epoch": 0.9683538475705209, + "grad_norm": 0.934958213628613, + "learning_rate": 5.238301703858306e-08, + "loss": 0.7438, + "step": 15774 + }, + { + "epoch": 0.9684152368089873, + "grad_norm": 1.2015110722495577, + "learning_rate": 5.217996227905309e-08, + "loss": 0.7475, + "step": 15775 + }, + { + "epoch": 0.9684766260474539, + "grad_norm": 0.9297817203359584, + "learning_rate": 5.1977300810053255e-08, + "loss": 0.7065, + "step": 15776 + }, + { + "epoch": 0.9685380152859204, + "grad_norm": 1.0718161181253183, + "learning_rate": 5.177503263959604e-08, + "loss": 0.7381, + "step": 15777 + }, + { + "epoch": 0.9685994045243869, + "grad_norm": 1.1165530526328011, + "learning_rate": 5.15731577756795e-08, + "loss": 0.7431, + "step": 15778 + }, + { + "epoch": 0.9686607937628534, + "grad_norm": 1.0927250946485119, + "learning_rate": 5.137167622628392e-08, + "loss": 0.7042, + "step": 15779 + }, + { + "epoch": 0.9687221830013198, + "grad_norm": 0.9682971443903514, + "learning_rate": 5.117058799937513e-08, + "loss": 0.7331, + "step": 15780 + }, + { + "epoch": 0.9687835722397864, + "grad_norm": 1.0364566919472742, + "learning_rate": 5.096989310290235e-08, + "loss": 0.7158, + "step": 15781 + }, + { + "epoch": 0.9688449614782528, + "grad_norm": 1.058654353680781, + "learning_rate": 5.076959154480143e-08, + "loss": 0.7416, + "step": 15782 + }, + { + "epoch": 0.9689063507167194, + "grad_norm": 1.1009318581987513, + "learning_rate": 5.0569683332990506e-08, + "loss": 0.7163, + "step": 15783 + }, + { + "epoch": 0.9689677399551858, + "grad_norm": 0.9435580487436146, + "learning_rate": 5.0370168475373235e-08, + "loss": 0.692, + "step": 15784 + }, + { + "epoch": 0.9690291291936524, + "grad_norm": 0.9545012235296438, + "learning_rate": 5.017104697983777e-08, + "loss": 0.7267, + "step": 15785 + }, + { + "epoch": 0.9690905184321188, + "grad_norm": 1.014712898228909, + "learning_rate": 4.9972318854256684e-08, + "loss": 0.6762, + "step": 15786 + }, + { + "epoch": 0.9691519076705853, + "grad_norm": 1.107976075545414, + "learning_rate": 4.9773984106485926e-08, + "loss": 0.6853, + "step": 15787 + }, + { + "epoch": 0.9692132969090519, + "grad_norm": 1.0620240017610876, + "learning_rate": 4.9576042744367e-08, + "loss": 0.7735, + "step": 15788 + }, + { + "epoch": 0.9692746861475183, + "grad_norm": 0.9628688050693822, + "learning_rate": 4.937849477572587e-08, + "loss": 0.6771, + "step": 15789 + }, + { + "epoch": 0.9693360753859849, + "grad_norm": 1.148440006097763, + "learning_rate": 4.9181340208371843e-08, + "loss": 0.7149, + "step": 15790 + }, + { + "epoch": 0.9693974646244513, + "grad_norm": 1.0391701406835314, + "learning_rate": 4.89845790501009e-08, + "loss": 0.7154, + "step": 15791 + }, + { + "epoch": 0.9694588538629179, + "grad_norm": 1.079715493909472, + "learning_rate": 4.878821130869127e-08, + "loss": 0.728, + "step": 15792 + }, + { + "epoch": 0.9695202431013843, + "grad_norm": 1.0429702014218107, + "learning_rate": 4.859223699190674e-08, + "loss": 0.707, + "step": 15793 + }, + { + "epoch": 0.9695816323398508, + "grad_norm": 1.1473251472811654, + "learning_rate": 4.8396656107493334e-08, + "loss": 0.7231, + "step": 15794 + }, + { + "epoch": 0.9696430215783173, + "grad_norm": 1.130887707322817, + "learning_rate": 4.820146866318709e-08, + "loss": 0.6967, + "step": 15795 + }, + { + "epoch": 0.9697044108167838, + "grad_norm": 1.0354530568727782, + "learning_rate": 4.800667466670183e-08, + "loss": 0.7077, + "step": 15796 + }, + { + "epoch": 0.9697658000552503, + "grad_norm": 1.094182161540813, + "learning_rate": 4.78122741257403e-08, + "loss": 0.7091, + "step": 15797 + }, + { + "epoch": 0.9698271892937168, + "grad_norm": 1.1222582303095632, + "learning_rate": 4.7618267047986335e-08, + "loss": 0.7078, + "step": 15798 + }, + { + "epoch": 0.9698885785321834, + "grad_norm": 1.0886676522227166, + "learning_rate": 4.742465344111269e-08, + "loss": 0.7122, + "step": 15799 + }, + { + "epoch": 0.9699499677706498, + "grad_norm": 1.0584149793298614, + "learning_rate": 4.7231433312772134e-08, + "loss": 0.7084, + "step": 15800 + }, + { + "epoch": 0.9700113570091163, + "grad_norm": 1.044271157848836, + "learning_rate": 4.703860667060301e-08, + "loss": 0.7402, + "step": 15801 + }, + { + "epoch": 0.9700727462475828, + "grad_norm": 1.1406994499815635, + "learning_rate": 4.684617352223142e-08, + "loss": 0.7417, + "step": 15802 + }, + { + "epoch": 0.9701341354860493, + "grad_norm": 0.9199921058904617, + "learning_rate": 4.665413387526352e-08, + "loss": 0.7206, + "step": 15803 + }, + { + "epoch": 0.9701955247245158, + "grad_norm": 1.0149168694833337, + "learning_rate": 4.6462487737292115e-08, + "loss": 0.7551, + "step": 15804 + }, + { + "epoch": 0.9702569139629823, + "grad_norm": 1.1218042042734098, + "learning_rate": 4.6271235115893374e-08, + "loss": 0.7427, + "step": 15805 + }, + { + "epoch": 0.9703183032014487, + "grad_norm": 1.055288198389205, + "learning_rate": 4.608037601862903e-08, + "loss": 0.7203, + "step": 15806 + }, + { + "epoch": 0.9703796924399153, + "grad_norm": 1.082761725441733, + "learning_rate": 4.588991045304525e-08, + "loss": 0.7468, + "step": 15807 + }, + { + "epoch": 0.9704410816783818, + "grad_norm": 1.0837530054297386, + "learning_rate": 4.5699838426670474e-08, + "loss": 0.7642, + "step": 15808 + }, + { + "epoch": 0.9705024709168483, + "grad_norm": 0.9795577983870634, + "learning_rate": 4.551015994702201e-08, + "loss": 0.7677, + "step": 15809 + }, + { + "epoch": 0.9705638601553148, + "grad_norm": 1.0051256044514678, + "learning_rate": 4.53208750215961e-08, + "loss": 0.7108, + "step": 15810 + }, + { + "epoch": 0.9706252493937813, + "grad_norm": 1.0366224217887743, + "learning_rate": 4.513198365787785e-08, + "loss": 0.7259, + "step": 15811 + }, + { + "epoch": 0.9706866386322478, + "grad_norm": 1.0804633576531555, + "learning_rate": 4.494348586333353e-08, + "loss": 0.7471, + "step": 15812 + }, + { + "epoch": 0.9707480278707142, + "grad_norm": 1.1862685834206894, + "learning_rate": 4.475538164541826e-08, + "loss": 0.7492, + "step": 15813 + }, + { + "epoch": 0.9708094171091808, + "grad_norm": 1.0413243735382929, + "learning_rate": 4.4567671011567224e-08, + "loss": 0.6907, + "step": 15814 + }, + { + "epoch": 0.9708708063476472, + "grad_norm": 1.0427148288718286, + "learning_rate": 4.438035396920004e-08, + "loss": 0.7452, + "step": 15815 + }, + { + "epoch": 0.9709321955861138, + "grad_norm": 1.015959335198253, + "learning_rate": 4.419343052572411e-08, + "loss": 0.6997, + "step": 15816 + }, + { + "epoch": 0.9709935848245802, + "grad_norm": 1.0662954973799748, + "learning_rate": 4.40069006885302e-08, + "loss": 0.6931, + "step": 15817 + }, + { + "epoch": 0.9710549740630467, + "grad_norm": 1.0599657056937266, + "learning_rate": 4.3820764464991286e-08, + "loss": 0.7129, + "step": 15818 + }, + { + "epoch": 0.9711163633015133, + "grad_norm": 1.0104334867569091, + "learning_rate": 4.363502186246704e-08, + "loss": 0.6933, + "step": 15819 + }, + { + "epoch": 0.9711777525399797, + "grad_norm": 1.0478456982346533, + "learning_rate": 4.34496728883016e-08, + "loss": 0.7452, + "step": 15820 + }, + { + "epoch": 0.9712391417784463, + "grad_norm": 1.0474656286442163, + "learning_rate": 4.326471754982131e-08, + "loss": 0.7192, + "step": 15821 + }, + { + "epoch": 0.9713005310169127, + "grad_norm": 1.2687430027567743, + "learning_rate": 4.3080155854338116e-08, + "loss": 0.726, + "step": 15822 + }, + { + "epoch": 0.9713619202553793, + "grad_norm": 1.1854922688312834, + "learning_rate": 4.2895987809150605e-08, + "loss": 0.755, + "step": 15823 + }, + { + "epoch": 0.9714233094938457, + "grad_norm": 1.094817205271589, + "learning_rate": 4.271221342153964e-08, + "loss": 0.7079, + "step": 15824 + }, + { + "epoch": 0.9714846987323122, + "grad_norm": 1.125816161770419, + "learning_rate": 4.2528832698769395e-08, + "loss": 0.7312, + "step": 15825 + }, + { + "epoch": 0.9715460879707787, + "grad_norm": 1.0820900799819757, + "learning_rate": 4.2345845648090743e-08, + "loss": 0.722, + "step": 15826 + }, + { + "epoch": 0.9716074772092452, + "grad_norm": 1.0831683470302058, + "learning_rate": 4.21632522767379e-08, + "loss": 0.774, + "step": 15827 + }, + { + "epoch": 0.9716688664477117, + "grad_norm": 1.1419863186964032, + "learning_rate": 4.198105259193064e-08, + "loss": 0.6664, + "step": 15828 + }, + { + "epoch": 0.9717302556861782, + "grad_norm": 0.6015329485606321, + "learning_rate": 4.179924660087098e-08, + "loss": 0.6379, + "step": 15829 + }, + { + "epoch": 0.9717916449246448, + "grad_norm": 1.0824801966535766, + "learning_rate": 4.161783431074762e-08, + "loss": 0.7712, + "step": 15830 + }, + { + "epoch": 0.9718530341631112, + "grad_norm": 1.172132616729115, + "learning_rate": 4.143681572873259e-08, + "loss": 0.7036, + "step": 15831 + }, + { + "epoch": 0.9719144234015777, + "grad_norm": 1.0474684522284614, + "learning_rate": 4.12561908619824e-08, + "loss": 0.7583, + "step": 15832 + }, + { + "epoch": 0.9719758126400442, + "grad_norm": 1.023106966420068, + "learning_rate": 4.107595971763689e-08, + "loss": 0.7086, + "step": 15833 + }, + { + "epoch": 0.9720372018785107, + "grad_norm": 1.1964772522432527, + "learning_rate": 4.0896122302824804e-08, + "loss": 0.7374, + "step": 15834 + }, + { + "epoch": 0.9720985911169772, + "grad_norm": 1.0407408720105202, + "learning_rate": 4.0716678624652676e-08, + "loss": 0.6959, + "step": 15835 + }, + { + "epoch": 0.9721599803554437, + "grad_norm": 1.0615713154890813, + "learning_rate": 4.053762869021705e-08, + "loss": 0.7044, + "step": 15836 + }, + { + "epoch": 0.9722213695939101, + "grad_norm": 1.0442750094117446, + "learning_rate": 4.0358972506594486e-08, + "loss": 0.7525, + "step": 15837 + }, + { + "epoch": 0.9722827588323767, + "grad_norm": 0.9144453417639486, + "learning_rate": 4.018071008085045e-08, + "loss": 0.7024, + "step": 15838 + }, + { + "epoch": 0.9723441480708431, + "grad_norm": 1.0885087597092171, + "learning_rate": 4.000284142003264e-08, + "loss": 0.7029, + "step": 15839 + }, + { + "epoch": 0.9724055373093097, + "grad_norm": 1.1603152406017605, + "learning_rate": 3.982536653117097e-08, + "loss": 0.7337, + "step": 15840 + }, + { + "epoch": 0.9724669265477762, + "grad_norm": 1.2162119703566245, + "learning_rate": 3.964828542128429e-08, + "loss": 0.692, + "step": 15841 + }, + { + "epoch": 0.9725283157862427, + "grad_norm": 1.246998970352002, + "learning_rate": 3.9471598097372554e-08, + "loss": 0.7263, + "step": 15842 + }, + { + "epoch": 0.9725897050247092, + "grad_norm": 1.0607777371828566, + "learning_rate": 3.929530456642017e-08, + "loss": 0.704, + "step": 15843 + }, + { + "epoch": 0.9726510942631756, + "grad_norm": 1.2062576613161384, + "learning_rate": 3.911940483539933e-08, + "loss": 0.7776, + "step": 15844 + }, + { + "epoch": 0.9727124835016422, + "grad_norm": 1.1284217757814758, + "learning_rate": 3.8943898911262266e-08, + "loss": 0.6846, + "step": 15845 + }, + { + "epoch": 0.9727738727401086, + "grad_norm": 1.0231216139214219, + "learning_rate": 3.876878680094787e-08, + "loss": 0.73, + "step": 15846 + }, + { + "epoch": 0.9728352619785752, + "grad_norm": 1.0558464878637204, + "learning_rate": 3.859406851138059e-08, + "loss": 0.6822, + "step": 15847 + }, + { + "epoch": 0.9728966512170416, + "grad_norm": 1.1470430888531693, + "learning_rate": 3.841974404946602e-08, + "loss": 0.7204, + "step": 15848 + }, + { + "epoch": 0.9729580404555082, + "grad_norm": 1.1130919800694592, + "learning_rate": 3.8245813422098653e-08, + "loss": 0.7353, + "step": 15849 + }, + { + "epoch": 0.9730194296939746, + "grad_norm": 1.0518115919525215, + "learning_rate": 3.8072276636152985e-08, + "loss": 0.7287, + "step": 15850 + }, + { + "epoch": 0.9730808189324411, + "grad_norm": 1.029517265873864, + "learning_rate": 3.789913369849019e-08, + "loss": 0.7237, + "step": 15851 + }, + { + "epoch": 0.9731422081709077, + "grad_norm": 1.0761680752174232, + "learning_rate": 3.77263846159559e-08, + "loss": 0.7279, + "step": 15852 + }, + { + "epoch": 0.9732035974093741, + "grad_norm": 1.0366610319035092, + "learning_rate": 3.755402939537911e-08, + "loss": 0.7735, + "step": 15853 + }, + { + "epoch": 0.9732649866478407, + "grad_norm": 1.0442756638237018, + "learning_rate": 3.738206804357436e-08, + "loss": 0.7329, + "step": 15854 + }, + { + "epoch": 0.9733263758863071, + "grad_norm": 1.0369774414184152, + "learning_rate": 3.721050056734066e-08, + "loss": 0.6825, + "step": 15855 + }, + { + "epoch": 0.9733877651247737, + "grad_norm": 1.0372001701109912, + "learning_rate": 3.7039326973461465e-08, + "loss": 0.7044, + "step": 15856 + }, + { + "epoch": 0.9734491543632401, + "grad_norm": 1.1278854314833078, + "learning_rate": 3.6868547268702484e-08, + "loss": 0.7021, + "step": 15857 + }, + { + "epoch": 0.9735105436017066, + "grad_norm": 1.1348926063244649, + "learning_rate": 3.669816145981608e-08, + "loss": 0.7437, + "step": 15858 + }, + { + "epoch": 0.9735719328401731, + "grad_norm": 1.0242653623232036, + "learning_rate": 3.652816955353911e-08, + "loss": 0.678, + "step": 15859 + }, + { + "epoch": 0.9736333220786396, + "grad_norm": 1.0802218520734794, + "learning_rate": 3.6358571556592834e-08, + "loss": 0.7455, + "step": 15860 + }, + { + "epoch": 0.9736947113171062, + "grad_norm": 1.2700092221948318, + "learning_rate": 3.61893674756808e-08, + "loss": 0.7065, + "step": 15861 + }, + { + "epoch": 0.9737561005555726, + "grad_norm": 1.1666697123435237, + "learning_rate": 3.60205573174921e-08, + "loss": 0.7354, + "step": 15862 + }, + { + "epoch": 0.9738174897940391, + "grad_norm": 1.1481761294067232, + "learning_rate": 3.5852141088703604e-08, + "loss": 0.7596, + "step": 15863 + }, + { + "epoch": 0.9738788790325056, + "grad_norm": 1.0385872936907412, + "learning_rate": 3.568411879597111e-08, + "loss": 0.7434, + "step": 15864 + }, + { + "epoch": 0.9739402682709721, + "grad_norm": 1.0164632678657202, + "learning_rate": 3.55164904459393e-08, + "loss": 0.6993, + "step": 15865 + }, + { + "epoch": 0.9740016575094386, + "grad_norm": 1.1500025656375044, + "learning_rate": 3.534925604523287e-08, + "loss": 0.6708, + "step": 15866 + }, + { + "epoch": 0.9740630467479051, + "grad_norm": 1.1117780325889304, + "learning_rate": 3.5182415600466534e-08, + "loss": 0.7023, + "step": 15867 + }, + { + "epoch": 0.9741244359863716, + "grad_norm": 1.014399580342334, + "learning_rate": 3.501596911823391e-08, + "loss": 0.7097, + "step": 15868 + }, + { + "epoch": 0.9741858252248381, + "grad_norm": 1.0433802350286572, + "learning_rate": 3.4849916605117496e-08, + "loss": 0.7416, + "step": 15869 + }, + { + "epoch": 0.9742472144633045, + "grad_norm": 1.0735313903787942, + "learning_rate": 3.468425806767983e-08, + "loss": 0.7156, + "step": 15870 + }, + { + "epoch": 0.9743086037017711, + "grad_norm": 1.148628731010014, + "learning_rate": 3.4518993512473456e-08, + "loss": 0.7056, + "step": 15871 + }, + { + "epoch": 0.9743699929402376, + "grad_norm": 1.0242436225876939, + "learning_rate": 3.435412294602869e-08, + "loss": 0.708, + "step": 15872 + }, + { + "epoch": 0.9744313821787041, + "grad_norm": 0.9273035741530581, + "learning_rate": 3.4189646374866994e-08, + "loss": 0.6724, + "step": 15873 + }, + { + "epoch": 0.9744927714171706, + "grad_norm": 1.0754482507113203, + "learning_rate": 3.4025563805488714e-08, + "loss": 0.7759, + "step": 15874 + }, + { + "epoch": 0.974554160655637, + "grad_norm": 1.0480488795630405, + "learning_rate": 3.3861875244380896e-08, + "loss": 0.7176, + "step": 15875 + }, + { + "epoch": 0.9746155498941036, + "grad_norm": 1.0851233231359698, + "learning_rate": 3.369858069801612e-08, + "loss": 0.7272, + "step": 15876 + }, + { + "epoch": 0.97467693913257, + "grad_norm": 1.1232091926204464, + "learning_rate": 3.353568017285036e-08, + "loss": 0.7504, + "step": 15877 + }, + { + "epoch": 0.9747383283710366, + "grad_norm": 0.9877761273804637, + "learning_rate": 3.3373173675324e-08, + "loss": 0.7946, + "step": 15878 + }, + { + "epoch": 0.974799717609503, + "grad_norm": 1.0746459054951876, + "learning_rate": 3.3211061211860796e-08, + "loss": 0.6921, + "step": 15879 + }, + { + "epoch": 0.9748611068479696, + "grad_norm": 1.0367890429531372, + "learning_rate": 3.3049342788871175e-08, + "loss": 0.6921, + "step": 15880 + }, + { + "epoch": 0.974922496086436, + "grad_norm": 1.0376832003791938, + "learning_rate": 3.28880184127478e-08, + "loss": 0.7338, + "step": 15881 + }, + { + "epoch": 0.9749838853249025, + "grad_norm": 1.1122762505080173, + "learning_rate": 3.27270880898678e-08, + "loss": 0.7391, + "step": 15882 + }, + { + "epoch": 0.9750452745633691, + "grad_norm": 1.124079624742045, + "learning_rate": 3.256655182659607e-08, + "loss": 0.7493, + "step": 15883 + }, + { + "epoch": 0.9751066638018355, + "grad_norm": 1.0550619217807786, + "learning_rate": 3.2406409629277546e-08, + "loss": 0.6936, + "step": 15884 + }, + { + "epoch": 0.9751680530403021, + "grad_norm": 1.089064379333353, + "learning_rate": 3.224666150424383e-08, + "loss": 0.7311, + "step": 15885 + }, + { + "epoch": 0.9752294422787685, + "grad_norm": 1.0475406843160864, + "learning_rate": 3.208730745781097e-08, + "loss": 0.7274, + "step": 15886 + }, + { + "epoch": 0.9752908315172351, + "grad_norm": 0.9261308941247, + "learning_rate": 3.192834749627949e-08, + "loss": 0.7194, + "step": 15887 + }, + { + "epoch": 0.9753522207557015, + "grad_norm": 1.0190858729836316, + "learning_rate": 3.1769781625933246e-08, + "loss": 0.6677, + "step": 15888 + }, + { + "epoch": 0.975413609994168, + "grad_norm": 0.9123180238544683, + "learning_rate": 3.161160985304168e-08, + "loss": 0.764, + "step": 15889 + }, + { + "epoch": 0.9754749992326345, + "grad_norm": 1.073779700915406, + "learning_rate": 3.145383218385756e-08, + "loss": 0.7236, + "step": 15890 + }, + { + "epoch": 0.975536388471101, + "grad_norm": 1.2347252915755018, + "learning_rate": 3.129644862461922e-08, + "loss": 0.7008, + "step": 15891 + }, + { + "epoch": 0.9755977777095675, + "grad_norm": 1.0242426736043966, + "learning_rate": 3.113945918154837e-08, + "loss": 0.6881, + "step": 15892 + }, + { + "epoch": 0.975659166948034, + "grad_norm": 1.0546297363843782, + "learning_rate": 3.0982863860851145e-08, + "loss": 0.7047, + "step": 15893 + }, + { + "epoch": 0.9757205561865006, + "grad_norm": 0.9841885289056893, + "learning_rate": 3.082666266872036e-08, + "loss": 0.6954, + "step": 15894 + }, + { + "epoch": 0.975781945424967, + "grad_norm": 1.0439312553060327, + "learning_rate": 3.067085561132998e-08, + "loss": 0.7039, + "step": 15895 + }, + { + "epoch": 0.9758433346634335, + "grad_norm": 0.957479591509577, + "learning_rate": 3.0515442694840636e-08, + "loss": 0.7026, + "step": 15896 + }, + { + "epoch": 0.9759047239019, + "grad_norm": 1.1282914027199578, + "learning_rate": 3.036042392539629e-08, + "loss": 0.6994, + "step": 15897 + }, + { + "epoch": 0.9759661131403665, + "grad_norm": 1.046605781287543, + "learning_rate": 3.0205799309126485e-08, + "loss": 0.7571, + "step": 15898 + }, + { + "epoch": 0.976027502378833, + "grad_norm": 1.126800204022912, + "learning_rate": 3.0051568852142996e-08, + "loss": 0.7553, + "step": 15899 + }, + { + "epoch": 0.9760888916172995, + "grad_norm": 1.0927826307935193, + "learning_rate": 2.989773256054429e-08, + "loss": 0.753, + "step": 15900 + }, + { + "epoch": 0.9761502808557659, + "grad_norm": 1.0186856800056043, + "learning_rate": 2.974429044041105e-08, + "loss": 0.728, + "step": 15901 + }, + { + "epoch": 0.9762116700942325, + "grad_norm": 1.0765945131973649, + "learning_rate": 2.9591242497811756e-08, + "loss": 0.754, + "step": 15902 + }, + { + "epoch": 0.9762730593326989, + "grad_norm": 1.1845826442683747, + "learning_rate": 2.9438588738796014e-08, + "loss": 0.7351, + "step": 15903 + }, + { + "epoch": 0.9763344485711655, + "grad_norm": 1.1421276598258894, + "learning_rate": 2.9286329169398997e-08, + "loss": 0.7331, + "step": 15904 + }, + { + "epoch": 0.976395837809632, + "grad_norm": 1.0256475705487749, + "learning_rate": 2.913446379564033e-08, + "loss": 0.7125, + "step": 15905 + }, + { + "epoch": 0.9764572270480985, + "grad_norm": 1.0167212065025542, + "learning_rate": 2.898299262352411e-08, + "loss": 0.6688, + "step": 15906 + }, + { + "epoch": 0.976518616286565, + "grad_norm": 1.0996743509659097, + "learning_rate": 2.8831915659039976e-08, + "loss": 0.7459, + "step": 15907 + }, + { + "epoch": 0.9765800055250314, + "grad_norm": 1.0404212751305126, + "learning_rate": 2.8681232908158718e-08, + "loss": 0.7053, + "step": 15908 + }, + { + "epoch": 0.976641394763498, + "grad_norm": 1.0584708322614145, + "learning_rate": 2.8530944376838898e-08, + "loss": 0.7725, + "step": 15909 + }, + { + "epoch": 0.9767027840019644, + "grad_norm": 1.0082105613700814, + "learning_rate": 2.8381050071022433e-08, + "loss": 0.7499, + "step": 15910 + }, + { + "epoch": 0.976764173240431, + "grad_norm": 0.8547767621222975, + "learning_rate": 2.823154999663458e-08, + "loss": 0.7071, + "step": 15911 + }, + { + "epoch": 0.9768255624788974, + "grad_norm": 1.0616524110651422, + "learning_rate": 2.8082444159586164e-08, + "loss": 0.7393, + "step": 15912 + }, + { + "epoch": 0.976886951717364, + "grad_norm": 1.151804643153672, + "learning_rate": 2.7933732565773587e-08, + "loss": 0.6881, + "step": 15913 + }, + { + "epoch": 0.9769483409558305, + "grad_norm": 1.1201493997530163, + "learning_rate": 2.7785415221073254e-08, + "loss": 0.7408, + "step": 15914 + }, + { + "epoch": 0.9770097301942969, + "grad_norm": 1.1323507096692587, + "learning_rate": 2.7637492131351585e-08, + "loss": 0.7013, + "step": 15915 + }, + { + "epoch": 0.9770711194327635, + "grad_norm": 1.1491481443348406, + "learning_rate": 2.7489963302455012e-08, + "loss": 0.6894, + "step": 15916 + }, + { + "epoch": 0.9771325086712299, + "grad_norm": 1.0330996558176566, + "learning_rate": 2.7342828740217765e-08, + "loss": 0.7131, + "step": 15917 + }, + { + "epoch": 0.9771938979096965, + "grad_norm": 1.1421648298202718, + "learning_rate": 2.719608845045518e-08, + "loss": 0.7418, + "step": 15918 + }, + { + "epoch": 0.9772552871481629, + "grad_norm": 1.0866995985686603, + "learning_rate": 2.7049742438970406e-08, + "loss": 0.7143, + "step": 15919 + }, + { + "epoch": 0.9773166763866294, + "grad_norm": 1.0637956842819705, + "learning_rate": 2.6903790711547694e-08, + "loss": 0.7255, + "step": 15920 + }, + { + "epoch": 0.9773780656250959, + "grad_norm": 0.9420910286584243, + "learning_rate": 2.67582332739591e-08, + "loss": 0.7726, + "step": 15921 + }, + { + "epoch": 0.9774394548635624, + "grad_norm": 1.0213914543632736, + "learning_rate": 2.6613070131956686e-08, + "loss": 0.7782, + "step": 15922 + }, + { + "epoch": 0.9775008441020289, + "grad_norm": 1.1306482644412992, + "learning_rate": 2.6468301291282526e-08, + "loss": 0.7213, + "step": 15923 + }, + { + "epoch": 0.9775622333404954, + "grad_norm": 1.1021884851322492, + "learning_rate": 2.6323926757657602e-08, + "loss": 0.7338, + "step": 15924 + }, + { + "epoch": 0.977623622578962, + "grad_norm": 0.9495949321084733, + "learning_rate": 2.617994653679068e-08, + "loss": 0.7141, + "step": 15925 + }, + { + "epoch": 0.9776850118174284, + "grad_norm": 1.0713524087385464, + "learning_rate": 2.603636063437498e-08, + "loss": 0.6967, + "step": 15926 + }, + { + "epoch": 0.9777464010558949, + "grad_norm": 1.041039049994215, + "learning_rate": 2.5893169056085966e-08, + "loss": 0.7271, + "step": 15927 + }, + { + "epoch": 0.9778077902943614, + "grad_norm": 0.956610737644022, + "learning_rate": 2.575037180758577e-08, + "loss": 0.6833, + "step": 15928 + }, + { + "epoch": 0.9778691795328279, + "grad_norm": 1.0293377864182816, + "learning_rate": 2.5607968894518775e-08, + "loss": 0.7504, + "step": 15929 + }, + { + "epoch": 0.9779305687712944, + "grad_norm": 0.9363659587981711, + "learning_rate": 2.5465960322516025e-08, + "loss": 0.7394, + "step": 15930 + }, + { + "epoch": 0.9779919580097609, + "grad_norm": 1.0082335167836243, + "learning_rate": 2.532434609719081e-08, + "loss": 0.7071, + "step": 15931 + }, + { + "epoch": 0.9780533472482273, + "grad_norm": 1.0708878855242296, + "learning_rate": 2.5183126224143094e-08, + "loss": 0.7414, + "step": 15932 + }, + { + "epoch": 0.9781147364866939, + "grad_norm": 0.9858511841955694, + "learning_rate": 2.5042300708955082e-08, + "loss": 0.6515, + "step": 15933 + }, + { + "epoch": 0.9781761257251603, + "grad_norm": 1.0550025149457753, + "learning_rate": 2.4901869557194537e-08, + "loss": 0.6823, + "step": 15934 + }, + { + "epoch": 0.9782375149636269, + "grad_norm": 0.9539473063525408, + "learning_rate": 2.4761832774414794e-08, + "loss": 0.7481, + "step": 15935 + }, + { + "epoch": 0.9782989042020934, + "grad_norm": 1.1397318382508628, + "learning_rate": 2.462219036615032e-08, + "loss": 0.7353, + "step": 15936 + }, + { + "epoch": 0.9783602934405599, + "grad_norm": 0.9472051829960706, + "learning_rate": 2.4482942337922255e-08, + "loss": 0.6898, + "step": 15937 + }, + { + "epoch": 0.9784216826790264, + "grad_norm": 1.0808187645304506, + "learning_rate": 2.43440886952373e-08, + "loss": 0.719, + "step": 15938 + }, + { + "epoch": 0.9784830719174928, + "grad_norm": 1.097790002670561, + "learning_rate": 2.420562944358329e-08, + "loss": 0.6632, + "step": 15939 + }, + { + "epoch": 0.9785444611559594, + "grad_norm": 1.0731127618810465, + "learning_rate": 2.4067564588435844e-08, + "loss": 0.7162, + "step": 15940 + }, + { + "epoch": 0.9786058503944258, + "grad_norm": 1.1914054147762267, + "learning_rate": 2.392989413525171e-08, + "loss": 0.796, + "step": 15941 + }, + { + "epoch": 0.9786672396328924, + "grad_norm": 1.1135102570024422, + "learning_rate": 2.3792618089475416e-08, + "loss": 0.7579, + "step": 15942 + }, + { + "epoch": 0.9787286288713588, + "grad_norm": 1.1421326824277467, + "learning_rate": 2.365573645653263e-08, + "loss": 0.7311, + "step": 15943 + }, + { + "epoch": 0.9787900181098254, + "grad_norm": 1.0215052198814722, + "learning_rate": 2.3519249241836794e-08, + "loss": 0.7315, + "step": 15944 + }, + { + "epoch": 0.9788514073482918, + "grad_norm": 1.2219653834321835, + "learning_rate": 2.3383156450782486e-08, + "loss": 0.7067, + "step": 15945 + }, + { + "epoch": 0.9789127965867583, + "grad_norm": 1.0868285837289828, + "learning_rate": 2.3247458088749842e-08, + "loss": 0.7386, + "step": 15946 + }, + { + "epoch": 0.9789741858252249, + "grad_norm": 1.0267435571103545, + "learning_rate": 2.311215416110568e-08, + "loss": 0.7027, + "step": 15947 + }, + { + "epoch": 0.9790355750636913, + "grad_norm": 1.038924447659107, + "learning_rate": 2.297724467319795e-08, + "loss": 0.8068, + "step": 15948 + }, + { + "epoch": 0.9790969643021579, + "grad_norm": 1.0154184782216322, + "learning_rate": 2.2842729630361272e-08, + "loss": 0.7083, + "step": 15949 + }, + { + "epoch": 0.9791583535406243, + "grad_norm": 0.980167563201097, + "learning_rate": 2.27086090379125e-08, + "loss": 0.6898, + "step": 15950 + }, + { + "epoch": 0.9792197427790909, + "grad_norm": 1.08023420905896, + "learning_rate": 2.2574882901154062e-08, + "loss": 0.7479, + "step": 15951 + }, + { + "epoch": 0.9792811320175573, + "grad_norm": 1.0538098826022315, + "learning_rate": 2.2441551225375058e-08, + "loss": 0.6732, + "step": 15952 + }, + { + "epoch": 0.9793425212560238, + "grad_norm": 1.0927540854470281, + "learning_rate": 2.23086140158435e-08, + "loss": 0.6996, + "step": 15953 + }, + { + "epoch": 0.9794039104944903, + "grad_norm": 1.1453105562670025, + "learning_rate": 2.2176071277817402e-08, + "loss": 0.7671, + "step": 15954 + }, + { + "epoch": 0.9794652997329568, + "grad_norm": 1.0454760008669566, + "learning_rate": 2.2043923016537015e-08, + "loss": 0.752, + "step": 15955 + }, + { + "epoch": 0.9795266889714234, + "grad_norm": 1.0040982914800476, + "learning_rate": 2.1912169237225946e-08, + "loss": 0.6495, + "step": 15956 + }, + { + "epoch": 0.9795880782098898, + "grad_norm": 1.1320075744313507, + "learning_rate": 2.178080994509335e-08, + "loss": 0.7462, + "step": 15957 + }, + { + "epoch": 0.9796494674483563, + "grad_norm": 1.0271687977399748, + "learning_rate": 2.164984514533286e-08, + "loss": 0.7295, + "step": 15958 + }, + { + "epoch": 0.9797108566868228, + "grad_norm": 0.9638933866372628, + "learning_rate": 2.1519274843121442e-08, + "loss": 0.6984, + "step": 15959 + }, + { + "epoch": 0.9797722459252893, + "grad_norm": 0.997361401721869, + "learning_rate": 2.138909904362163e-08, + "loss": 0.7247, + "step": 15960 + }, + { + "epoch": 0.9798336351637558, + "grad_norm": 1.114492884140878, + "learning_rate": 2.1259317751980422e-08, + "loss": 0.7209, + "step": 15961 + }, + { + "epoch": 0.9798950244022223, + "grad_norm": 1.011370078175868, + "learning_rate": 2.112993097332927e-08, + "loss": 0.7552, + "step": 15962 + }, + { + "epoch": 0.9799564136406888, + "grad_norm": 1.0090463070763143, + "learning_rate": 2.100093871278186e-08, + "loss": 0.7005, + "step": 15963 + }, + { + "epoch": 0.9800178028791553, + "grad_norm": 1.0533436449088232, + "learning_rate": 2.0872340975438555e-08, + "loss": 0.7241, + "step": 15964 + }, + { + "epoch": 0.9800791921176217, + "grad_norm": 1.0746070403582872, + "learning_rate": 2.0744137766384175e-08, + "loss": 0.7628, + "step": 15965 + }, + { + "epoch": 0.9801405813560883, + "grad_norm": 1.055833642285508, + "learning_rate": 2.0616329090685782e-08, + "loss": 0.7122, + "step": 15966 + }, + { + "epoch": 0.9802019705945548, + "grad_norm": 1.0632454664112596, + "learning_rate": 2.048891495339933e-08, + "loss": 0.7152, + "step": 15967 + }, + { + "epoch": 0.9802633598330213, + "grad_norm": 1.2360689669173992, + "learning_rate": 2.036189535955857e-08, + "loss": 0.7404, + "step": 15968 + }, + { + "epoch": 0.9803247490714878, + "grad_norm": 0.8789514596979328, + "learning_rate": 2.023527031418726e-08, + "loss": 0.7074, + "step": 15969 + }, + { + "epoch": 0.9803861383099542, + "grad_norm": 0.9794090296494032, + "learning_rate": 2.010903982229251e-08, + "loss": 0.7235, + "step": 15970 + }, + { + "epoch": 0.9804475275484208, + "grad_norm": 1.2085666423933623, + "learning_rate": 1.9983203888862547e-08, + "loss": 0.7177, + "step": 15971 + }, + { + "epoch": 0.9805089167868872, + "grad_norm": 1.1151568523544788, + "learning_rate": 1.985776251887339e-08, + "loss": 0.7191, + "step": 15972 + }, + { + "epoch": 0.9805703060253538, + "grad_norm": 1.0358151000536036, + "learning_rate": 1.973271571728441e-08, + "loss": 0.7034, + "step": 15973 + }, + { + "epoch": 0.9806316952638202, + "grad_norm": 1.0767069376504992, + "learning_rate": 1.960806348903943e-08, + "loss": 0.7171, + "step": 15974 + }, + { + "epoch": 0.9806930845022868, + "grad_norm": 0.5940778512551198, + "learning_rate": 1.9483805839066726e-08, + "loss": 0.6438, + "step": 15975 + }, + { + "epoch": 0.9807544737407532, + "grad_norm": 1.2586067192300059, + "learning_rate": 1.9359942772279038e-08, + "loss": 0.745, + "step": 15976 + }, + { + "epoch": 0.9808158629792197, + "grad_norm": 1.117479628116604, + "learning_rate": 1.9236474293572448e-08, + "loss": 0.708, + "step": 15977 + }, + { + "epoch": 0.9808772522176863, + "grad_norm": 1.1161185089730945, + "learning_rate": 1.911340040782972e-08, + "loss": 0.7547, + "step": 15978 + }, + { + "epoch": 0.9809386414561527, + "grad_norm": 1.0230535993766543, + "learning_rate": 1.8990721119914734e-08, + "loss": 0.7064, + "step": 15979 + }, + { + "epoch": 0.9810000306946193, + "grad_norm": 1.1718003869429423, + "learning_rate": 1.886843643467917e-08, + "loss": 0.7236, + "step": 15980 + }, + { + "epoch": 0.9810614199330857, + "grad_norm": 1.072474614910985, + "learning_rate": 1.874654635695805e-08, + "loss": 0.7203, + "step": 15981 + }, + { + "epoch": 0.9811228091715523, + "grad_norm": 1.099307057992944, + "learning_rate": 1.8625050891568632e-08, + "loss": 0.7191, + "step": 15982 + }, + { + "epoch": 0.9811841984100187, + "grad_norm": 0.9684645219950646, + "learning_rate": 1.8503950043314845e-08, + "loss": 0.7587, + "step": 15983 + }, + { + "epoch": 0.9812455876484852, + "grad_norm": 1.139298677110735, + "learning_rate": 1.8383243816985087e-08, + "loss": 0.7973, + "step": 15984 + }, + { + "epoch": 0.9813069768869517, + "grad_norm": 1.1867484136537025, + "learning_rate": 1.8262932217351094e-08, + "loss": 0.7597, + "step": 15985 + }, + { + "epoch": 0.9813683661254182, + "grad_norm": 1.0768672664046346, + "learning_rate": 1.814301524916906e-08, + "loss": 0.7575, + "step": 15986 + }, + { + "epoch": 0.9814297553638847, + "grad_norm": 0.978261719810162, + "learning_rate": 1.8023492917180752e-08, + "loss": 0.6942, + "step": 15987 + }, + { + "epoch": 0.9814911446023512, + "grad_norm": 1.0161603613699244, + "learning_rate": 1.7904365226111276e-08, + "loss": 0.6928, + "step": 15988 + }, + { + "epoch": 0.9815525338408178, + "grad_norm": 1.1889455634052795, + "learning_rate": 1.77856321806702e-08, + "loss": 0.7348, + "step": 15989 + }, + { + "epoch": 0.9816139230792842, + "grad_norm": 1.0453949905613702, + "learning_rate": 1.7667293785551543e-08, + "loss": 0.7414, + "step": 15990 + }, + { + "epoch": 0.9816753123177507, + "grad_norm": 1.1533494972697687, + "learning_rate": 1.7549350045433788e-08, + "loss": 0.7543, + "step": 15991 + }, + { + "epoch": 0.9817367015562172, + "grad_norm": 0.9958261876094904, + "learning_rate": 1.7431800964980984e-08, + "loss": 0.745, + "step": 15992 + }, + { + "epoch": 0.9817980907946837, + "grad_norm": 1.0205164909235025, + "learning_rate": 1.73146465488383e-08, + "loss": 0.6601, + "step": 15993 + }, + { + "epoch": 0.9818594800331502, + "grad_norm": 1.0189352912441139, + "learning_rate": 1.7197886801639806e-08, + "loss": 0.7438, + "step": 15994 + }, + { + "epoch": 0.9819208692716167, + "grad_norm": 1.1382642362369686, + "learning_rate": 1.7081521728000704e-08, + "loss": 0.7508, + "step": 15995 + }, + { + "epoch": 0.9819822585100831, + "grad_norm": 0.9896719411495439, + "learning_rate": 1.6965551332520648e-08, + "loss": 0.7512, + "step": 15996 + }, + { + "epoch": 0.9820436477485497, + "grad_norm": 1.0353297202019816, + "learning_rate": 1.6849975619785963e-08, + "loss": 0.7166, + "step": 15997 + }, + { + "epoch": 0.9821050369870161, + "grad_norm": 1.104011415789741, + "learning_rate": 1.6734794594365224e-08, + "loss": 0.7084, + "step": 15998 + }, + { + "epoch": 0.9821664262254827, + "grad_norm": 1.0839566840787316, + "learning_rate": 1.662000826081256e-08, + "loss": 0.7112, + "step": 15999 + }, + { + "epoch": 0.9822278154639492, + "grad_norm": 1.0458119038090448, + "learning_rate": 1.6505616623665455e-08, + "loss": 0.7387, + "step": 16000 + }, + { + "epoch": 0.9822892047024157, + "grad_norm": 0.9886136812387191, + "learning_rate": 1.6391619687446957e-08, + "loss": 0.7282, + "step": 16001 + }, + { + "epoch": 0.9823505939408822, + "grad_norm": 0.9599719897616166, + "learning_rate": 1.6278017456663464e-08, + "loss": 0.6858, + "step": 16002 + }, + { + "epoch": 0.9824119831793486, + "grad_norm": 1.038514211429929, + "learning_rate": 1.6164809935806935e-08, + "loss": 0.7284, + "step": 16003 + }, + { + "epoch": 0.9824733724178152, + "grad_norm": 1.0806420551141918, + "learning_rate": 1.605199712935268e-08, + "loss": 0.7103, + "step": 16004 + }, + { + "epoch": 0.9825347616562816, + "grad_norm": 1.0914119113356224, + "learning_rate": 1.5939579041761577e-08, + "loss": 0.7066, + "step": 16005 + }, + { + "epoch": 0.9825961508947482, + "grad_norm": 1.0513780159145056, + "learning_rate": 1.5827555677476736e-08, + "loss": 0.6919, + "step": 16006 + }, + { + "epoch": 0.9826575401332146, + "grad_norm": 1.0354146782959066, + "learning_rate": 1.5715927040927947e-08, + "loss": 0.686, + "step": 16007 + }, + { + "epoch": 0.9827189293716811, + "grad_norm": 1.1602582448066792, + "learning_rate": 1.5604693136528348e-08, + "loss": 0.7819, + "step": 16008 + }, + { + "epoch": 0.9827803186101477, + "grad_norm": 1.0704100830494954, + "learning_rate": 1.5493853968675533e-08, + "loss": 0.7956, + "step": 16009 + }, + { + "epoch": 0.9828417078486141, + "grad_norm": 1.002061474986515, + "learning_rate": 1.538340954175044e-08, + "loss": 0.7373, + "step": 16010 + }, + { + "epoch": 0.9829030970870807, + "grad_norm": 0.9649147195920073, + "learning_rate": 1.5273359860121796e-08, + "loss": 0.7251, + "step": 16011 + }, + { + "epoch": 0.9829644863255471, + "grad_norm": 1.0696129593464339, + "learning_rate": 1.5163704928139456e-08, + "loss": 0.7319, + "step": 16012 + }, + { + "epoch": 0.9830258755640137, + "grad_norm": 0.9866704523102083, + "learning_rate": 1.505444475013773e-08, + "loss": 0.7009, + "step": 16013 + }, + { + "epoch": 0.9830872648024801, + "grad_norm": 1.1400175986282228, + "learning_rate": 1.494557933043761e-08, + "loss": 0.7979, + "step": 16014 + }, + { + "epoch": 0.9831486540409466, + "grad_norm": 1.0772019414624017, + "learning_rate": 1.4837108673342315e-08, + "loss": 0.7512, + "step": 16015 + }, + { + "epoch": 0.9832100432794131, + "grad_norm": 1.0915064758684347, + "learning_rate": 1.472903278314175e-08, + "loss": 0.6735, + "step": 16016 + }, + { + "epoch": 0.9832714325178796, + "grad_norm": 1.0951410857749226, + "learning_rate": 1.4621351664105831e-08, + "loss": 0.6875, + "step": 16017 + }, + { + "epoch": 0.9833328217563461, + "grad_norm": 1.1139117413056463, + "learning_rate": 1.4514065320493376e-08, + "loss": 0.7361, + "step": 16018 + }, + { + "epoch": 0.9833942109948126, + "grad_norm": 1.0737567448708163, + "learning_rate": 1.4407173756547654e-08, + "loss": 0.7183, + "step": 16019 + }, + { + "epoch": 0.9834556002332792, + "grad_norm": 1.028242304476374, + "learning_rate": 1.4300676976491957e-08, + "loss": 0.7606, + "step": 16020 + }, + { + "epoch": 0.9835169894717456, + "grad_norm": 1.0868859263010642, + "learning_rate": 1.4194574984537357e-08, + "loss": 0.7194, + "step": 16021 + }, + { + "epoch": 0.9835783787102121, + "grad_norm": 0.975564172212722, + "learning_rate": 1.408886778487939e-08, + "loss": 0.7592, + "step": 16022 + }, + { + "epoch": 0.9836397679486786, + "grad_norm": 0.9535195009320856, + "learning_rate": 1.3983555381698044e-08, + "loss": 0.7328, + "step": 16023 + }, + { + "epoch": 0.9837011571871451, + "grad_norm": 1.0737751249926701, + "learning_rate": 1.3878637779154437e-08, + "loss": 0.7401, + "step": 16024 + }, + { + "epoch": 0.9837625464256116, + "grad_norm": 1.1270484857412522, + "learning_rate": 1.3774114981397469e-08, + "loss": 0.7469, + "step": 16025 + }, + { + "epoch": 0.9838239356640781, + "grad_norm": 1.1278481452521891, + "learning_rate": 1.3669986992561613e-08, + "loss": 0.7633, + "step": 16026 + }, + { + "epoch": 0.9838853249025445, + "grad_norm": 1.1058770283789956, + "learning_rate": 1.3566253816760245e-08, + "loss": 0.7414, + "step": 16027 + }, + { + "epoch": 0.9839467141410111, + "grad_norm": 1.0255895697450244, + "learning_rate": 1.3462915458096748e-08, + "loss": 0.7627, + "step": 16028 + }, + { + "epoch": 0.9840081033794775, + "grad_norm": 0.9650782154288567, + "learning_rate": 1.3359971920655634e-08, + "loss": 0.6544, + "step": 16029 + }, + { + "epoch": 0.9840694926179441, + "grad_norm": 0.9580731599087391, + "learning_rate": 1.325742320850698e-08, + "loss": 0.7581, + "step": 16030 + }, + { + "epoch": 0.9841308818564106, + "grad_norm": 1.0324206490230217, + "learning_rate": 1.3155269325706432e-08, + "loss": 0.717, + "step": 16031 + }, + { + "epoch": 0.9841922710948771, + "grad_norm": 1.1186772686617457, + "learning_rate": 1.3053510276289649e-08, + "loss": 0.7553, + "step": 16032 + }, + { + "epoch": 0.9842536603333436, + "grad_norm": 1.060494949955841, + "learning_rate": 1.29521460642823e-08, + "loss": 0.7679, + "step": 16033 + }, + { + "epoch": 0.98431504957181, + "grad_norm": 0.9694380638657009, + "learning_rate": 1.2851176693691182e-08, + "loss": 0.6944, + "step": 16034 + }, + { + "epoch": 0.9843764388102766, + "grad_norm": 0.8960562911052534, + "learning_rate": 1.2750602168508652e-08, + "loss": 0.7443, + "step": 16035 + }, + { + "epoch": 0.984437828048743, + "grad_norm": 0.5906623992402201, + "learning_rate": 1.2650422492710424e-08, + "loss": 0.6186, + "step": 16036 + }, + { + "epoch": 0.9844992172872096, + "grad_norm": 1.0776405882912177, + "learning_rate": 1.255063767025666e-08, + "loss": 0.7733, + "step": 16037 + }, + { + "epoch": 0.984560606525676, + "grad_norm": 1.121958687826892, + "learning_rate": 1.2451247705091985e-08, + "loss": 0.7441, + "step": 16038 + }, + { + "epoch": 0.9846219957641426, + "grad_norm": 1.0337919969973621, + "learning_rate": 1.2352252601147696e-08, + "loss": 0.7423, + "step": 16039 + }, + { + "epoch": 0.984683385002609, + "grad_norm": 1.0510021104941487, + "learning_rate": 1.2253652362336222e-08, + "loss": 0.7156, + "step": 16040 + }, + { + "epoch": 0.9847447742410755, + "grad_norm": 1.107568343740764, + "learning_rate": 1.2155446992556664e-08, + "loss": 0.7427, + "step": 16041 + }, + { + "epoch": 0.9848061634795421, + "grad_norm": 1.0792914578887585, + "learning_rate": 1.2057636495690362e-08, + "loss": 0.7225, + "step": 16042 + }, + { + "epoch": 0.9848675527180085, + "grad_norm": 1.0238119920449757, + "learning_rate": 1.1960220875604222e-08, + "loss": 0.7078, + "step": 16043 + }, + { + "epoch": 0.9849289419564751, + "grad_norm": 0.942495358795749, + "learning_rate": 1.186320013615183e-08, + "loss": 0.7178, + "step": 16044 + }, + { + "epoch": 0.9849903311949415, + "grad_norm": 0.9018541844272563, + "learning_rate": 1.1766574281166787e-08, + "loss": 0.707, + "step": 16045 + }, + { + "epoch": 0.985051720433408, + "grad_norm": 0.9019112881566739, + "learning_rate": 1.1670343314469367e-08, + "loss": 0.7224, + "step": 16046 + }, + { + "epoch": 0.9851131096718745, + "grad_norm": 0.9917053121478752, + "learning_rate": 1.1574507239865418e-08, + "loss": 0.6742, + "step": 16047 + }, + { + "epoch": 0.985174498910341, + "grad_norm": 1.1525088732194744, + "learning_rate": 1.1479066061143018e-08, + "loss": 0.7225, + "step": 16048 + }, + { + "epoch": 0.9852358881488075, + "grad_norm": 1.0220209459976097, + "learning_rate": 1.1384019782075818e-08, + "loss": 0.7172, + "step": 16049 + }, + { + "epoch": 0.985297277387274, + "grad_norm": 0.9517045254960216, + "learning_rate": 1.1289368406419698e-08, + "loss": 0.725, + "step": 16050 + }, + { + "epoch": 0.9853586666257405, + "grad_norm": 1.0450561032073868, + "learning_rate": 1.1195111937919444e-08, + "loss": 0.7233, + "step": 16051 + }, + { + "epoch": 0.985420055864207, + "grad_norm": 1.212020117268933, + "learning_rate": 1.1101250380300965e-08, + "loss": 0.7121, + "step": 16052 + }, + { + "epoch": 0.9854814451026735, + "grad_norm": 1.1482475065776103, + "learning_rate": 1.1007783737272403e-08, + "loss": 0.76, + "step": 16053 + }, + { + "epoch": 0.98554283434114, + "grad_norm": 1.1506456664725424, + "learning_rate": 1.0914712012533023e-08, + "loss": 0.7395, + "step": 16054 + }, + { + "epoch": 0.9856042235796065, + "grad_norm": 1.0774124023536071, + "learning_rate": 1.0822035209758775e-08, + "loss": 0.7658, + "step": 16055 + }, + { + "epoch": 0.985665612818073, + "grad_norm": 1.1113581104836758, + "learning_rate": 1.072975333261672e-08, + "loss": 0.7128, + "step": 16056 + }, + { + "epoch": 0.9857270020565395, + "grad_norm": 0.9635518893697106, + "learning_rate": 1.0637866384752837e-08, + "loss": 0.732, + "step": 16057 + }, + { + "epoch": 0.985788391295006, + "grad_norm": 0.9416650065806825, + "learning_rate": 1.0546374369801992e-08, + "loss": 0.7109, + "step": 16058 + }, + { + "epoch": 0.9858497805334725, + "grad_norm": 1.0169520156214409, + "learning_rate": 1.0455277291380183e-08, + "loss": 0.6736, + "step": 16059 + }, + { + "epoch": 0.9859111697719389, + "grad_norm": 0.9882869248224679, + "learning_rate": 1.0364575153087863e-08, + "loss": 0.7404, + "step": 16060 + }, + { + "epoch": 0.9859725590104055, + "grad_norm": 1.189143649826372, + "learning_rate": 1.0274267958513273e-08, + "loss": 0.7546, + "step": 16061 + }, + { + "epoch": 0.986033948248872, + "grad_norm": 1.0153929512052466, + "learning_rate": 1.018435571122578e-08, + "loss": 0.7348, + "step": 16062 + }, + { + "epoch": 0.9860953374873385, + "grad_norm": 1.068873493206477, + "learning_rate": 1.0094838414780316e-08, + "loss": 0.7293, + "step": 16063 + }, + { + "epoch": 0.986156726725805, + "grad_norm": 1.064367570002799, + "learning_rate": 1.0005716072714055e-08, + "loss": 0.7449, + "step": 16064 + }, + { + "epoch": 0.9862181159642714, + "grad_norm": 1.1962949989114409, + "learning_rate": 9.916988688553065e-09, + "loss": 0.7708, + "step": 16065 + }, + { + "epoch": 0.986279505202738, + "grad_norm": 1.047402089750412, + "learning_rate": 9.828656265804537e-09, + "loss": 0.7326, + "step": 16066 + }, + { + "epoch": 0.9863408944412044, + "grad_norm": 1.1020640835603748, + "learning_rate": 9.740718807960125e-09, + "loss": 0.7695, + "step": 16067 + }, + { + "epoch": 0.986402283679671, + "grad_norm": 0.9663568914499429, + "learning_rate": 9.653176318497048e-09, + "loss": 0.7235, + "step": 16068 + }, + { + "epoch": 0.9864636729181374, + "grad_norm": 1.1323359635679753, + "learning_rate": 9.56602880087587e-09, + "loss": 0.7675, + "step": 16069 + }, + { + "epoch": 0.986525062156604, + "grad_norm": 0.9848240394604864, + "learning_rate": 9.479276258541614e-09, + "loss": 0.7169, + "step": 16070 + }, + { + "epoch": 0.9865864513950704, + "grad_norm": 1.0206680501747847, + "learning_rate": 9.392918694924869e-09, + "loss": 0.7228, + "step": 16071 + }, + { + "epoch": 0.9866478406335369, + "grad_norm": 1.0317723368015377, + "learning_rate": 9.30695611344068e-09, + "loss": 0.7051, + "step": 16072 + }, + { + "epoch": 0.9867092298720035, + "grad_norm": 0.9800910155798642, + "learning_rate": 9.221388517485218e-09, + "loss": 0.7534, + "step": 16073 + }, + { + "epoch": 0.9867706191104699, + "grad_norm": 1.0864117278899488, + "learning_rate": 9.136215910442448e-09, + "loss": 0.7388, + "step": 16074 + }, + { + "epoch": 0.9868320083489365, + "grad_norm": 1.006171584853988, + "learning_rate": 9.05143829568078e-09, + "loss": 0.775, + "step": 16075 + }, + { + "epoch": 0.9868933975874029, + "grad_norm": 1.050175734201429, + "learning_rate": 8.967055676550874e-09, + "loss": 0.7169, + "step": 16076 + }, + { + "epoch": 0.9869547868258695, + "grad_norm": 1.196006081967551, + "learning_rate": 8.883068056390053e-09, + "loss": 0.697, + "step": 16077 + }, + { + "epoch": 0.9870161760643359, + "grad_norm": 1.061620325178529, + "learning_rate": 8.79947543851567e-09, + "loss": 0.6831, + "step": 16078 + }, + { + "epoch": 0.9870775653028024, + "grad_norm": 1.1620001460016744, + "learning_rate": 8.716277826236186e-09, + "loss": 0.7505, + "step": 16079 + }, + { + "epoch": 0.9871389545412689, + "grad_norm": 1.0272773188741888, + "learning_rate": 8.633475222838972e-09, + "loss": 0.6923, + "step": 16080 + }, + { + "epoch": 0.9872003437797354, + "grad_norm": 1.0768652873884057, + "learning_rate": 8.551067631599186e-09, + "loss": 0.7707, + "step": 16081 + }, + { + "epoch": 0.9872617330182019, + "grad_norm": 0.8909110274208285, + "learning_rate": 8.469055055772002e-09, + "loss": 0.7113, + "step": 16082 + }, + { + "epoch": 0.9873231222566684, + "grad_norm": 1.0792602395885535, + "learning_rate": 8.387437498602602e-09, + "loss": 0.7106, + "step": 16083 + }, + { + "epoch": 0.987384511495135, + "grad_norm": 1.0723647732342199, + "learning_rate": 8.306214963316183e-09, + "loss": 0.7257, + "step": 16084 + }, + { + "epoch": 0.9874459007336014, + "grad_norm": 1.0162367654358573, + "learning_rate": 8.225387453124623e-09, + "loss": 0.7195, + "step": 16085 + }, + { + "epoch": 0.9875072899720679, + "grad_norm": 1.074301214133178, + "learning_rate": 8.144954971223141e-09, + "loss": 0.7317, + "step": 16086 + }, + { + "epoch": 0.9875686792105344, + "grad_norm": 1.0581634029649727, + "learning_rate": 8.064917520791416e-09, + "loss": 0.7371, + "step": 16087 + }, + { + "epoch": 0.9876300684490009, + "grad_norm": 1.0022821941313542, + "learning_rate": 7.985275104994694e-09, + "loss": 0.7019, + "step": 16088 + }, + { + "epoch": 0.9876914576874674, + "grad_norm": 1.0363571466973538, + "learning_rate": 7.906027726981568e-09, + "loss": 0.7605, + "step": 16089 + }, + { + "epoch": 0.9877528469259339, + "grad_norm": 0.9821607305577357, + "learning_rate": 7.827175389883979e-09, + "loss": 0.716, + "step": 16090 + }, + { + "epoch": 0.9878142361644003, + "grad_norm": 1.1190624947174685, + "learning_rate": 7.74871809682054e-09, + "loss": 0.7644, + "step": 16091 + }, + { + "epoch": 0.9878756254028669, + "grad_norm": 1.1524575199768514, + "learning_rate": 7.670655850892106e-09, + "loss": 0.8056, + "step": 16092 + }, + { + "epoch": 0.9879370146413333, + "grad_norm": 0.8976029128623594, + "learning_rate": 7.592988655185097e-09, + "loss": 0.703, + "step": 16093 + }, + { + "epoch": 0.9879984038797999, + "grad_norm": 1.0143552504907487, + "learning_rate": 7.515716512770388e-09, + "loss": 0.6691, + "step": 16094 + }, + { + "epoch": 0.9880597931182664, + "grad_norm": 1.1151217318323725, + "learning_rate": 7.438839426703315e-09, + "loss": 0.7095, + "step": 16095 + }, + { + "epoch": 0.9881211823567329, + "grad_norm": 1.0312882502485359, + "learning_rate": 7.362357400023668e-09, + "loss": 0.7396, + "step": 16096 + }, + { + "epoch": 0.9881825715951994, + "grad_norm": 1.14692841482414, + "learning_rate": 7.286270435753473e-09, + "loss": 0.7227, + "step": 16097 + }, + { + "epoch": 0.9882439608336658, + "grad_norm": 1.0612018514904407, + "learning_rate": 7.210578536901436e-09, + "loss": 0.6702, + "step": 16098 + }, + { + "epoch": 0.9883053500721324, + "grad_norm": 1.063944078510042, + "learning_rate": 7.135281706461828e-09, + "loss": 0.7234, + "step": 16099 + }, + { + "epoch": 0.9883667393105988, + "grad_norm": 1.0691646908532062, + "learning_rate": 7.060379947408935e-09, + "loss": 0.74, + "step": 16100 + }, + { + "epoch": 0.9884281285490654, + "grad_norm": 1.1194824997502038, + "learning_rate": 6.985873262705945e-09, + "loss": 0.7305, + "step": 16101 + }, + { + "epoch": 0.9884895177875318, + "grad_norm": 1.082396090702226, + "learning_rate": 6.9117616552971664e-09, + "loss": 0.7497, + "step": 16102 + }, + { + "epoch": 0.9885509070259983, + "grad_norm": 0.9247832997062743, + "learning_rate": 6.838045128113591e-09, + "loss": 0.7237, + "step": 16103 + }, + { + "epoch": 0.9886122962644648, + "grad_norm": 1.0671053040238478, + "learning_rate": 6.764723684068442e-09, + "loss": 0.7067, + "step": 16104 + }, + { + "epoch": 0.9886736855029313, + "grad_norm": 1.126648228044208, + "learning_rate": 6.691797326062732e-09, + "loss": 0.7594, + "step": 16105 + }, + { + "epoch": 0.9887350747413979, + "grad_norm": 1.1089797136139175, + "learning_rate": 6.619266056977491e-09, + "loss": 0.7464, + "step": 16106 + }, + { + "epoch": 0.9887964639798643, + "grad_norm": 1.0705401967925547, + "learning_rate": 6.547129879680425e-09, + "loss": 0.7014, + "step": 16107 + }, + { + "epoch": 0.9888578532183309, + "grad_norm": 1.0396259278337212, + "learning_rate": 6.475388797024807e-09, + "loss": 0.7027, + "step": 16108 + }, + { + "epoch": 0.9889192424567973, + "grad_norm": 1.0595569504204163, + "learning_rate": 6.404042811846145e-09, + "loss": 0.7495, + "step": 16109 + }, + { + "epoch": 0.9889806316952638, + "grad_norm": 1.1486217041215658, + "learning_rate": 6.333091926965518e-09, + "loss": 0.7396, + "step": 16110 + }, + { + "epoch": 0.9890420209337303, + "grad_norm": 1.0477659223208025, + "learning_rate": 6.262536145187348e-09, + "loss": 0.7423, + "step": 16111 + }, + { + "epoch": 0.9891034101721968, + "grad_norm": 0.9647353724666602, + "learning_rate": 6.192375469301626e-09, + "loss": 0.7364, + "step": 16112 + }, + { + "epoch": 0.9891647994106633, + "grad_norm": 1.0237698303909295, + "learning_rate": 6.122609902081689e-09, + "loss": 0.7221, + "step": 16113 + }, + { + "epoch": 0.9892261886491298, + "grad_norm": 1.0993278290501218, + "learning_rate": 6.05323944628533e-09, + "loss": 0.7366, + "step": 16114 + }, + { + "epoch": 0.9892875778875964, + "grad_norm": 0.9825357148718837, + "learning_rate": 5.9842641046570225e-09, + "loss": 0.7833, + "step": 16115 + }, + { + "epoch": 0.9893489671260628, + "grad_norm": 1.0695909429872912, + "learning_rate": 5.915683879921253e-09, + "loss": 0.7703, + "step": 16116 + }, + { + "epoch": 0.9894103563645293, + "grad_norm": 1.053264958663328, + "learning_rate": 5.847498774791405e-09, + "loss": 0.7282, + "step": 16117 + }, + { + "epoch": 0.9894717456029958, + "grad_norm": 1.1347937550947644, + "learning_rate": 5.779708791961991e-09, + "loss": 0.7788, + "step": 16118 + }, + { + "epoch": 0.9895331348414623, + "grad_norm": 1.057017238440396, + "learning_rate": 5.7123139341142e-09, + "loss": 0.6583, + "step": 16119 + }, + { + "epoch": 0.9895945240799288, + "grad_norm": 1.0309906300356375, + "learning_rate": 5.645314203911456e-09, + "loss": 0.7384, + "step": 16120 + }, + { + "epoch": 0.9896559133183953, + "grad_norm": 1.0165320356828422, + "learning_rate": 5.5787096040027526e-09, + "loss": 0.6824, + "step": 16121 + }, + { + "epoch": 0.9897173025568617, + "grad_norm": 1.0196821346994607, + "learning_rate": 5.512500137022647e-09, + "loss": 0.7416, + "step": 16122 + }, + { + "epoch": 0.9897786917953283, + "grad_norm": 1.1403400263953314, + "learning_rate": 5.4466858055868265e-09, + "loss": 0.737, + "step": 16123 + }, + { + "epoch": 0.9898400810337947, + "grad_norm": 1.056643555385394, + "learning_rate": 5.381266612297653e-09, + "loss": 0.7441, + "step": 16124 + }, + { + "epoch": 0.9899014702722613, + "grad_norm": 1.0809970593319083, + "learning_rate": 5.316242559743057e-09, + "loss": 0.6949, + "step": 16125 + }, + { + "epoch": 0.9899628595107278, + "grad_norm": 1.036606983798109, + "learning_rate": 5.251613650492094e-09, + "loss": 0.6947, + "step": 16126 + }, + { + "epoch": 0.9900242487491943, + "grad_norm": 0.9962648293068742, + "learning_rate": 5.187379887100496e-09, + "loss": 0.7194, + "step": 16127 + }, + { + "epoch": 0.9900856379876608, + "grad_norm": 0.9663611607070451, + "learning_rate": 5.123541272108457e-09, + "loss": 0.7184, + "step": 16128 + }, + { + "epoch": 0.9901470272261272, + "grad_norm": 1.1234296475413164, + "learning_rate": 5.0600978080384e-09, + "loss": 0.6944, + "step": 16129 + }, + { + "epoch": 0.9902084164645938, + "grad_norm": 1.0683724186321761, + "learning_rate": 4.997049497399431e-09, + "loss": 0.7417, + "step": 16130 + }, + { + "epoch": 0.9902698057030602, + "grad_norm": 0.9848768703901845, + "learning_rate": 4.9343963426840006e-09, + "loss": 0.7102, + "step": 16131 + }, + { + "epoch": 0.9903311949415268, + "grad_norm": 1.0082695108698818, + "learning_rate": 4.8721383463701255e-09, + "loss": 0.7112, + "step": 16132 + }, + { + "epoch": 0.9903925841799932, + "grad_norm": 0.9598491405833987, + "learning_rate": 4.810275510918061e-09, + "loss": 0.7237, + "step": 16133 + }, + { + "epoch": 0.9904539734184598, + "grad_norm": 1.1464646867648436, + "learning_rate": 4.748807838773628e-09, + "loss": 0.7371, + "step": 16134 + }, + { + "epoch": 0.9905153626569262, + "grad_norm": 1.0295231773121831, + "learning_rate": 4.6877353323671046e-09, + "loss": 0.7306, + "step": 16135 + }, + { + "epoch": 0.9905767518953927, + "grad_norm": 1.1109541433111605, + "learning_rate": 4.627057994113226e-09, + "loss": 0.7694, + "step": 16136 + }, + { + "epoch": 0.9906381411338593, + "grad_norm": 1.0425525910139275, + "learning_rate": 4.566775826410075e-09, + "loss": 0.7291, + "step": 16137 + }, + { + "epoch": 0.9906995303723257, + "grad_norm": 1.1145980306207743, + "learning_rate": 4.506888831642408e-09, + "loss": 0.7465, + "step": 16138 + }, + { + "epoch": 0.9907609196107923, + "grad_norm": 1.0117303760778913, + "learning_rate": 4.447397012177224e-09, + "loss": 0.6828, + "step": 16139 + }, + { + "epoch": 0.9908223088492587, + "grad_norm": 1.0670157174051185, + "learning_rate": 4.3883003703659724e-09, + "loss": 0.7174, + "step": 16140 + }, + { + "epoch": 0.9908836980877253, + "grad_norm": 1.0396110302211288, + "learning_rate": 4.329598908544563e-09, + "loss": 0.7367, + "step": 16141 + }, + { + "epoch": 0.9909450873261917, + "grad_norm": 1.118154955129449, + "learning_rate": 4.2712926290355835e-09, + "loss": 0.7756, + "step": 16142 + }, + { + "epoch": 0.9910064765646582, + "grad_norm": 1.088079140802586, + "learning_rate": 4.213381534143857e-09, + "loss": 0.7076, + "step": 16143 + }, + { + "epoch": 0.9910678658031247, + "grad_norm": 1.1620960341026751, + "learning_rate": 4.1558656261586616e-09, + "loss": 0.7015, + "step": 16144 + }, + { + "epoch": 0.9911292550415912, + "grad_norm": 1.0742855533539153, + "learning_rate": 4.0987449073526254e-09, + "loss": 0.774, + "step": 16145 + }, + { + "epoch": 0.9911906442800577, + "grad_norm": 1.1141884933308492, + "learning_rate": 4.042019379985052e-09, + "loss": 0.7367, + "step": 16146 + }, + { + "epoch": 0.9912520335185242, + "grad_norm": 0.8852417829580196, + "learning_rate": 3.985689046298591e-09, + "loss": 0.6935, + "step": 16147 + }, + { + "epoch": 0.9913134227569907, + "grad_norm": 0.9988295735392739, + "learning_rate": 3.929753908521461e-09, + "loss": 0.7497, + "step": 16148 + }, + { + "epoch": 0.9913748119954572, + "grad_norm": 1.0074769522569593, + "learning_rate": 3.874213968863005e-09, + "loss": 0.7049, + "step": 16149 + }, + { + "epoch": 0.9914362012339237, + "grad_norm": 1.1951635550125819, + "learning_rate": 3.819069229519245e-09, + "loss": 0.714, + "step": 16150 + }, + { + "epoch": 0.9914975904723902, + "grad_norm": 1.152194789245232, + "learning_rate": 3.7643196926717695e-09, + "loss": 0.7309, + "step": 16151 + }, + { + "epoch": 0.9915589797108567, + "grad_norm": 1.0339834157783796, + "learning_rate": 3.709965360484402e-09, + "loss": 0.753, + "step": 16152 + }, + { + "epoch": 0.9916203689493231, + "grad_norm": 1.1690547424969628, + "learning_rate": 3.656006235105425e-09, + "loss": 0.7478, + "step": 16153 + }, + { + "epoch": 0.9916817581877897, + "grad_norm": 1.069787040373229, + "learning_rate": 3.6024423186697966e-09, + "loss": 0.718, + "step": 16154 + }, + { + "epoch": 0.9917431474262561, + "grad_norm": 1.062517266231648, + "learning_rate": 3.5492736132936023e-09, + "loss": 0.7, + "step": 16155 + }, + { + "epoch": 0.9918045366647227, + "grad_norm": 1.0814000644809352, + "learning_rate": 3.4965001210796045e-09, + "loss": 0.7489, + "step": 16156 + }, + { + "epoch": 0.9918659259031891, + "grad_norm": 1.0614562968462893, + "learning_rate": 3.444121844112802e-09, + "loss": 0.7035, + "step": 16157 + }, + { + "epoch": 0.9919273151416557, + "grad_norm": 1.03075090664827, + "learning_rate": 3.3921387844670915e-09, + "loss": 0.7366, + "step": 16158 + }, + { + "epoch": 0.9919887043801222, + "grad_norm": 1.1045333689288819, + "learning_rate": 3.340550944194165e-09, + "loss": 0.7585, + "step": 16159 + }, + { + "epoch": 0.9920500936185886, + "grad_norm": 0.6224374201219927, + "learning_rate": 3.289358325335723e-09, + "loss": 0.6697, + "step": 16160 + }, + { + "epoch": 0.9921114828570552, + "grad_norm": 1.1251219723215395, + "learning_rate": 3.238560929915702e-09, + "loss": 0.7078, + "step": 16161 + }, + { + "epoch": 0.9921728720955216, + "grad_norm": 1.1563437361677096, + "learning_rate": 3.1881587599413845e-09, + "loss": 0.7724, + "step": 16162 + }, + { + "epoch": 0.9922342613339882, + "grad_norm": 1.0285622840530242, + "learning_rate": 3.1381518174056214e-09, + "loss": 0.7495, + "step": 16163 + }, + { + "epoch": 0.9922956505724546, + "grad_norm": 1.1027881088692568, + "learning_rate": 3.0885401042857197e-09, + "loss": 0.7103, + "step": 16164 + }, + { + "epoch": 0.9923570398109212, + "grad_norm": 1.1291767926028373, + "learning_rate": 3.039323622543444e-09, + "loss": 0.7238, + "step": 16165 + }, + { + "epoch": 0.9924184290493876, + "grad_norm": 0.9287432483990581, + "learning_rate": 2.9905023741239048e-09, + "loss": 0.7147, + "step": 16166 + }, + { + "epoch": 0.9924798182878541, + "grad_norm": 1.086336694356532, + "learning_rate": 2.9420763609577798e-09, + "loss": 0.7374, + "step": 16167 + }, + { + "epoch": 0.9925412075263207, + "grad_norm": 1.0144776014450825, + "learning_rate": 2.894045584959093e-09, + "loss": 0.7089, + "step": 16168 + }, + { + "epoch": 0.9926025967647871, + "grad_norm": 1.0032427304984133, + "learning_rate": 2.846410048027437e-09, + "loss": 0.745, + "step": 16169 + }, + { + "epoch": 0.9926639860032537, + "grad_norm": 0.9927098837652114, + "learning_rate": 2.7991697520446394e-09, + "loss": 0.6953, + "step": 16170 + }, + { + "epoch": 0.9927253752417201, + "grad_norm": 1.0745381697715823, + "learning_rate": 2.752324698880315e-09, + "loss": 0.7419, + "step": 16171 + }, + { + "epoch": 0.9927867644801867, + "grad_norm": 1.1029439401132564, + "learning_rate": 2.7058748903863173e-09, + "loss": 0.6994, + "step": 16172 + }, + { + "epoch": 0.9928481537186531, + "grad_norm": 1.0249199104827178, + "learning_rate": 2.6598203283978443e-09, + "loss": 0.7318, + "step": 16173 + }, + { + "epoch": 0.9929095429571196, + "grad_norm": 1.1649139817229315, + "learning_rate": 2.6141610147356613e-09, + "loss": 0.7539, + "step": 16174 + }, + { + "epoch": 0.9929709321955861, + "grad_norm": 1.0362454296777766, + "learning_rate": 2.5688969512061012e-09, + "loss": 0.7296, + "step": 16175 + }, + { + "epoch": 0.9930323214340526, + "grad_norm": 1.0010672378931593, + "learning_rate": 2.524028139597734e-09, + "loss": 0.7337, + "step": 16176 + }, + { + "epoch": 0.9930937106725191, + "grad_norm": 1.0608811916297713, + "learning_rate": 2.4795545816846955e-09, + "loss": 0.7148, + "step": 16177 + }, + { + "epoch": 0.9931550999109856, + "grad_norm": 0.904225914942143, + "learning_rate": 2.4354762792255794e-09, + "loss": 0.7062, + "step": 16178 + }, + { + "epoch": 0.9932164891494522, + "grad_norm": 0.9825079000568198, + "learning_rate": 2.391793233962325e-09, + "loss": 0.7234, + "step": 16179 + }, + { + "epoch": 0.9932778783879186, + "grad_norm": 1.1293400231453967, + "learning_rate": 2.34850544762355e-09, + "loss": 0.7012, + "step": 16180 + }, + { + "epoch": 0.9933392676263851, + "grad_norm": 1.1254915658748375, + "learning_rate": 2.3056129219189983e-09, + "loss": 0.6622, + "step": 16181 + }, + { + "epoch": 0.9934006568648516, + "grad_norm": 1.1635232286405632, + "learning_rate": 2.2631156585439794e-09, + "loss": 0.701, + "step": 16182 + }, + { + "epoch": 0.9934620461033181, + "grad_norm": 0.9111773968407939, + "learning_rate": 2.221013659181592e-09, + "loss": 0.7255, + "step": 16183 + }, + { + "epoch": 0.9935234353417846, + "grad_norm": 0.9482181825842272, + "learning_rate": 2.1793069254927302e-09, + "loss": 0.6842, + "step": 16184 + }, + { + "epoch": 0.9935848245802511, + "grad_norm": 1.137662594321333, + "learning_rate": 2.1379954591282946e-09, + "loss": 0.6915, + "step": 16185 + }, + { + "epoch": 0.9936462138187175, + "grad_norm": 0.9901103763671708, + "learning_rate": 2.0970792617225345e-09, + "loss": 0.6936, + "step": 16186 + }, + { + "epoch": 0.9937076030571841, + "grad_norm": 1.2966206383550731, + "learning_rate": 2.0565583348908236e-09, + "loss": 0.698, + "step": 16187 + }, + { + "epoch": 0.9937689922956505, + "grad_norm": 1.122263273830187, + "learning_rate": 2.016432680235214e-09, + "loss": 0.6901, + "step": 16188 + }, + { + "epoch": 0.9938303815341171, + "grad_norm": 0.8753672006650961, + "learning_rate": 1.9767022993444353e-09, + "loss": 0.7295, + "step": 16189 + }, + { + "epoch": 0.9938917707725836, + "grad_norm": 1.049762405369792, + "learning_rate": 1.937367193787232e-09, + "loss": 0.7179, + "step": 16190 + }, + { + "epoch": 0.99395316001105, + "grad_norm": 1.007376345237496, + "learning_rate": 1.8984273651190265e-09, + "loss": 0.6977, + "step": 16191 + }, + { + "epoch": 0.9940145492495166, + "grad_norm": 1.0280348657506997, + "learning_rate": 1.8598828148796988e-09, + "loss": 0.7275, + "step": 16192 + }, + { + "epoch": 0.994075938487983, + "grad_norm": 1.0180920744070228, + "learning_rate": 1.8217335445935847e-09, + "loss": 0.7478, + "step": 16193 + }, + { + "epoch": 0.9941373277264496, + "grad_norm": 1.0610641255211324, + "learning_rate": 1.783979555768367e-09, + "loss": 0.7889, + "step": 16194 + }, + { + "epoch": 0.994198716964916, + "grad_norm": 0.9521324507704644, + "learning_rate": 1.7466208498961857e-09, + "loss": 0.7251, + "step": 16195 + }, + { + "epoch": 0.9942601062033826, + "grad_norm": 1.11106825754502, + "learning_rate": 1.7096574284547474e-09, + "loss": 0.6977, + "step": 16196 + }, + { + "epoch": 0.994321495441849, + "grad_norm": 1.2187200052699638, + "learning_rate": 1.6730892929051057e-09, + "loss": 0.7467, + "step": 16197 + }, + { + "epoch": 0.9943828846803155, + "grad_norm": 1.3032747277507535, + "learning_rate": 1.636916444692771e-09, + "loss": 0.7372, + "step": 16198 + }, + { + "epoch": 0.994444273918782, + "grad_norm": 1.1409443811303406, + "learning_rate": 1.6011388852477106e-09, + "loss": 0.7342, + "step": 16199 + }, + { + "epoch": 0.9945056631572485, + "grad_norm": 1.101829969220092, + "learning_rate": 1.5657566159854586e-09, + "loss": 0.7566, + "step": 16200 + }, + { + "epoch": 0.9945670523957151, + "grad_norm": 1.0969317257256679, + "learning_rate": 1.5307696383048965e-09, + "loss": 0.7353, + "step": 16201 + }, + { + "epoch": 0.9946284416341815, + "grad_norm": 1.2382630103712442, + "learning_rate": 1.4961779535871412e-09, + "loss": 0.7449, + "step": 16202 + }, + { + "epoch": 0.9946898308726481, + "grad_norm": 1.0337892190641689, + "learning_rate": 1.4619815632022083e-09, + "loss": 0.7624, + "step": 16203 + }, + { + "epoch": 0.9947512201111145, + "grad_norm": 0.9402136468066186, + "learning_rate": 1.428180468501239e-09, + "loss": 0.7321, + "step": 16204 + }, + { + "epoch": 0.994812609349581, + "grad_norm": 1.1763134385706417, + "learning_rate": 1.3947746708198318e-09, + "loss": 0.761, + "step": 16205 + }, + { + "epoch": 0.9948739985880475, + "grad_norm": 1.0303495246270395, + "learning_rate": 1.3617641714791518e-09, + "loss": 0.7369, + "step": 16206 + }, + { + "epoch": 0.994935387826514, + "grad_norm": 0.9856717568490003, + "learning_rate": 1.3291489717848215e-09, + "loss": 0.717, + "step": 16207 + }, + { + "epoch": 0.9949967770649805, + "grad_norm": 1.1473861689941152, + "learning_rate": 1.29692907302581e-09, + "loss": 0.7207, + "step": 16208 + }, + { + "epoch": 0.995058166303447, + "grad_norm": 1.048074055156042, + "learning_rate": 1.265104476476653e-09, + "loss": 0.6858, + "step": 16209 + }, + { + "epoch": 0.9951195555419134, + "grad_norm": 1.1501758647475826, + "learning_rate": 1.233675183394123e-09, + "loss": 0.7375, + "step": 16210 + }, + { + "epoch": 0.99518094478038, + "grad_norm": 1.040313855870842, + "learning_rate": 1.2026411950216698e-09, + "loss": 0.6927, + "step": 16211 + }, + { + "epoch": 0.9952423340188465, + "grad_norm": 1.171725671927245, + "learning_rate": 1.1720025125860901e-09, + "loss": 0.7129, + "step": 16212 + }, + { + "epoch": 0.995303723257313, + "grad_norm": 1.0130718252042312, + "learning_rate": 1.1417591372986369e-09, + "loss": 0.751, + "step": 16213 + }, + { + "epoch": 0.9953651124957795, + "grad_norm": 1.1883473156452964, + "learning_rate": 1.111911070356131e-09, + "loss": 0.7839, + "step": 16214 + }, + { + "epoch": 0.995426501734246, + "grad_norm": 1.1490000983909006, + "learning_rate": 1.0824583129365184e-09, + "loss": 0.7485, + "step": 16215 + }, + { + "epoch": 0.9954878909727125, + "grad_norm": 0.9487610837314838, + "learning_rate": 1.053400866205534e-09, + "loss": 0.673, + "step": 16216 + }, + { + "epoch": 0.9955492802111789, + "grad_norm": 1.095115674652836, + "learning_rate": 1.024738731311148e-09, + "loss": 0.7324, + "step": 16217 + }, + { + "epoch": 0.9956106694496455, + "grad_norm": 1.035685589350173, + "learning_rate": 9.964719093880082e-10, + "loss": 0.7159, + "step": 16218 + }, + { + "epoch": 0.9956720586881119, + "grad_norm": 1.0581002158574586, + "learning_rate": 9.686004015529992e-10, + "loss": 0.6956, + "step": 16219 + }, + { + "epoch": 0.9957334479265785, + "grad_norm": 1.058945142862273, + "learning_rate": 9.411242089063521e-10, + "loss": 0.7019, + "step": 16220 + }, + { + "epoch": 0.995794837165045, + "grad_norm": 1.163215497820953, + "learning_rate": 9.140433325371956e-10, + "loss": 0.7687, + "step": 16221 + }, + { + "epoch": 0.9958562264035115, + "grad_norm": 0.9577597185339946, + "learning_rate": 8.873577735146743e-10, + "loss": 0.7439, + "step": 16222 + }, + { + "epoch": 0.995917615641978, + "grad_norm": 1.0274859570719876, + "learning_rate": 8.610675328935003e-10, + "loss": 0.7502, + "step": 16223 + }, + { + "epoch": 0.9959790048804444, + "grad_norm": 1.13923419691728, + "learning_rate": 8.351726117128422e-10, + "loss": 0.749, + "step": 16224 + }, + { + "epoch": 0.996040394118911, + "grad_norm": 1.1004761549068711, + "learning_rate": 8.096730109985462e-10, + "loss": 0.706, + "step": 16225 + }, + { + "epoch": 0.9961017833573774, + "grad_norm": 1.0190602926318257, + "learning_rate": 7.845687317564743e-10, + "loss": 0.6963, + "step": 16226 + }, + { + "epoch": 0.996163172595844, + "grad_norm": 1.0128699485423882, + "learning_rate": 7.598597749791658e-10, + "loss": 0.7394, + "step": 16227 + }, + { + "epoch": 0.9962245618343104, + "grad_norm": 1.0416660689600357, + "learning_rate": 7.355461416458376e-10, + "loss": 0.7, + "step": 16228 + }, + { + "epoch": 0.996285951072777, + "grad_norm": 1.0422616967891418, + "learning_rate": 7.116278327157223e-10, + "loss": 0.6684, + "step": 16229 + }, + { + "epoch": 0.9963473403112434, + "grad_norm": 1.0933591856568825, + "learning_rate": 6.881048491347297e-10, + "loss": 0.7147, + "step": 16230 + }, + { + "epoch": 0.9964087295497099, + "grad_norm": 0.9621244454410014, + "learning_rate": 6.649771918321169e-10, + "loss": 0.7374, + "step": 16231 + }, + { + "epoch": 0.9964701187881765, + "grad_norm": 1.0522962422164877, + "learning_rate": 6.422448617249277e-10, + "loss": 0.6857, + "step": 16232 + }, + { + "epoch": 0.9965315080266429, + "grad_norm": 1.0141767892383762, + "learning_rate": 6.199078597091124e-10, + "loss": 0.6935, + "step": 16233 + }, + { + "epoch": 0.9965928972651095, + "grad_norm": 0.9848987721234316, + "learning_rate": 5.979661866684083e-10, + "loss": 0.6968, + "step": 16234 + }, + { + "epoch": 0.9966542865035759, + "grad_norm": 0.992087783264446, + "learning_rate": 5.7641984347101e-10, + "loss": 0.7846, + "step": 16235 + }, + { + "epoch": 0.9967156757420425, + "grad_norm": 1.0110221325747926, + "learning_rate": 5.552688309684585e-10, + "loss": 0.7523, + "step": 16236 + }, + { + "epoch": 0.9967770649805089, + "grad_norm": 1.1515186637428843, + "learning_rate": 5.345131499978618e-10, + "loss": 0.7081, + "step": 16237 + }, + { + "epoch": 0.9968384542189754, + "grad_norm": 1.0510988887402117, + "learning_rate": 5.141528013774543e-10, + "loss": 0.7427, + "step": 16238 + }, + { + "epoch": 0.9968998434574419, + "grad_norm": 0.9669423660910372, + "learning_rate": 4.941877859143684e-10, + "loss": 0.6807, + "step": 16239 + }, + { + "epoch": 0.9969612326959084, + "grad_norm": 1.0756862246593213, + "learning_rate": 4.746181043968623e-10, + "loss": 0.7394, + "step": 16240 + }, + { + "epoch": 0.9970226219343749, + "grad_norm": 0.9817872669166602, + "learning_rate": 4.5544375759876135e-10, + "loss": 0.7822, + "step": 16241 + }, + { + "epoch": 0.9970840111728414, + "grad_norm": 1.0174830228338299, + "learning_rate": 4.366647462794582e-10, + "loss": 0.7224, + "step": 16242 + }, + { + "epoch": 0.997145400411308, + "grad_norm": 1.0815694697408873, + "learning_rate": 4.182810711794716e-10, + "loss": 0.7106, + "step": 16243 + }, + { + "epoch": 0.9972067896497744, + "grad_norm": 1.131886761644036, + "learning_rate": 4.002927330259976e-10, + "loss": 0.7226, + "step": 16244 + }, + { + "epoch": 0.9972681788882409, + "grad_norm": 1.1326577272285798, + "learning_rate": 3.8269973253068915e-10, + "loss": 0.734, + "step": 16245 + }, + { + "epoch": 0.9973295681267074, + "grad_norm": 1.108811965080069, + "learning_rate": 3.655020703885459e-10, + "loss": 0.7614, + "step": 16246 + }, + { + "epoch": 0.9973909573651739, + "grad_norm": 1.0730284999665933, + "learning_rate": 3.4869974728013457e-10, + "loss": 0.722, + "step": 16247 + }, + { + "epoch": 0.9974523466036403, + "grad_norm": 1.082158320933942, + "learning_rate": 3.3229276387047873e-10, + "loss": 0.7285, + "step": 16248 + }, + { + "epoch": 0.9975137358421069, + "grad_norm": 1.120553767007912, + "learning_rate": 3.1628112080683837e-10, + "loss": 0.7049, + "step": 16249 + }, + { + "epoch": 0.9975751250805733, + "grad_norm": 1.1472705862518078, + "learning_rate": 3.006648187220407e-10, + "loss": 0.7158, + "step": 16250 + }, + { + "epoch": 0.9976365143190399, + "grad_norm": 1.0522244361247168, + "learning_rate": 2.8544385823447984e-10, + "loss": 0.7586, + "step": 16251 + }, + { + "epoch": 0.9976979035575063, + "grad_norm": 1.1494832575259646, + "learning_rate": 2.7061823994589676e-10, + "loss": 0.7458, + "step": 16252 + }, + { + "epoch": 0.9977592927959729, + "grad_norm": 1.0951672067133387, + "learning_rate": 2.5618796444137893e-10, + "loss": 0.7177, + "step": 16253 + }, + { + "epoch": 0.9978206820344394, + "grad_norm": 1.0545484817786308, + "learning_rate": 2.4215303229269127e-10, + "loss": 0.763, + "step": 16254 + }, + { + "epoch": 0.9978820712729058, + "grad_norm": 1.0359360034623635, + "learning_rate": 2.2851344405383503e-10, + "loss": 0.6643, + "step": 16255 + }, + { + "epoch": 0.9979434605113724, + "grad_norm": 1.0803613025920804, + "learning_rate": 2.1526920026437858e-10, + "loss": 0.7154, + "step": 16256 + }, + { + "epoch": 0.9980048497498388, + "grad_norm": 0.9229693544773885, + "learning_rate": 2.0242030144834724e-10, + "loss": 0.7475, + "step": 16257 + }, + { + "epoch": 0.9980662389883054, + "grad_norm": 1.1017124131913105, + "learning_rate": 1.899667481131129e-10, + "loss": 0.7232, + "step": 16258 + }, + { + "epoch": 0.9981276282267718, + "grad_norm": 1.0649066737644752, + "learning_rate": 1.7790854075161456e-10, + "loss": 0.7005, + "step": 16259 + }, + { + "epoch": 0.9981890174652384, + "grad_norm": 1.18754935312642, + "learning_rate": 1.6624567983902774e-10, + "loss": 0.7558, + "step": 16260 + }, + { + "epoch": 0.9982504067037048, + "grad_norm": 1.0018095471208115, + "learning_rate": 1.5497816583831538e-10, + "loss": 0.696, + "step": 16261 + }, + { + "epoch": 0.9983117959421713, + "grad_norm": 1.0803047655415725, + "learning_rate": 1.4410599919467694e-10, + "loss": 0.7412, + "step": 16262 + }, + { + "epoch": 0.9983731851806378, + "grad_norm": 0.9906442776038121, + "learning_rate": 1.3362918033776873e-10, + "loss": 0.7057, + "step": 16263 + }, + { + "epoch": 0.9984345744191043, + "grad_norm": 1.1291106671404811, + "learning_rate": 1.235477096805937e-10, + "loss": 0.753, + "step": 16264 + }, + { + "epoch": 0.9984959636575709, + "grad_norm": 0.9542577212261647, + "learning_rate": 1.1386158762283217e-10, + "loss": 0.7674, + "step": 16265 + }, + { + "epoch": 0.9985573528960373, + "grad_norm": 1.120219696277068, + "learning_rate": 1.0457081454751105e-10, + "loss": 0.7644, + "step": 16266 + }, + { + "epoch": 0.9986187421345039, + "grad_norm": 1.020401632285532, + "learning_rate": 9.567539082211418e-11, + "loss": 0.7113, + "step": 16267 + }, + { + "epoch": 0.9986801313729703, + "grad_norm": 1.143014670174182, + "learning_rate": 8.717531679747205e-11, + "loss": 0.6914, + "step": 16268 + }, + { + "epoch": 0.9987415206114368, + "grad_norm": 1.2215384060208203, + "learning_rate": 7.90705928099822e-11, + "loss": 0.7265, + "step": 16269 + }, + { + "epoch": 0.9988029098499033, + "grad_norm": 1.0806215070266394, + "learning_rate": 7.136121917938887e-11, + "loss": 0.7215, + "step": 16270 + }, + { + "epoch": 0.9988642990883698, + "grad_norm": 1.0584894246101098, + "learning_rate": 6.404719621211364e-11, + "loss": 0.7259, + "step": 16271 + }, + { + "epoch": 0.9989256883268363, + "grad_norm": 0.9204732157121305, + "learning_rate": 5.712852419681447e-11, + "loss": 0.7051, + "step": 16272 + }, + { + "epoch": 0.9989870775653028, + "grad_norm": 1.087044274432493, + "learning_rate": 5.060520340660624e-11, + "loss": 0.744, + "step": 16273 + }, + { + "epoch": 0.9990484668037694, + "grad_norm": 1.0420512629098169, + "learning_rate": 4.4477234099060685e-11, + "loss": 0.7361, + "step": 16274 + }, + { + "epoch": 0.9991098560422358, + "grad_norm": 1.0037133435407752, + "learning_rate": 3.8744616517316644e-11, + "loss": 0.7068, + "step": 16275 + }, + { + "epoch": 0.9991712452807023, + "grad_norm": 1.0000590214340077, + "learning_rate": 3.3407350886749403e-11, + "loss": 0.7037, + "step": 16276 + }, + { + "epoch": 0.9992326345191688, + "grad_norm": 1.0868421090992122, + "learning_rate": 2.8465437419411547e-11, + "loss": 0.7167, + "step": 16277 + }, + { + "epoch": 0.9992940237576353, + "grad_norm": 1.0414620276147493, + "learning_rate": 2.391887631070233e-11, + "loss": 0.718, + "step": 16278 + }, + { + "epoch": 0.9993554129961018, + "grad_norm": 1.1387876363231835, + "learning_rate": 1.976766774047789e-11, + "loss": 0.8134, + "step": 16279 + }, + { + "epoch": 0.9994168022345683, + "grad_norm": 1.0876197054146806, + "learning_rate": 1.6011811871941007e-11, + "loss": 0.7292, + "step": 16280 + }, + { + "epoch": 0.9994781914730347, + "grad_norm": 1.0864729854901647, + "learning_rate": 1.2651308853861566e-11, + "loss": 0.6939, + "step": 16281 + }, + { + "epoch": 0.9995395807115013, + "grad_norm": 1.0351404071730943, + "learning_rate": 9.686158820576552e-12, + "loss": 0.7165, + "step": 16282 + }, + { + "epoch": 0.9996009699499677, + "grad_norm": 1.09621486249818, + "learning_rate": 7.1163618875491616e-12, + "loss": 0.6937, + "step": 16283 + }, + { + "epoch": 0.9996623591884343, + "grad_norm": 1.1488431955962843, + "learning_rate": 4.941918155809689e-12, + "loss": 0.7024, + "step": 16284 + }, + { + "epoch": 0.9997237484269008, + "grad_norm": 1.0994881914625476, + "learning_rate": 3.1628277141759754e-12, + "loss": 0.6928, + "step": 16285 + }, + { + "epoch": 0.9997851376653673, + "grad_norm": 1.1826173059315166, + "learning_rate": 1.779090630371627e-12, + "loss": 0.709, + "step": 16286 + }, + { + "epoch": 0.9998465269038338, + "grad_norm": 1.2107029395733446, + "learning_rate": 7.907069599077943e-13, + "loss": 0.7502, + "step": 16287 + }, + { + "epoch": 0.9999079161423002, + "grad_norm": 1.085388175871007, + "learning_rate": 1.9767674164228312e-13, + "loss": 0.7427, + "step": 16288 + }, + { + "epoch": 0.9999693053807668, + "grad_norm": 0.724888611985626, + "learning_rate": 0.0, + "loss": 0.6631, + "step": 16289 + }, + { + "epoch": 0.9999693053807668, + "step": 16289, + "total_flos": 2.9484990053482496e+16, + "train_loss": 0.8763824042031848, + "train_runtime": 165677.34, + "train_samples_per_second": 12.585, + "train_steps_per_second": 0.098 + } + ], + "logging_steps": 1.0, + "max_steps": 16289, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 50000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.9484990053482496e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +}