| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2783143881998358, | |
| "eval_steps": 500, | |
| "global_step": 116000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016529927433618567, | |
| "grad_norm": 2.137389659881592, | |
| "learning_rate": 0.0001599141895763845, | |
| "loss": 6.3906, | |
| "num_input_tokens_seen": 872064, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0033059854867237134, | |
| "grad_norm": 1.725138783454895, | |
| "learning_rate": 0.000159826028182259, | |
| "loss": 5.6466, | |
| "num_input_tokens_seen": 1744032, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00495897823008557, | |
| "grad_norm": 1.9830477237701416, | |
| "learning_rate": 0.00015973786678813348, | |
| "loss": 5.4449, | |
| "num_input_tokens_seen": 2615552, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.006611970973447427, | |
| "grad_norm": 1.8168050050735474, | |
| "learning_rate": 0.00015964970539400798, | |
| "loss": 5.3521, | |
| "num_input_tokens_seen": 3469792, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.008264963716809284, | |
| "grad_norm": 1.9247260093688965, | |
| "learning_rate": 0.00015956154399988245, | |
| "loss": 5.2863, | |
| "num_input_tokens_seen": 4342304, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.00991795646017114, | |
| "grad_norm": 1.9191653728485107, | |
| "learning_rate": 0.00015947338260575695, | |
| "loss": 5.2405, | |
| "num_input_tokens_seen": 5211616, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.011570949203532997, | |
| "grad_norm": 1.748758316040039, | |
| "learning_rate": 0.00015938522121163143, | |
| "loss": 5.1998, | |
| "num_input_tokens_seen": 6098432, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.013223941946894854, | |
| "grad_norm": 2.057206869125366, | |
| "learning_rate": 0.00015929705981750593, | |
| "loss": 5.1706, | |
| "num_input_tokens_seen": 6967904, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.014876934690256709, | |
| "grad_norm": 2.0983762741088867, | |
| "learning_rate": 0.0001592088984233804, | |
| "loss": 5.1521, | |
| "num_input_tokens_seen": 7851072, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.016529927433618568, | |
| "grad_norm": 1.9689010381698608, | |
| "learning_rate": 0.0001591207370292549, | |
| "loss": 5.1314, | |
| "num_input_tokens_seen": 8719744, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01818292017698042, | |
| "grad_norm": 1.7962827682495117, | |
| "learning_rate": 0.00015903257563512938, | |
| "loss": 5.0878, | |
| "num_input_tokens_seen": 9566912, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.01983591292034228, | |
| "grad_norm": 1.8615788221359253, | |
| "learning_rate": 0.00015894441424100389, | |
| "loss": 5.0739, | |
| "num_input_tokens_seen": 10450048, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.021488905663704136, | |
| "grad_norm": 1.8449132442474365, | |
| "learning_rate": 0.00015885625284687836, | |
| "loss": 5.0658, | |
| "num_input_tokens_seen": 11348640, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.023141898407065993, | |
| "grad_norm": 1.8516219854354858, | |
| "learning_rate": 0.00015876809145275284, | |
| "loss": 5.0462, | |
| "num_input_tokens_seen": 12226144, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.02479489115042785, | |
| "grad_norm": 1.9487632513046265, | |
| "learning_rate": 0.00015867993005862734, | |
| "loss": 5.0265, | |
| "num_input_tokens_seen": 13119040, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.026447883893789707, | |
| "grad_norm": 1.8343034982681274, | |
| "learning_rate": 0.0001585917686645018, | |
| "loss": 5.0056, | |
| "num_input_tokens_seen": 13993280, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.028100876637151564, | |
| "grad_norm": 2.002856731414795, | |
| "learning_rate": 0.00015850360727037632, | |
| "loss": 4.9993, | |
| "num_input_tokens_seen": 14876768, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.029753869380513418, | |
| "grad_norm": 1.981166124343872, | |
| "learning_rate": 0.0001584154458762508, | |
| "loss": 4.9943, | |
| "num_input_tokens_seen": 15749088, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.03140686212387528, | |
| "grad_norm": 1.9732400178909302, | |
| "learning_rate": 0.0001583272844821253, | |
| "loss": 4.9762, | |
| "num_input_tokens_seen": 16634176, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.033059854867237136, | |
| "grad_norm": 1.8369622230529785, | |
| "learning_rate": 0.00015823912308799977, | |
| "loss": 4.9525, | |
| "num_input_tokens_seen": 17509824, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.034712847610598986, | |
| "grad_norm": 1.9628883600234985, | |
| "learning_rate": 0.00015815096169387427, | |
| "loss": 4.9481, | |
| "num_input_tokens_seen": 18398112, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.03636584035396084, | |
| "grad_norm": 1.8523181676864624, | |
| "learning_rate": 0.00015806280029974874, | |
| "loss": 4.9306, | |
| "num_input_tokens_seen": 19272928, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.0380188330973227, | |
| "grad_norm": 1.9627933502197266, | |
| "learning_rate": 0.00015797463890562325, | |
| "loss": 4.9217, | |
| "num_input_tokens_seen": 20162880, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.03967182584068456, | |
| "grad_norm": 1.8966543674468994, | |
| "learning_rate": 0.00015788647751149772, | |
| "loss": 4.919, | |
| "num_input_tokens_seen": 21041888, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.041324818584046415, | |
| "grad_norm": 1.9131779670715332, | |
| "learning_rate": 0.00015779831611737222, | |
| "loss": 4.9118, | |
| "num_input_tokens_seen": 21914272, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.04297781132740827, | |
| "grad_norm": 1.8262194395065308, | |
| "learning_rate": 0.0001577101547232467, | |
| "loss": 4.9139, | |
| "num_input_tokens_seen": 22802432, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.04463080407077013, | |
| "grad_norm": 1.9549835920333862, | |
| "learning_rate": 0.0001576219933291212, | |
| "loss": 4.8919, | |
| "num_input_tokens_seen": 23680544, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.046283796814131986, | |
| "grad_norm": 1.9537177085876465, | |
| "learning_rate": 0.00015753383193499568, | |
| "loss": 4.8895, | |
| "num_input_tokens_seen": 24572928, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.04793678955749384, | |
| "grad_norm": 1.9916348457336426, | |
| "learning_rate": 0.00015744567054087018, | |
| "loss": 4.8798, | |
| "num_input_tokens_seen": 25458752, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.0495897823008557, | |
| "grad_norm": 1.9964395761489868, | |
| "learning_rate": 0.00015735750914674465, | |
| "loss": 4.8734, | |
| "num_input_tokens_seen": 26339424, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.05124277504421756, | |
| "grad_norm": 1.9595707654953003, | |
| "learning_rate": 0.00015726934775261916, | |
| "loss": 4.8654, | |
| "num_input_tokens_seen": 27208928, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.052895767787579415, | |
| "grad_norm": 2.002746820449829, | |
| "learning_rate": 0.00015718118635849363, | |
| "loss": 4.8536, | |
| "num_input_tokens_seen": 28083488, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.05454876053094127, | |
| "grad_norm": 2.014301300048828, | |
| "learning_rate": 0.00015709302496436813, | |
| "loss": 4.8513, | |
| "num_input_tokens_seen": 28948832, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.05620175327430313, | |
| "grad_norm": 1.82748544216156, | |
| "learning_rate": 0.0001570048635702426, | |
| "loss": 4.8477, | |
| "num_input_tokens_seen": 29830752, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.05785474601766498, | |
| "grad_norm": 1.907245397567749, | |
| "learning_rate": 0.0001569167021761171, | |
| "loss": 4.8445, | |
| "num_input_tokens_seen": 30709248, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.059507738761026836, | |
| "grad_norm": 1.9649808406829834, | |
| "learning_rate": 0.00015682854078199158, | |
| "loss": 4.8313, | |
| "num_input_tokens_seen": 31597856, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.06116073150438869, | |
| "grad_norm": 1.9375178813934326, | |
| "learning_rate": 0.00015674037938786606, | |
| "loss": 4.8206, | |
| "num_input_tokens_seen": 32485120, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.06281372424775056, | |
| "grad_norm": 1.8886380195617676, | |
| "learning_rate": 0.00015665221799374056, | |
| "loss": 4.8152, | |
| "num_input_tokens_seen": 33354688, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.06446671699111241, | |
| "grad_norm": 1.8993780612945557, | |
| "learning_rate": 0.00015656405659961504, | |
| "loss": 4.8155, | |
| "num_input_tokens_seen": 34230592, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.06611970973447427, | |
| "grad_norm": 1.8930308818817139, | |
| "learning_rate": 0.00015647589520548954, | |
| "loss": 4.8173, | |
| "num_input_tokens_seen": 35090336, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.06777270247783612, | |
| "grad_norm": 1.951819658279419, | |
| "learning_rate": 0.00015638773381136401, | |
| "loss": 4.8118, | |
| "num_input_tokens_seen": 35973024, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.06942569522119797, | |
| "grad_norm": 1.9142402410507202, | |
| "learning_rate": 0.00015629957241723852, | |
| "loss": 4.8079, | |
| "num_input_tokens_seen": 36855936, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.07107868796455984, | |
| "grad_norm": 1.9393310546875, | |
| "learning_rate": 0.000156211411023113, | |
| "loss": 4.7883, | |
| "num_input_tokens_seen": 37722848, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.07273168070792169, | |
| "grad_norm": 1.8511933088302612, | |
| "learning_rate": 0.00015612383737161498, | |
| "loss": 4.8043, | |
| "num_input_tokens_seen": 38597600, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.07438467345128355, | |
| "grad_norm": 1.8763892650604248, | |
| "learning_rate": 0.00015603567597748946, | |
| "loss": 4.7932, | |
| "num_input_tokens_seen": 39493152, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.0760376661946454, | |
| "grad_norm": 1.9806557893753052, | |
| "learning_rate": 0.00015594751458336396, | |
| "loss": 4.7813, | |
| "num_input_tokens_seen": 40352640, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.07769065893800726, | |
| "grad_norm": 2.001722574234009, | |
| "learning_rate": 0.00015585935318923843, | |
| "loss": 4.7941, | |
| "num_input_tokens_seen": 41236160, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.07934365168136912, | |
| "grad_norm": 2.1065292358398438, | |
| "learning_rate": 0.00015577119179511294, | |
| "loss": 4.7819, | |
| "num_input_tokens_seen": 42111296, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.08099664442473098, | |
| "grad_norm": 1.8941328525543213, | |
| "learning_rate": 0.0001556830304009874, | |
| "loss": 4.7737, | |
| "num_input_tokens_seen": 42992864, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.08264963716809283, | |
| "grad_norm": 1.8765467405319214, | |
| "learning_rate": 0.00015559486900686191, | |
| "loss": 4.764, | |
| "num_input_tokens_seen": 43871808, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.0843026299114547, | |
| "grad_norm": 1.9826706647872925, | |
| "learning_rate": 0.0001555067076127364, | |
| "loss": 4.7805, | |
| "num_input_tokens_seen": 44742496, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.08595562265481654, | |
| "grad_norm": 1.9296499490737915, | |
| "learning_rate": 0.0001554185462186109, | |
| "loss": 4.7585, | |
| "num_input_tokens_seen": 45594112, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.08760861539817841, | |
| "grad_norm": 1.9379116296768188, | |
| "learning_rate": 0.00015533038482448537, | |
| "loss": 4.7682, | |
| "num_input_tokens_seen": 46465952, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.08926160814154026, | |
| "grad_norm": 1.8769218921661377, | |
| "learning_rate": 0.00015524222343035987, | |
| "loss": 4.7574, | |
| "num_input_tokens_seen": 47325664, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.09091460088490212, | |
| "grad_norm": 1.8942108154296875, | |
| "learning_rate": 0.00015515406203623434, | |
| "loss": 4.7493, | |
| "num_input_tokens_seen": 48202944, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.09256759362826397, | |
| "grad_norm": 1.84010648727417, | |
| "learning_rate": 0.00015506590064210885, | |
| "loss": 4.7515, | |
| "num_input_tokens_seen": 49074048, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.09422058637162582, | |
| "grad_norm": 1.8978796005249023, | |
| "learning_rate": 0.00015497773924798332, | |
| "loss": 4.7512, | |
| "num_input_tokens_seen": 49959008, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.09587357911498769, | |
| "grad_norm": 1.9536223411560059, | |
| "learning_rate": 0.0001548895778538578, | |
| "loss": 4.758, | |
| "num_input_tokens_seen": 50863648, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.09752657185834954, | |
| "grad_norm": 2.0626060962677, | |
| "learning_rate": 0.0001548014164597323, | |
| "loss": 4.7434, | |
| "num_input_tokens_seen": 51730944, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.0991795646017114, | |
| "grad_norm": 1.9423109292984009, | |
| "learning_rate": 0.00015471325506560677, | |
| "loss": 4.736, | |
| "num_input_tokens_seen": 52593024, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.10083255734507325, | |
| "grad_norm": 1.9180619716644287, | |
| "learning_rate": 0.00015462509367148127, | |
| "loss": 4.7187, | |
| "num_input_tokens_seen": 53470528, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.10248555008843512, | |
| "grad_norm": 1.8776642084121704, | |
| "learning_rate": 0.00015453693227735575, | |
| "loss": 4.7382, | |
| "num_input_tokens_seen": 54362720, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.10413854283179697, | |
| "grad_norm": 1.9289714097976685, | |
| "learning_rate": 0.00015444877088323025, | |
| "loss": 4.7181, | |
| "num_input_tokens_seen": 55238304, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.10579153557515883, | |
| "grad_norm": 1.9489550590515137, | |
| "learning_rate": 0.00015436060948910473, | |
| "loss": 4.7287, | |
| "num_input_tokens_seen": 56107040, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.10744452831852068, | |
| "grad_norm": 2.01839280128479, | |
| "learning_rate": 0.00015427244809497923, | |
| "loss": 4.7097, | |
| "num_input_tokens_seen": 56995456, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.10909752106188254, | |
| "grad_norm": 1.9155646562576294, | |
| "learning_rate": 0.0001541842867008537, | |
| "loss": 4.7153, | |
| "num_input_tokens_seen": 57852640, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.1107505138052444, | |
| "grad_norm": 2.008150100708008, | |
| "learning_rate": 0.0001540961253067282, | |
| "loss": 4.7139, | |
| "num_input_tokens_seen": 58719840, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 0.11240350654860626, | |
| "grad_norm": 1.9440505504608154, | |
| "learning_rate": 0.00015400796391260268, | |
| "loss": 4.7184, | |
| "num_input_tokens_seen": 59594784, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.11405649929196811, | |
| "grad_norm": 1.9298348426818848, | |
| "learning_rate": 0.00015391980251847718, | |
| "loss": 4.708, | |
| "num_input_tokens_seen": 60451712, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 0.11570949203532996, | |
| "grad_norm": 1.9444379806518555, | |
| "learning_rate": 0.00015383164112435166, | |
| "loss": 4.6979, | |
| "num_input_tokens_seen": 61335008, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.11736248477869182, | |
| "grad_norm": 2.0216357707977295, | |
| "learning_rate": 0.00015374406747285365, | |
| "loss": 4.7055, | |
| "num_input_tokens_seen": 62197344, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 0.11901547752205367, | |
| "grad_norm": 1.9788328409194946, | |
| "learning_rate": 0.00015365590607872815, | |
| "loss": 4.6948, | |
| "num_input_tokens_seen": 63058464, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.12066847026541554, | |
| "grad_norm": 2.0648193359375, | |
| "learning_rate": 0.00015356774468460263, | |
| "loss": 4.7058, | |
| "num_input_tokens_seen": 63942112, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 0.12232146300877739, | |
| "grad_norm": 1.9497121572494507, | |
| "learning_rate": 0.00015348017103310462, | |
| "loss": 4.6924, | |
| "num_input_tokens_seen": 64815232, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.12397445575213925, | |
| "grad_norm": 1.9825148582458496, | |
| "learning_rate": 0.0001533920096389791, | |
| "loss": 4.7021, | |
| "num_input_tokens_seen": 65689856, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.12562744849550112, | |
| "grad_norm": 1.9766299724578857, | |
| "learning_rate": 0.0001533038482448536, | |
| "loss": 4.6921, | |
| "num_input_tokens_seen": 66570272, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.12728044123886295, | |
| "grad_norm": 1.9706653356552124, | |
| "learning_rate": 0.00015321568685072807, | |
| "loss": 4.6847, | |
| "num_input_tokens_seen": 67436096, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 0.12893343398222482, | |
| "grad_norm": 1.9741766452789307, | |
| "learning_rate": 0.00015312811319923006, | |
| "loss": 4.6835, | |
| "num_input_tokens_seen": 68326816, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.13058642672558668, | |
| "grad_norm": 1.850825548171997, | |
| "learning_rate": 0.00015303995180510456, | |
| "loss": 4.6874, | |
| "num_input_tokens_seen": 69203328, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 0.13223941946894854, | |
| "grad_norm": 2.0040206909179688, | |
| "learning_rate": 0.00015295179041097904, | |
| "loss": 4.6805, | |
| "num_input_tokens_seen": 70049696, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.13389241221231038, | |
| "grad_norm": 1.9326891899108887, | |
| "learning_rate": 0.00015286362901685354, | |
| "loss": 4.6781, | |
| "num_input_tokens_seen": 70929856, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 0.13554540495567224, | |
| "grad_norm": 1.8233270645141602, | |
| "learning_rate": 0.00015277546762272802, | |
| "loss": 4.6732, | |
| "num_input_tokens_seen": 71797184, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.1371983976990341, | |
| "grad_norm": 2.026263475418091, | |
| "learning_rate": 0.00015268730622860252, | |
| "loss": 4.672, | |
| "num_input_tokens_seen": 72662528, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 0.13885139044239594, | |
| "grad_norm": 1.8338570594787598, | |
| "learning_rate": 0.000152599144834477, | |
| "loss": 4.6718, | |
| "num_input_tokens_seen": 73543840, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.1405043831857578, | |
| "grad_norm": 1.934313416481018, | |
| "learning_rate": 0.0001525109834403515, | |
| "loss": 4.6595, | |
| "num_input_tokens_seen": 74426752, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 0.14215737592911967, | |
| "grad_norm": 1.861647367477417, | |
| "learning_rate": 0.00015242282204622597, | |
| "loss": 4.6692, | |
| "num_input_tokens_seen": 75309888, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.14381036867248154, | |
| "grad_norm": 1.9282541275024414, | |
| "learning_rate": 0.00015233466065210047, | |
| "loss": 4.6604, | |
| "num_input_tokens_seen": 76194976, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 0.14546336141584337, | |
| "grad_norm": 1.975542664527893, | |
| "learning_rate": 0.00015224649925797495, | |
| "loss": 4.662, | |
| "num_input_tokens_seen": 77078048, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.14711635415920524, | |
| "grad_norm": 1.8979029655456543, | |
| "learning_rate": 0.00015215833786384945, | |
| "loss": 4.6554, | |
| "num_input_tokens_seen": 77940000, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 0.1487693469025671, | |
| "grad_norm": 1.875108242034912, | |
| "learning_rate": 0.00015207017646972392, | |
| "loss": 4.6599, | |
| "num_input_tokens_seen": 78822336, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.15042233964592897, | |
| "grad_norm": 1.9476161003112793, | |
| "learning_rate": 0.0001519820150755984, | |
| "loss": 4.6688, | |
| "num_input_tokens_seen": 79708256, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 0.1520753323892908, | |
| "grad_norm": 1.9902242422103882, | |
| "learning_rate": 0.0001518938536814729, | |
| "loss": 4.6626, | |
| "num_input_tokens_seen": 80595168, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.15372832513265267, | |
| "grad_norm": 1.7958108186721802, | |
| "learning_rate": 0.00015180569228734738, | |
| "loss": 4.662, | |
| "num_input_tokens_seen": 81484416, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 0.15538131787601453, | |
| "grad_norm": 1.8727210760116577, | |
| "learning_rate": 0.00015171753089322188, | |
| "loss": 4.6579, | |
| "num_input_tokens_seen": 82355712, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.1570343106193764, | |
| "grad_norm": 2.0186071395874023, | |
| "learning_rate": 0.00015162936949909635, | |
| "loss": 4.6494, | |
| "num_input_tokens_seen": 83223136, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 0.15868730336273823, | |
| "grad_norm": 1.8837051391601562, | |
| "learning_rate": 0.00015154120810497086, | |
| "loss": 4.6463, | |
| "num_input_tokens_seen": 84097152, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.1603402961061001, | |
| "grad_norm": 1.8699517250061035, | |
| "learning_rate": 0.00015145304671084533, | |
| "loss": 4.6489, | |
| "num_input_tokens_seen": 84976576, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 0.16199328884946196, | |
| "grad_norm": 1.956932783126831, | |
| "learning_rate": 0.00015136488531671983, | |
| "loss": 4.649, | |
| "num_input_tokens_seen": 85868224, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.1636462815928238, | |
| "grad_norm": 2.020624876022339, | |
| "learning_rate": 0.0001512767239225943, | |
| "loss": 4.6458, | |
| "num_input_tokens_seen": 86746944, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 0.16529927433618566, | |
| "grad_norm": 1.9445135593414307, | |
| "learning_rate": 0.0001511885625284688, | |
| "loss": 4.6387, | |
| "num_input_tokens_seen": 87626976, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.16695226707954752, | |
| "grad_norm": 1.9843000173568726, | |
| "learning_rate": 0.00015110040113434328, | |
| "loss": 4.6481, | |
| "num_input_tokens_seen": 88483616, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 0.1686052598229094, | |
| "grad_norm": 2.0259897708892822, | |
| "learning_rate": 0.00015101282748284528, | |
| "loss": 4.6317, | |
| "num_input_tokens_seen": 89374048, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.17025825256627122, | |
| "grad_norm": 1.8472915887832642, | |
| "learning_rate": 0.00015092466608871975, | |
| "loss": 4.6468, | |
| "num_input_tokens_seen": 90265376, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 0.1719112453096331, | |
| "grad_norm": 1.9485039710998535, | |
| "learning_rate": 0.00015083650469459425, | |
| "loss": 4.6272, | |
| "num_input_tokens_seen": 91161504, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.17356423805299495, | |
| "grad_norm": 2.0340664386749268, | |
| "learning_rate": 0.00015074834330046873, | |
| "loss": 4.6252, | |
| "num_input_tokens_seen": 92033536, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 0.17521723079635682, | |
| "grad_norm": 1.8034217357635498, | |
| "learning_rate": 0.00015066018190634323, | |
| "loss": 4.6347, | |
| "num_input_tokens_seen": 92906464, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.17687022353971865, | |
| "grad_norm": 1.9323750734329224, | |
| "learning_rate": 0.0001505720205122177, | |
| "loss": 4.624, | |
| "num_input_tokens_seen": 93773664, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 0.17852321628308052, | |
| "grad_norm": 1.9791151285171509, | |
| "learning_rate": 0.00015048385911809218, | |
| "loss": 4.6184, | |
| "num_input_tokens_seen": 94646528, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.18017620902644238, | |
| "grad_norm": 2.0325284004211426, | |
| "learning_rate": 0.00015039569772396668, | |
| "loss": 4.6129, | |
| "num_input_tokens_seen": 95522304, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 0.18182920176980424, | |
| "grad_norm": 1.773972511291504, | |
| "learning_rate": 0.00015030753632984116, | |
| "loss": 4.6283, | |
| "num_input_tokens_seen": 96397632, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.18348219451316608, | |
| "grad_norm": 1.792601466178894, | |
| "learning_rate": 0.00015021937493571566, | |
| "loss": 4.6201, | |
| "num_input_tokens_seen": 97283072, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 0.18513518725652794, | |
| "grad_norm": 1.9488441944122314, | |
| "learning_rate": 0.00015013121354159013, | |
| "loss": 4.6174, | |
| "num_input_tokens_seen": 98164960, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.1867881799998898, | |
| "grad_norm": 1.8708151578903198, | |
| "learning_rate": 0.00015004305214746464, | |
| "loss": 4.6156, | |
| "num_input_tokens_seen": 99030464, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 0.18844117274325164, | |
| "grad_norm": 1.9848783016204834, | |
| "learning_rate": 0.0001499548907533391, | |
| "loss": 4.6069, | |
| "num_input_tokens_seen": 99913184, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.1900941654866135, | |
| "grad_norm": 1.9591269493103027, | |
| "learning_rate": 0.00014986672935921361, | |
| "loss": 4.6195, | |
| "num_input_tokens_seen": 100797056, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 0.19174715822997537, | |
| "grad_norm": 1.9400300979614258, | |
| "learning_rate": 0.0001497785679650881, | |
| "loss": 4.6167, | |
| "num_input_tokens_seen": 101678336, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.19340015097333724, | |
| "grad_norm": 1.9163286685943604, | |
| "learning_rate": 0.0001496904065709626, | |
| "loss": 4.6135, | |
| "num_input_tokens_seen": 102532640, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 0.19505314371669907, | |
| "grad_norm": 1.86648690700531, | |
| "learning_rate": 0.00014960224517683707, | |
| "loss": 4.6063, | |
| "num_input_tokens_seen": 103403264, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.19670613646006094, | |
| "grad_norm": 1.9310001134872437, | |
| "learning_rate": 0.00014951408378271157, | |
| "loss": 4.6143, | |
| "num_input_tokens_seen": 104304224, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 0.1983591292034228, | |
| "grad_norm": 1.9832515716552734, | |
| "learning_rate": 0.00014942592238858604, | |
| "loss": 4.6138, | |
| "num_input_tokens_seen": 105184128, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.20001212194678467, | |
| "grad_norm": 1.9453548192977905, | |
| "learning_rate": 0.00014933776099446055, | |
| "loss": 4.6143, | |
| "num_input_tokens_seen": 106070880, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 0.2016651146901465, | |
| "grad_norm": 1.8135297298431396, | |
| "learning_rate": 0.00014924959960033502, | |
| "loss": 4.6197, | |
| "num_input_tokens_seen": 106944960, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.20331810743350837, | |
| "grad_norm": 1.892717719078064, | |
| "learning_rate": 0.00014916143820620952, | |
| "loss": 4.6039, | |
| "num_input_tokens_seen": 107808512, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 0.20497110017687023, | |
| "grad_norm": 1.9304077625274658, | |
| "learning_rate": 0.000149073276812084, | |
| "loss": 4.6103, | |
| "num_input_tokens_seen": 108679584, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.20662409292023207, | |
| "grad_norm": 1.874104380607605, | |
| "learning_rate": 0.0001489851154179585, | |
| "loss": 4.6092, | |
| "num_input_tokens_seen": 109561440, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 0.20827708566359393, | |
| "grad_norm": 1.9672309160232544, | |
| "learning_rate": 0.00014889695402383297, | |
| "loss": 4.6027, | |
| "num_input_tokens_seen": 110445760, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.2099300784069558, | |
| "grad_norm": 1.9013960361480713, | |
| "learning_rate": 0.00014880879262970748, | |
| "loss": 4.6161, | |
| "num_input_tokens_seen": 111310304, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 0.21158307115031766, | |
| "grad_norm": 1.902948021888733, | |
| "learning_rate": 0.00014872063123558195, | |
| "loss": 4.6118, | |
| "num_input_tokens_seen": 112181440, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.2132360638936795, | |
| "grad_norm": 1.9160059690475464, | |
| "learning_rate": 0.00014863246984145645, | |
| "loss": 4.5929, | |
| "num_input_tokens_seen": 113074496, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 0.21488905663704136, | |
| "grad_norm": 1.843983769416809, | |
| "learning_rate": 0.00014854489618995845, | |
| "loss": 4.5982, | |
| "num_input_tokens_seen": 113972512, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.21654204938040322, | |
| "grad_norm": 1.83791184425354, | |
| "learning_rate": 0.00014845673479583292, | |
| "loss": 4.6046, | |
| "num_input_tokens_seen": 114839680, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 0.2181950421237651, | |
| "grad_norm": 1.8458436727523804, | |
| "learning_rate": 0.00014836857340170742, | |
| "loss": 4.5987, | |
| "num_input_tokens_seen": 115716000, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.21984803486712692, | |
| "grad_norm": 2.0030035972595215, | |
| "learning_rate": 0.0001482804120075819, | |
| "loss": 4.5873, | |
| "num_input_tokens_seen": 116581408, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 0.2215010276104888, | |
| "grad_norm": 1.8120313882827759, | |
| "learning_rate": 0.00014819225061345637, | |
| "loss": 4.5893, | |
| "num_input_tokens_seen": 117446368, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.22315402035385065, | |
| "grad_norm": 1.8799773454666138, | |
| "learning_rate": 0.00014810408921933087, | |
| "loss": 4.5746, | |
| "num_input_tokens_seen": 118320096, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 0.22480701309721252, | |
| "grad_norm": 1.9042309522628784, | |
| "learning_rate": 0.00014801592782520535, | |
| "loss": 4.5851, | |
| "num_input_tokens_seen": 119192128, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.22646000584057435, | |
| "grad_norm": 1.8850473165512085, | |
| "learning_rate": 0.00014792776643107985, | |
| "loss": 4.5883, | |
| "num_input_tokens_seen": 120065888, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 0.22811299858393622, | |
| "grad_norm": 1.8963854312896729, | |
| "learning_rate": 0.00014783960503695433, | |
| "loss": 4.5869, | |
| "num_input_tokens_seen": 120921504, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.22976599132729808, | |
| "grad_norm": 1.8145036697387695, | |
| "learning_rate": 0.00014775144364282883, | |
| "loss": 4.5857, | |
| "num_input_tokens_seen": 121819936, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 0.23141898407065992, | |
| "grad_norm": 1.8780988454818726, | |
| "learning_rate": 0.0001476632822487033, | |
| "loss": 4.5793, | |
| "num_input_tokens_seen": 122700576, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.23307197681402178, | |
| "grad_norm": 1.8859424591064453, | |
| "learning_rate": 0.00014757512085457778, | |
| "loss": 4.5847, | |
| "num_input_tokens_seen": 123578848, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 0.23472496955738364, | |
| "grad_norm": 1.8556190729141235, | |
| "learning_rate": 0.00014748695946045228, | |
| "loss": 4.5915, | |
| "num_input_tokens_seen": 124451552, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.2363779623007455, | |
| "grad_norm": 1.8445396423339844, | |
| "learning_rate": 0.00014739879806632676, | |
| "loss": 4.5857, | |
| "num_input_tokens_seen": 125326208, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 0.23803095504410735, | |
| "grad_norm": 1.903262972831726, | |
| "learning_rate": 0.00014731063667220126, | |
| "loss": 4.5811, | |
| "num_input_tokens_seen": 126206560, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.2396839477874692, | |
| "grad_norm": 1.7595880031585693, | |
| "learning_rate": 0.00014722247527807573, | |
| "loss": 4.567, | |
| "num_input_tokens_seen": 127077440, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 0.24133694053083107, | |
| "grad_norm": 1.8828771114349365, | |
| "learning_rate": 0.00014713431388395024, | |
| "loss": 4.5792, | |
| "num_input_tokens_seen": 127955584, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.24298993327419294, | |
| "grad_norm": 1.8850219249725342, | |
| "learning_rate": 0.0001470461524898247, | |
| "loss": 4.5749, | |
| "num_input_tokens_seen": 128807200, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 0.24464292601755477, | |
| "grad_norm": 1.9162580966949463, | |
| "learning_rate": 0.00014695799109569919, | |
| "loss": 4.5725, | |
| "num_input_tokens_seen": 129672192, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.24629591876091664, | |
| "grad_norm": 1.866351842880249, | |
| "learning_rate": 0.0001468698297015737, | |
| "loss": 4.569, | |
| "num_input_tokens_seen": 130541696, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 0.2479489115042785, | |
| "grad_norm": 1.849186658859253, | |
| "learning_rate": 0.00014678166830744816, | |
| "loss": 4.5832, | |
| "num_input_tokens_seen": 131420992, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.24960190424764037, | |
| "grad_norm": 1.8402087688446045, | |
| "learning_rate": 0.00014669350691332266, | |
| "loss": 4.5664, | |
| "num_input_tokens_seen": 132312352, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 0.25125489699100223, | |
| "grad_norm": 1.8887277841567993, | |
| "learning_rate": 0.00014660534551919714, | |
| "loss": 4.5771, | |
| "num_input_tokens_seen": 133195968, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.25290788973436407, | |
| "grad_norm": 2.029491424560547, | |
| "learning_rate": 0.00014651718412507164, | |
| "loss": 4.5718, | |
| "num_input_tokens_seen": 134079040, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 0.2545608824777259, | |
| "grad_norm": 1.9162187576293945, | |
| "learning_rate": 0.00014642902273094612, | |
| "loss": 4.5746, | |
| "num_input_tokens_seen": 134957440, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.2562138752210878, | |
| "grad_norm": 1.8331772089004517, | |
| "learning_rate": 0.00014634086133682062, | |
| "loss": 4.5736, | |
| "num_input_tokens_seen": 135835328, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 0.25786686796444963, | |
| "grad_norm": 1.9076178073883057, | |
| "learning_rate": 0.0001462526999426951, | |
| "loss": 4.5647, | |
| "num_input_tokens_seen": 136701184, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.25951986070781147, | |
| "grad_norm": 1.9407544136047363, | |
| "learning_rate": 0.0001461645385485696, | |
| "loss": 4.5607, | |
| "num_input_tokens_seen": 137547264, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 0.26117285345117336, | |
| "grad_norm": 1.9287118911743164, | |
| "learning_rate": 0.0001460769648970716, | |
| "loss": 4.5642, | |
| "num_input_tokens_seen": 138417888, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.2628258461945352, | |
| "grad_norm": 2.0106074810028076, | |
| "learning_rate": 0.00014598939124557358, | |
| "loss": 4.5689, | |
| "num_input_tokens_seen": 139297088, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 0.2644788389378971, | |
| "grad_norm": 1.8796470165252686, | |
| "learning_rate": 0.00014590122985144808, | |
| "loss": 4.5736, | |
| "num_input_tokens_seen": 140165984, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.2661318316812589, | |
| "grad_norm": 1.8495882749557495, | |
| "learning_rate": 0.00014581306845732256, | |
| "loss": 4.5613, | |
| "num_input_tokens_seen": 141043680, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 0.26778482442462076, | |
| "grad_norm": 1.8603812456130981, | |
| "learning_rate": 0.00014572490706319706, | |
| "loss": 4.5707, | |
| "num_input_tokens_seen": 141913088, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.26943781716798265, | |
| "grad_norm": 1.8450992107391357, | |
| "learning_rate": 0.00014563674566907153, | |
| "loss": 4.5685, | |
| "num_input_tokens_seen": 142780992, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 0.2710908099113445, | |
| "grad_norm": 1.9459301233291626, | |
| "learning_rate": 0.000145548584274946, | |
| "loss": 4.5624, | |
| "num_input_tokens_seen": 143655008, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.2727438026547063, | |
| "grad_norm": 1.87797212600708, | |
| "learning_rate": 0.0001454604228808205, | |
| "loss": 4.5753, | |
| "num_input_tokens_seen": 144533760, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 0.2743967953980682, | |
| "grad_norm": 1.9368420839309692, | |
| "learning_rate": 0.00014537226148669498, | |
| "loss": 4.5473, | |
| "num_input_tokens_seen": 145405376, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.27604978814143005, | |
| "grad_norm": 1.9425833225250244, | |
| "learning_rate": 0.0001452841000925695, | |
| "loss": 4.5621, | |
| "num_input_tokens_seen": 146278176, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 0.2777027808847919, | |
| "grad_norm": 1.8315942287445068, | |
| "learning_rate": 0.00014519593869844396, | |
| "loss": 4.5441, | |
| "num_input_tokens_seen": 147150880, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.2793557736281538, | |
| "grad_norm": 1.865020990371704, | |
| "learning_rate": 0.00014510777730431846, | |
| "loss": 4.5681, | |
| "num_input_tokens_seen": 148039488, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 0.2810087663715156, | |
| "grad_norm": 1.9058725833892822, | |
| "learning_rate": 0.00014501961591019294, | |
| "loss": 4.55, | |
| "num_input_tokens_seen": 148898720, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.2826617591148775, | |
| "grad_norm": 1.9358283281326294, | |
| "learning_rate": 0.00014493145451606741, | |
| "loss": 4.5608, | |
| "num_input_tokens_seen": 149776576, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 0.28431475185823935, | |
| "grad_norm": 1.871090292930603, | |
| "learning_rate": 0.00014484329312194192, | |
| "loss": 4.539, | |
| "num_input_tokens_seen": 150667296, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.2859677446016012, | |
| "grad_norm": 1.885185956954956, | |
| "learning_rate": 0.0001447551317278164, | |
| "loss": 4.5421, | |
| "num_input_tokens_seen": 151536512, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 0.2876207373449631, | |
| "grad_norm": 1.851283073425293, | |
| "learning_rate": 0.0001446669703336909, | |
| "loss": 4.5469, | |
| "num_input_tokens_seen": 152395904, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.2892737300883249, | |
| "grad_norm": 1.8593121767044067, | |
| "learning_rate": 0.00014457880893956537, | |
| "loss": 4.5536, | |
| "num_input_tokens_seen": 153263904, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 0.29092672283168675, | |
| "grad_norm": 1.8973345756530762, | |
| "learning_rate": 0.00014449064754543987, | |
| "loss": 4.5613, | |
| "num_input_tokens_seen": 154143616, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.29257971557504864, | |
| "grad_norm": 1.9224932193756104, | |
| "learning_rate": 0.00014440307389394186, | |
| "loss": 4.5513, | |
| "num_input_tokens_seen": 155013568, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 0.2942327083184105, | |
| "grad_norm": 1.8901547193527222, | |
| "learning_rate": 0.00014431491249981634, | |
| "loss": 4.5552, | |
| "num_input_tokens_seen": 155889408, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.29588570106177237, | |
| "grad_norm": 1.8522729873657227, | |
| "learning_rate": 0.0001442267511056908, | |
| "loss": 4.546, | |
| "num_input_tokens_seen": 156769184, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 0.2975386938051342, | |
| "grad_norm": 1.8729475736618042, | |
| "learning_rate": 0.00014413858971156531, | |
| "loss": 4.553, | |
| "num_input_tokens_seen": 157648416, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.29919168654849604, | |
| "grad_norm": 1.8859171867370605, | |
| "learning_rate": 0.0001440504283174398, | |
| "loss": 4.5468, | |
| "num_input_tokens_seen": 158528480, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 0.30084467929185793, | |
| "grad_norm": 1.8305902481079102, | |
| "learning_rate": 0.0001439628546659418, | |
| "loss": 4.554, | |
| "num_input_tokens_seen": 159401376, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.30249767203521977, | |
| "grad_norm": 1.7858612537384033, | |
| "learning_rate": 0.00014387469327181628, | |
| "loss": 4.5459, | |
| "num_input_tokens_seen": 160297888, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 0.3041506647785816, | |
| "grad_norm": 1.9333041906356812, | |
| "learning_rate": 0.00014378653187769078, | |
| "loss": 4.5488, | |
| "num_input_tokens_seen": 161189632, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.3058036575219435, | |
| "grad_norm": 1.904167652130127, | |
| "learning_rate": 0.00014369837048356526, | |
| "loss": 4.5457, | |
| "num_input_tokens_seen": 162069728, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 0.30745665026530533, | |
| "grad_norm": 1.8620493412017822, | |
| "learning_rate": 0.00014361020908943976, | |
| "loss": 4.543, | |
| "num_input_tokens_seen": 162956000, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.30910964300866717, | |
| "grad_norm": 1.9523295164108276, | |
| "learning_rate": 0.00014352204769531424, | |
| "loss": 4.5368, | |
| "num_input_tokens_seen": 163850880, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 0.31076263575202906, | |
| "grad_norm": 1.842017412185669, | |
| "learning_rate": 0.00014343388630118874, | |
| "loss": 4.5423, | |
| "num_input_tokens_seen": 164723840, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.3124156284953909, | |
| "grad_norm": 2.015977621078491, | |
| "learning_rate": 0.0001433457249070632, | |
| "loss": 4.5306, | |
| "num_input_tokens_seen": 165582464, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 0.3140686212387528, | |
| "grad_norm": 1.7622820138931274, | |
| "learning_rate": 0.00014325756351293772, | |
| "loss": 4.5336, | |
| "num_input_tokens_seen": 166442496, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.3157216139821146, | |
| "grad_norm": 1.8762463331222534, | |
| "learning_rate": 0.0001431694021188122, | |
| "loss": 4.5363, | |
| "num_input_tokens_seen": 167318048, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 0.31737460672547646, | |
| "grad_norm": 1.9524190425872803, | |
| "learning_rate": 0.00014308124072468667, | |
| "loss": 4.5498, | |
| "num_input_tokens_seen": 168209312, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.31902759946883835, | |
| "grad_norm": 1.8535164594650269, | |
| "learning_rate": 0.00014299307933056117, | |
| "loss": 4.5481, | |
| "num_input_tokens_seen": 169096896, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 0.3206805922122002, | |
| "grad_norm": 1.9309056997299194, | |
| "learning_rate": 0.00014290491793643564, | |
| "loss": 4.5416, | |
| "num_input_tokens_seen": 169963008, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.322333584955562, | |
| "grad_norm": 1.8341314792633057, | |
| "learning_rate": 0.00014281675654231014, | |
| "loss": 4.5439, | |
| "num_input_tokens_seen": 170836736, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 0.3239865776989239, | |
| "grad_norm": 1.8341432809829712, | |
| "learning_rate": 0.00014272859514818462, | |
| "loss": 4.5365, | |
| "num_input_tokens_seen": 171728896, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.32563957044228575, | |
| "grad_norm": 1.9161962270736694, | |
| "learning_rate": 0.00014264043375405912, | |
| "loss": 4.5428, | |
| "num_input_tokens_seen": 172603008, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 0.3272925631856476, | |
| "grad_norm": 1.8521162271499634, | |
| "learning_rate": 0.0001425522723599336, | |
| "loss": 4.5283, | |
| "num_input_tokens_seen": 173475392, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.3289455559290095, | |
| "grad_norm": 1.9026546478271484, | |
| "learning_rate": 0.0001424641109658081, | |
| "loss": 4.5306, | |
| "num_input_tokens_seen": 174360832, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 0.3305985486723713, | |
| "grad_norm": 1.9297667741775513, | |
| "learning_rate": 0.00014237594957168257, | |
| "loss": 4.5301, | |
| "num_input_tokens_seen": 175244576, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.3322515414157332, | |
| "grad_norm": 1.9747087955474854, | |
| "learning_rate": 0.00014228778817755705, | |
| "loss": 4.54, | |
| "num_input_tokens_seen": 176108352, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 0.33390453415909505, | |
| "grad_norm": 1.9235451221466064, | |
| "learning_rate": 0.00014219962678343155, | |
| "loss": 4.5438, | |
| "num_input_tokens_seen": 176987808, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 0.3355575269024569, | |
| "grad_norm": 1.8416277170181274, | |
| "learning_rate": 0.00014211146538930603, | |
| "loss": 4.5476, | |
| "num_input_tokens_seen": 177875584, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 0.3372105196458188, | |
| "grad_norm": 1.899798035621643, | |
| "learning_rate": 0.00014202330399518053, | |
| "loss": 4.5413, | |
| "num_input_tokens_seen": 178752480, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 0.3388635123891806, | |
| "grad_norm": 1.8849375247955322, | |
| "learning_rate": 0.000141935142601055, | |
| "loss": 4.5199, | |
| "num_input_tokens_seen": 179634080, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 0.34051650513254245, | |
| "grad_norm": 1.7944519519805908, | |
| "learning_rate": 0.0001418469812069295, | |
| "loss": 4.5268, | |
| "num_input_tokens_seen": 180501472, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 0.34216949787590434, | |
| "grad_norm": 1.8572932481765747, | |
| "learning_rate": 0.00014175881981280398, | |
| "loss": 4.5268, | |
| "num_input_tokens_seen": 181388384, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 0.3438224906192662, | |
| "grad_norm": 1.8637559413909912, | |
| "learning_rate": 0.00014167065841867846, | |
| "loss": 4.5245, | |
| "num_input_tokens_seen": 182271040, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 0.345475483362628, | |
| "grad_norm": 1.902794361114502, | |
| "learning_rate": 0.00014158249702455296, | |
| "loss": 4.5138, | |
| "num_input_tokens_seen": 183160032, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 0.3471284761059899, | |
| "grad_norm": 1.8915212154388428, | |
| "learning_rate": 0.00014149433563042743, | |
| "loss": 4.5296, | |
| "num_input_tokens_seen": 184045856, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.34878146884935174, | |
| "grad_norm": 1.9054772853851318, | |
| "learning_rate": 0.00014140617423630193, | |
| "loss": 4.5343, | |
| "num_input_tokens_seen": 184935872, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 0.35043446159271363, | |
| "grad_norm": 1.8381603956222534, | |
| "learning_rate": 0.0001413180128421764, | |
| "loss": 4.5241, | |
| "num_input_tokens_seen": 185812160, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 0.35208745433607547, | |
| "grad_norm": 1.8929849863052368, | |
| "learning_rate": 0.0001412298514480509, | |
| "loss": 4.5311, | |
| "num_input_tokens_seen": 186698304, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 0.3537404470794373, | |
| "grad_norm": 1.8554471731185913, | |
| "learning_rate": 0.0001411422777965529, | |
| "loss": 4.52, | |
| "num_input_tokens_seen": 187570560, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 0.3553934398227992, | |
| "grad_norm": 1.8524342775344849, | |
| "learning_rate": 0.00014105411640242738, | |
| "loss": 4.5231, | |
| "num_input_tokens_seen": 188446880, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 0.35704643256616103, | |
| "grad_norm": 1.8730753660202026, | |
| "learning_rate": 0.00014096595500830188, | |
| "loss": 4.5315, | |
| "num_input_tokens_seen": 189329856, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 0.35869942530952287, | |
| "grad_norm": 1.8252793550491333, | |
| "learning_rate": 0.00014087779361417636, | |
| "loss": 4.5165, | |
| "num_input_tokens_seen": 190203872, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 0.36035241805288476, | |
| "grad_norm": 1.8541933298110962, | |
| "learning_rate": 0.00014078963222005086, | |
| "loss": 4.5318, | |
| "num_input_tokens_seen": 191086784, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 0.3620054107962466, | |
| "grad_norm": 1.9790152311325073, | |
| "learning_rate": 0.00014070147082592533, | |
| "loss": 4.5202, | |
| "num_input_tokens_seen": 191964288, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 0.3636584035396085, | |
| "grad_norm": 1.980690836906433, | |
| "learning_rate": 0.00014061330943179983, | |
| "loss": 4.5282, | |
| "num_input_tokens_seen": 192848672, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.3653113962829703, | |
| "grad_norm": 1.8499431610107422, | |
| "learning_rate": 0.0001405251480376743, | |
| "loss": 4.5094, | |
| "num_input_tokens_seen": 193723936, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 0.36696438902633216, | |
| "grad_norm": 1.7975043058395386, | |
| "learning_rate": 0.0001404369866435488, | |
| "loss": 4.5296, | |
| "num_input_tokens_seen": 194603072, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 0.36861738176969405, | |
| "grad_norm": 1.8439886569976807, | |
| "learning_rate": 0.0001403488252494233, | |
| "loss": 4.5274, | |
| "num_input_tokens_seen": 195468512, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 0.3702703745130559, | |
| "grad_norm": 1.8969649076461792, | |
| "learning_rate": 0.0001402606638552978, | |
| "loss": 4.5195, | |
| "num_input_tokens_seen": 196345888, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 0.3719233672564177, | |
| "grad_norm": 1.8763043880462646, | |
| "learning_rate": 0.00014017250246117226, | |
| "loss": 4.5071, | |
| "num_input_tokens_seen": 197239776, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 0.3735763599997796, | |
| "grad_norm": 1.8754463195800781, | |
| "learning_rate": 0.00014008434106704677, | |
| "loss": 4.513, | |
| "num_input_tokens_seen": 198122528, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 0.37522935274314145, | |
| "grad_norm": 2.011179208755493, | |
| "learning_rate": 0.00013999617967292124, | |
| "loss": 4.5146, | |
| "num_input_tokens_seen": 198998208, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 0.3768823454865033, | |
| "grad_norm": 1.8127686977386475, | |
| "learning_rate": 0.00013990801827879574, | |
| "loss": 4.5103, | |
| "num_input_tokens_seen": 199877440, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 0.3785353382298652, | |
| "grad_norm": 1.792159080505371, | |
| "learning_rate": 0.00013981985688467022, | |
| "loss": 4.5139, | |
| "num_input_tokens_seen": 200738880, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 0.380188330973227, | |
| "grad_norm": 1.7812391519546509, | |
| "learning_rate": 0.0001397322832331722, | |
| "loss": 4.5151, | |
| "num_input_tokens_seen": 201618880, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.3818413237165889, | |
| "grad_norm": 1.8573509454727173, | |
| "learning_rate": 0.00013964412183904668, | |
| "loss": 4.5113, | |
| "num_input_tokens_seen": 202481888, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 0.38349431645995075, | |
| "grad_norm": 1.9190624952316284, | |
| "learning_rate": 0.0001395559604449212, | |
| "loss": 4.5118, | |
| "num_input_tokens_seen": 203344320, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.3851473092033126, | |
| "grad_norm": 1.8508821725845337, | |
| "learning_rate": 0.00013946779905079566, | |
| "loss": 4.5152, | |
| "num_input_tokens_seen": 204227936, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 0.3868003019466745, | |
| "grad_norm": 1.8276251554489136, | |
| "learning_rate": 0.00013937963765667016, | |
| "loss": 4.5182, | |
| "num_input_tokens_seen": 205119008, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 0.3884532946900363, | |
| "grad_norm": 1.773224949836731, | |
| "learning_rate": 0.00013929147626254464, | |
| "loss": 4.5091, | |
| "num_input_tokens_seen": 205989696, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 0.39010628743339815, | |
| "grad_norm": 1.889553189277649, | |
| "learning_rate": 0.00013920331486841914, | |
| "loss": 4.5111, | |
| "num_input_tokens_seen": 206865088, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 0.39175928017676004, | |
| "grad_norm": 1.844975233078003, | |
| "learning_rate": 0.00013911515347429362, | |
| "loss": 4.4982, | |
| "num_input_tokens_seen": 207738880, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 0.3934122729201219, | |
| "grad_norm": 1.8811978101730347, | |
| "learning_rate": 0.0001390269920801681, | |
| "loss": 4.5168, | |
| "num_input_tokens_seen": 208626688, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 0.3950652656634837, | |
| "grad_norm": 1.8564339876174927, | |
| "learning_rate": 0.0001389388306860426, | |
| "loss": 4.5122, | |
| "num_input_tokens_seen": 209484800, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 0.3967182584068456, | |
| "grad_norm": 1.8316396474838257, | |
| "learning_rate": 0.00013885066929191707, | |
| "loss": 4.5046, | |
| "num_input_tokens_seen": 210369792, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.39837125115020744, | |
| "grad_norm": 1.925075650215149, | |
| "learning_rate": 0.00013876250789779157, | |
| "loss": 4.5116, | |
| "num_input_tokens_seen": 211250176, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 0.40002424389356933, | |
| "grad_norm": 1.860660195350647, | |
| "learning_rate": 0.00013867434650366605, | |
| "loss": 4.4998, | |
| "num_input_tokens_seen": 212136000, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 0.40167723663693117, | |
| "grad_norm": 1.8505064249038696, | |
| "learning_rate": 0.00013858618510954055, | |
| "loss": 4.5124, | |
| "num_input_tokens_seen": 213009056, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 0.403330229380293, | |
| "grad_norm": 1.8910654783248901, | |
| "learning_rate": 0.00013849802371541502, | |
| "loss": 4.4966, | |
| "num_input_tokens_seen": 213871744, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 0.4049832221236549, | |
| "grad_norm": 1.883748173713684, | |
| "learning_rate": 0.0001384098623212895, | |
| "loss": 4.5074, | |
| "num_input_tokens_seen": 214739520, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 0.40663621486701673, | |
| "grad_norm": 1.8115665912628174, | |
| "learning_rate": 0.000138321700927164, | |
| "loss": 4.5187, | |
| "num_input_tokens_seen": 215629472, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 0.40828920761037857, | |
| "grad_norm": 1.9036102294921875, | |
| "learning_rate": 0.000138234127275666, | |
| "loss": 4.4892, | |
| "num_input_tokens_seen": 216497184, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 0.40994220035374046, | |
| "grad_norm": 1.8916597366333008, | |
| "learning_rate": 0.0001381459658815405, | |
| "loss": 4.5019, | |
| "num_input_tokens_seen": 217381152, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 0.4115951930971023, | |
| "grad_norm": 1.8847101926803589, | |
| "learning_rate": 0.00013805780448741497, | |
| "loss": 4.5064, | |
| "num_input_tokens_seen": 218251456, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 0.41324818584046413, | |
| "grad_norm": 1.730322241783142, | |
| "learning_rate": 0.00013796964309328947, | |
| "loss": 4.4988, | |
| "num_input_tokens_seen": 219141056, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.414901178583826, | |
| "grad_norm": 1.833764672279358, | |
| "learning_rate": 0.00013788148169916395, | |
| "loss": 4.5155, | |
| "num_input_tokens_seen": 220036992, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 0.41655417132718786, | |
| "grad_norm": 1.8188276290893555, | |
| "learning_rate": 0.00013779332030503845, | |
| "loss": 4.4984, | |
| "num_input_tokens_seen": 220910208, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 0.41820716407054975, | |
| "grad_norm": 1.7197022438049316, | |
| "learning_rate": 0.00013770515891091292, | |
| "loss": 4.5018, | |
| "num_input_tokens_seen": 221803520, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 0.4198601568139116, | |
| "grad_norm": 1.879470944404602, | |
| "learning_rate": 0.00013761699751678742, | |
| "loss": 4.497, | |
| "num_input_tokens_seen": 222679392, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 0.4215131495572734, | |
| "grad_norm": 1.716430902481079, | |
| "learning_rate": 0.0001375288361226619, | |
| "loss": 4.4979, | |
| "num_input_tokens_seen": 223568224, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 0.4231661423006353, | |
| "grad_norm": 1.8879536390304565, | |
| "learning_rate": 0.0001374406747285364, | |
| "loss": 4.4972, | |
| "num_input_tokens_seen": 224460192, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 0.42481913504399715, | |
| "grad_norm": 1.9361037015914917, | |
| "learning_rate": 0.00013735251333441088, | |
| "loss": 4.4968, | |
| "num_input_tokens_seen": 225318816, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 0.426472127787359, | |
| "grad_norm": 1.8587005138397217, | |
| "learning_rate": 0.00013726435194028535, | |
| "loss": 4.4982, | |
| "num_input_tokens_seen": 226176704, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 0.4281251205307209, | |
| "grad_norm": 1.8819633722305298, | |
| "learning_rate": 0.00013717619054615985, | |
| "loss": 4.4929, | |
| "num_input_tokens_seen": 227049984, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 0.4297781132740827, | |
| "grad_norm": 1.8268516063690186, | |
| "learning_rate": 0.00013708802915203433, | |
| "loss": 4.5063, | |
| "num_input_tokens_seen": 227926784, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.4314311060174446, | |
| "grad_norm": 1.8819466829299927, | |
| "learning_rate": 0.00013699986775790883, | |
| "loss": 4.5024, | |
| "num_input_tokens_seen": 228823584, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 0.43308409876080645, | |
| "grad_norm": 1.8801319599151611, | |
| "learning_rate": 0.0001369117063637833, | |
| "loss": 4.5043, | |
| "num_input_tokens_seen": 229691904, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 0.4347370915041683, | |
| "grad_norm": 1.8677760362625122, | |
| "learning_rate": 0.0001368241327122853, | |
| "loss": 4.5102, | |
| "num_input_tokens_seen": 230569056, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 0.4363900842475302, | |
| "grad_norm": 1.8280800580978394, | |
| "learning_rate": 0.0001367359713181598, | |
| "loss": 4.5014, | |
| "num_input_tokens_seen": 231437792, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 0.438043076990892, | |
| "grad_norm": 1.7932913303375244, | |
| "learning_rate": 0.00013664780992403427, | |
| "loss": 4.5082, | |
| "num_input_tokens_seen": 232310848, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 0.43969606973425385, | |
| "grad_norm": 1.7872642278671265, | |
| "learning_rate": 0.00013655964852990878, | |
| "loss": 4.5091, | |
| "num_input_tokens_seen": 233190464, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 0.44134906247761574, | |
| "grad_norm": 1.9207595586776733, | |
| "learning_rate": 0.00013647148713578325, | |
| "loss": 4.4932, | |
| "num_input_tokens_seen": 234064256, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 0.4430020552209776, | |
| "grad_norm": 1.9176338911056519, | |
| "learning_rate": 0.00013638332574165773, | |
| "loss": 4.4982, | |
| "num_input_tokens_seen": 234931104, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 0.4446550479643394, | |
| "grad_norm": 1.839328646659851, | |
| "learning_rate": 0.00013629516434753223, | |
| "loss": 4.5, | |
| "num_input_tokens_seen": 235790176, | |
| "step": 40350 | |
| }, | |
| { | |
| "epoch": 0.4463080407077013, | |
| "grad_norm": 1.8120410442352295, | |
| "learning_rate": 0.0001362070029534067, | |
| "loss": 4.4866, | |
| "num_input_tokens_seen": 236663488, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.44796103345106314, | |
| "grad_norm": 1.7365509271621704, | |
| "learning_rate": 0.0001361188415592812, | |
| "loss": 4.484, | |
| "num_input_tokens_seen": 237550016, | |
| "step": 40650 | |
| }, | |
| { | |
| "epoch": 0.44961402619442503, | |
| "grad_norm": 1.8573724031448364, | |
| "learning_rate": 0.00013603068016515568, | |
| "loss": 4.4949, | |
| "num_input_tokens_seen": 238428800, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 0.45126701893778687, | |
| "grad_norm": 1.8714196681976318, | |
| "learning_rate": 0.00013594251877103018, | |
| "loss": 4.4861, | |
| "num_input_tokens_seen": 239301216, | |
| "step": 40950 | |
| }, | |
| { | |
| "epoch": 0.4529200116811487, | |
| "grad_norm": 1.813636064529419, | |
| "learning_rate": 0.00013585435737690466, | |
| "loss": 4.4939, | |
| "num_input_tokens_seen": 240172352, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 0.4545730044245106, | |
| "grad_norm": 1.7828494310379028, | |
| "learning_rate": 0.00013576619598277913, | |
| "loss": 4.5073, | |
| "num_input_tokens_seen": 241058368, | |
| "step": 41250 | |
| }, | |
| { | |
| "epoch": 0.45622599716787243, | |
| "grad_norm": 1.9278478622436523, | |
| "learning_rate": 0.00013567803458865363, | |
| "loss": 4.4831, | |
| "num_input_tokens_seen": 241944320, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 0.45787898991123427, | |
| "grad_norm": 1.8244856595993042, | |
| "learning_rate": 0.0001355898731945281, | |
| "loss": 4.4889, | |
| "num_input_tokens_seen": 242827808, | |
| "step": 41550 | |
| }, | |
| { | |
| "epoch": 0.45953198265459616, | |
| "grad_norm": 1.9578852653503418, | |
| "learning_rate": 0.0001355017118004026, | |
| "loss": 4.4938, | |
| "num_input_tokens_seen": 243697248, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 0.461184975397958, | |
| "grad_norm": 1.8681639432907104, | |
| "learning_rate": 0.0001354135504062771, | |
| "loss": 4.493, | |
| "num_input_tokens_seen": 244549632, | |
| "step": 41850 | |
| }, | |
| { | |
| "epoch": 0.46283796814131983, | |
| "grad_norm": 1.9330469369888306, | |
| "learning_rate": 0.0001353253890121516, | |
| "loss": 4.4823, | |
| "num_input_tokens_seen": 245429600, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.4644909608846817, | |
| "grad_norm": 1.775819182395935, | |
| "learning_rate": 0.00013523722761802606, | |
| "loss": 4.4887, | |
| "num_input_tokens_seen": 246307872, | |
| "step": 42150 | |
| }, | |
| { | |
| "epoch": 0.46614395362804356, | |
| "grad_norm": 1.9359744787216187, | |
| "learning_rate": 0.00013514906622390057, | |
| "loss": 4.4813, | |
| "num_input_tokens_seen": 247194432, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 0.46779694637140545, | |
| "grad_norm": 1.8034732341766357, | |
| "learning_rate": 0.00013506090482977504, | |
| "loss": 4.4957, | |
| "num_input_tokens_seen": 248049248, | |
| "step": 42450 | |
| }, | |
| { | |
| "epoch": 0.4694499391147673, | |
| "grad_norm": 1.8069413900375366, | |
| "learning_rate": 0.00013497274343564954, | |
| "loss": 4.484, | |
| "num_input_tokens_seen": 248930624, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 0.4711029318581291, | |
| "grad_norm": 1.8796617984771729, | |
| "learning_rate": 0.00013488458204152402, | |
| "loss": 4.4887, | |
| "num_input_tokens_seen": 249808512, | |
| "step": 42750 | |
| }, | |
| { | |
| "epoch": 0.472755924601491, | |
| "grad_norm": 1.8367630243301392, | |
| "learning_rate": 0.00013479642064739852, | |
| "loss": 4.4779, | |
| "num_input_tokens_seen": 250669088, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 0.47440891734485285, | |
| "grad_norm": 1.9085215330123901, | |
| "learning_rate": 0.0001347088469959005, | |
| "loss": 4.489, | |
| "num_input_tokens_seen": 251553792, | |
| "step": 43050 | |
| }, | |
| { | |
| "epoch": 0.4760619100882147, | |
| "grad_norm": 1.8323450088500977, | |
| "learning_rate": 0.000134620685601775, | |
| "loss": 4.482, | |
| "num_input_tokens_seen": 252440032, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 0.4777149028315766, | |
| "grad_norm": 2.1364452838897705, | |
| "learning_rate": 0.0001345325242076495, | |
| "loss": 4.4873, | |
| "num_input_tokens_seen": 253320576, | |
| "step": 43350 | |
| }, | |
| { | |
| "epoch": 0.4793678955749384, | |
| "grad_norm": 1.8431365489959717, | |
| "learning_rate": 0.00013444436281352396, | |
| "loss": 4.4844, | |
| "num_input_tokens_seen": 254203552, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.4810208883183003, | |
| "grad_norm": 1.853715419769287, | |
| "learning_rate": 0.00013435620141939847, | |
| "loss": 4.4905, | |
| "num_input_tokens_seen": 255078656, | |
| "step": 43650 | |
| }, | |
| { | |
| "epoch": 0.48267388106166215, | |
| "grad_norm": 2.0351803302764893, | |
| "learning_rate": 0.00013426804002527294, | |
| "loss": 4.4854, | |
| "num_input_tokens_seen": 255961792, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 0.484326873805024, | |
| "grad_norm": 1.867595911026001, | |
| "learning_rate": 0.00013417987863114744, | |
| "loss": 4.4734, | |
| "num_input_tokens_seen": 256823744, | |
| "step": 43950 | |
| }, | |
| { | |
| "epoch": 0.4859798665483859, | |
| "grad_norm": 1.9231115579605103, | |
| "learning_rate": 0.00013409171723702192, | |
| "loss": 4.4982, | |
| "num_input_tokens_seen": 257687488, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 0.4876328592917477, | |
| "grad_norm": 1.9620647430419922, | |
| "learning_rate": 0.00013400355584289642, | |
| "loss": 4.4815, | |
| "num_input_tokens_seen": 258561568, | |
| "step": 44250 | |
| }, | |
| { | |
| "epoch": 0.48928585203510955, | |
| "grad_norm": 1.741739273071289, | |
| "learning_rate": 0.0001339153944487709, | |
| "loss": 4.4863, | |
| "num_input_tokens_seen": 259449344, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 0.49093884477847144, | |
| "grad_norm": 1.9869145154953003, | |
| "learning_rate": 0.0001338272330546454, | |
| "loss": 4.48, | |
| "num_input_tokens_seen": 260317888, | |
| "step": 44550 | |
| }, | |
| { | |
| "epoch": 0.4925918375218333, | |
| "grad_norm": 1.9364657402038574, | |
| "learning_rate": 0.00013373907166051987, | |
| "loss": 4.477, | |
| "num_input_tokens_seen": 261198656, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 0.4942448302651951, | |
| "grad_norm": 1.946509599685669, | |
| "learning_rate": 0.00013365091026639437, | |
| "loss": 4.4762, | |
| "num_input_tokens_seen": 262082432, | |
| "step": 44850 | |
| }, | |
| { | |
| "epoch": 0.495897823008557, | |
| "grad_norm": 1.7882816791534424, | |
| "learning_rate": 0.00013356274887226885, | |
| "loss": 4.478, | |
| "num_input_tokens_seen": 262961504, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.49755081575191884, | |
| "grad_norm": 1.8857409954071045, | |
| "learning_rate": 0.00013347458747814332, | |
| "loss": 4.48, | |
| "num_input_tokens_seen": 263810336, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 0.49920380849528073, | |
| "grad_norm": 1.8983428478240967, | |
| "learning_rate": 0.00013338642608401783, | |
| "loss": 4.4792, | |
| "num_input_tokens_seen": 264684512, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 0.5008568012386425, | |
| "grad_norm": 1.8649096488952637, | |
| "learning_rate": 0.0001332982646898923, | |
| "loss": 4.473, | |
| "num_input_tokens_seen": 265553056, | |
| "step": 45450 | |
| }, | |
| { | |
| "epoch": 0.5025097939820045, | |
| "grad_norm": 1.8233070373535156, | |
| "learning_rate": 0.0001332101032957668, | |
| "loss": 4.4854, | |
| "num_input_tokens_seen": 266438976, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 0.5041627867253663, | |
| "grad_norm": 1.8780871629714966, | |
| "learning_rate": 0.00013312194190164128, | |
| "loss": 4.4806, | |
| "num_input_tokens_seen": 267305760, | |
| "step": 45750 | |
| }, | |
| { | |
| "epoch": 0.5058157794687281, | |
| "grad_norm": 1.9368178844451904, | |
| "learning_rate": 0.00013303378050751578, | |
| "loss": 4.4805, | |
| "num_input_tokens_seen": 268185792, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 0.50746877221209, | |
| "grad_norm": 1.8207215070724487, | |
| "learning_rate": 0.00013294561911339026, | |
| "loss": 4.4839, | |
| "num_input_tokens_seen": 269074432, | |
| "step": 46050 | |
| }, | |
| { | |
| "epoch": 0.5091217649554518, | |
| "grad_norm": 1.9221956729888916, | |
| "learning_rate": 0.00013285745771926473, | |
| "loss": 4.4724, | |
| "num_input_tokens_seen": 269945728, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 0.5107747576988138, | |
| "grad_norm": 1.8592416048049927, | |
| "learning_rate": 0.00013276929632513923, | |
| "loss": 4.4801, | |
| "num_input_tokens_seen": 270826912, | |
| "step": 46350 | |
| }, | |
| { | |
| "epoch": 0.5124277504421756, | |
| "grad_norm": 1.8793606758117676, | |
| "learning_rate": 0.0001326811349310137, | |
| "loss": 4.4832, | |
| "num_input_tokens_seen": 271696640, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.5140807431855374, | |
| "grad_norm": 1.9293113946914673, | |
| "learning_rate": 0.0001325929735368882, | |
| "loss": 4.4703, | |
| "num_input_tokens_seen": 272577280, | |
| "step": 46650 | |
| }, | |
| { | |
| "epoch": 0.5157337359288993, | |
| "grad_norm": 1.8582684993743896, | |
| "learning_rate": 0.00013250481214276269, | |
| "loss": 4.4785, | |
| "num_input_tokens_seen": 273448128, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 0.5173867286722611, | |
| "grad_norm": 1.8803818225860596, | |
| "learning_rate": 0.0001324166507486372, | |
| "loss": 4.4851, | |
| "num_input_tokens_seen": 274313472, | |
| "step": 46950 | |
| }, | |
| { | |
| "epoch": 0.5190397214156229, | |
| "grad_norm": 1.989717721939087, | |
| "learning_rate": 0.00013232907709713918, | |
| "loss": 4.4814, | |
| "num_input_tokens_seen": 275168416, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 0.5206927141589849, | |
| "grad_norm": 1.9770921468734741, | |
| "learning_rate": 0.00013224091570301365, | |
| "loss": 4.4825, | |
| "num_input_tokens_seen": 276035776, | |
| "step": 47250 | |
| }, | |
| { | |
| "epoch": 0.5223457069023467, | |
| "grad_norm": 1.8764408826828003, | |
| "learning_rate": 0.00013215275430888816, | |
| "loss": 4.4788, | |
| "num_input_tokens_seen": 276909952, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 0.5239986996457086, | |
| "grad_norm": 1.860009789466858, | |
| "learning_rate": 0.00013206459291476263, | |
| "loss": 4.4834, | |
| "num_input_tokens_seen": 277795232, | |
| "step": 47550 | |
| }, | |
| { | |
| "epoch": 0.5256516923890704, | |
| "grad_norm": 1.949278473854065, | |
| "learning_rate": 0.00013197643152063713, | |
| "loss": 4.4752, | |
| "num_input_tokens_seen": 278690720, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 0.5273046851324322, | |
| "grad_norm": 1.868780255317688, | |
| "learning_rate": 0.0001318882701265116, | |
| "loss": 4.4797, | |
| "num_input_tokens_seen": 279567232, | |
| "step": 47850 | |
| }, | |
| { | |
| "epoch": 0.5289576778757942, | |
| "grad_norm": 1.7434320449829102, | |
| "learning_rate": 0.0001318001087323861, | |
| "loss": 4.4726, | |
| "num_input_tokens_seen": 280424832, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.530610670619156, | |
| "grad_norm": 1.8644661903381348, | |
| "learning_rate": 0.00013171194733826059, | |
| "loss": 4.4648, | |
| "num_input_tokens_seen": 281294752, | |
| "step": 48150 | |
| }, | |
| { | |
| "epoch": 0.5322636633625178, | |
| "grad_norm": 1.9029775857925415, | |
| "learning_rate": 0.00013162378594413506, | |
| "loss": 4.4791, | |
| "num_input_tokens_seen": 282156544, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 0.5339166561058797, | |
| "grad_norm": 1.7862669229507446, | |
| "learning_rate": 0.00013153562455000956, | |
| "loss": 4.4688, | |
| "num_input_tokens_seen": 283033248, | |
| "step": 48450 | |
| }, | |
| { | |
| "epoch": 0.5355696488492415, | |
| "grad_norm": 1.7603411674499512, | |
| "learning_rate": 0.00013144746315588404, | |
| "loss": 4.4807, | |
| "num_input_tokens_seen": 283922048, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 0.5372226415926034, | |
| "grad_norm": 1.868235468864441, | |
| "learning_rate": 0.00013135930176175854, | |
| "loss": 4.4702, | |
| "num_input_tokens_seen": 284800416, | |
| "step": 48750 | |
| }, | |
| { | |
| "epoch": 0.5388756343359653, | |
| "grad_norm": 1.864640474319458, | |
| "learning_rate": 0.00013127114036763301, | |
| "loss": 4.479, | |
| "num_input_tokens_seen": 285673888, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 0.5405286270793271, | |
| "grad_norm": 1.7705098390579224, | |
| "learning_rate": 0.00013118297897350752, | |
| "loss": 4.4782, | |
| "num_input_tokens_seen": 286553856, | |
| "step": 49050 | |
| }, | |
| { | |
| "epoch": 0.542181619822689, | |
| "grad_norm": 1.9763901233673096, | |
| "learning_rate": 0.000131094817579382, | |
| "loss": 4.4654, | |
| "num_input_tokens_seen": 287436736, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 0.5438346125660508, | |
| "grad_norm": 1.905661702156067, | |
| "learning_rate": 0.0001310066561852565, | |
| "loss": 4.4718, | |
| "num_input_tokens_seen": 288306976, | |
| "step": 49350 | |
| }, | |
| { | |
| "epoch": 0.5454876053094126, | |
| "grad_norm": 1.8861178159713745, | |
| "learning_rate": 0.00013091849479113097, | |
| "loss": 4.4618, | |
| "num_input_tokens_seen": 289176352, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.5471405980527746, | |
| "grad_norm": 1.8697651624679565, | |
| "learning_rate": 0.00013083033339700547, | |
| "loss": 4.4725, | |
| "num_input_tokens_seen": 290061760, | |
| "step": 49650 | |
| }, | |
| { | |
| "epoch": 0.5487935907961364, | |
| "grad_norm": 1.8051494359970093, | |
| "learning_rate": 0.00013074217200287995, | |
| "loss": 4.459, | |
| "num_input_tokens_seen": 290924640, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 0.5504465835394983, | |
| "grad_norm": 1.7766984701156616, | |
| "learning_rate": 0.00013065401060875445, | |
| "loss": 4.4729, | |
| "num_input_tokens_seen": 291801280, | |
| "step": 49950 | |
| }, | |
| { | |
| "epoch": 0.5520995762828601, | |
| "grad_norm": 1.7969352006912231, | |
| "learning_rate": 0.00013056584921462892, | |
| "loss": 4.4789, | |
| "num_input_tokens_seen": 292673632, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 0.5537525690262219, | |
| "grad_norm": 1.8939694166183472, | |
| "learning_rate": 0.00013047768782050343, | |
| "loss": 4.4674, | |
| "num_input_tokens_seen": 293542176, | |
| "step": 50250 | |
| }, | |
| { | |
| "epoch": 0.5554055617695838, | |
| "grad_norm": 1.8721749782562256, | |
| "learning_rate": 0.0001303895264263779, | |
| "loss": 4.4591, | |
| "num_input_tokens_seen": 294415424, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 0.5570585545129457, | |
| "grad_norm": 1.7810068130493164, | |
| "learning_rate": 0.0001303013650322524, | |
| "loss": 4.475, | |
| "num_input_tokens_seen": 295292384, | |
| "step": 50550 | |
| }, | |
| { | |
| "epoch": 0.5587115472563076, | |
| "grad_norm": 1.8184670209884644, | |
| "learning_rate": 0.00013021320363812688, | |
| "loss": 4.473, | |
| "num_input_tokens_seen": 296168640, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 0.5603645399996694, | |
| "grad_norm": 1.8167736530303955, | |
| "learning_rate": 0.00013012504224400138, | |
| "loss": 4.4604, | |
| "num_input_tokens_seen": 297035904, | |
| "step": 50850 | |
| }, | |
| { | |
| "epoch": 0.5620175327430312, | |
| "grad_norm": 1.902001142501831, | |
| "learning_rate": 0.00013003688084987585, | |
| "loss": 4.4653, | |
| "num_input_tokens_seen": 297893248, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.5636705254863931, | |
| "grad_norm": 1.7989624738693237, | |
| "learning_rate": 0.00012994930719837785, | |
| "loss": 4.4581, | |
| "num_input_tokens_seen": 298773088, | |
| "step": 51150 | |
| }, | |
| { | |
| "epoch": 0.565323518229755, | |
| "grad_norm": 1.9608672857284546, | |
| "learning_rate": 0.00012986114580425232, | |
| "loss": 4.4553, | |
| "num_input_tokens_seen": 299639712, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 0.5669765109731169, | |
| "grad_norm": 1.8063366413116455, | |
| "learning_rate": 0.00012977298441012682, | |
| "loss": 4.4748, | |
| "num_input_tokens_seen": 300504576, | |
| "step": 51450 | |
| }, | |
| { | |
| "epoch": 0.5686295037164787, | |
| "grad_norm": 1.7892522811889648, | |
| "learning_rate": 0.0001296848230160013, | |
| "loss": 4.4759, | |
| "num_input_tokens_seen": 301381600, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 0.5702824964598405, | |
| "grad_norm": 1.9009445905685425, | |
| "learning_rate": 0.00012959666162187577, | |
| "loss": 4.4643, | |
| "num_input_tokens_seen": 302264064, | |
| "step": 51750 | |
| }, | |
| { | |
| "epoch": 0.5719354892032024, | |
| "grad_norm": 1.8855173587799072, | |
| "learning_rate": 0.00012950850022775027, | |
| "loss": 4.4569, | |
| "num_input_tokens_seen": 303131648, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 0.5735884819465642, | |
| "grad_norm": 1.8198268413543701, | |
| "learning_rate": 0.00012942033883362475, | |
| "loss": 4.465, | |
| "num_input_tokens_seen": 304010848, | |
| "step": 52050 | |
| }, | |
| { | |
| "epoch": 0.5752414746899261, | |
| "grad_norm": 1.8278980255126953, | |
| "learning_rate": 0.00012933217743949925, | |
| "loss": 4.4674, | |
| "num_input_tokens_seen": 304901952, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 0.576894467433288, | |
| "grad_norm": 1.8281151056289673, | |
| "learning_rate": 0.00012924401604537373, | |
| "loss": 4.4718, | |
| "num_input_tokens_seen": 305763424, | |
| "step": 52350 | |
| }, | |
| { | |
| "epoch": 0.5785474601766498, | |
| "grad_norm": 1.8816980123519897, | |
| "learning_rate": 0.00012915585465124823, | |
| "loss": 4.4726, | |
| "num_input_tokens_seen": 306641856, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.5802004529200117, | |
| "grad_norm": 1.8755218982696533, | |
| "learning_rate": 0.0001290676932571227, | |
| "loss": 4.4744, | |
| "num_input_tokens_seen": 307520288, | |
| "step": 52650 | |
| }, | |
| { | |
| "epoch": 0.5818534456633735, | |
| "grad_norm": 1.8329659700393677, | |
| "learning_rate": 0.0001289795318629972, | |
| "loss": 4.4572, | |
| "num_input_tokens_seen": 308410624, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 0.5835064384067354, | |
| "grad_norm": 1.9654128551483154, | |
| "learning_rate": 0.00012889137046887168, | |
| "loss": 4.4671, | |
| "num_input_tokens_seen": 309288736, | |
| "step": 52950 | |
| }, | |
| { | |
| "epoch": 0.5851594311500973, | |
| "grad_norm": 1.8310860395431519, | |
| "learning_rate": 0.00012880320907474618, | |
| "loss": 4.4684, | |
| "num_input_tokens_seen": 310165440, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 0.5868124238934591, | |
| "grad_norm": 1.8104560375213623, | |
| "learning_rate": 0.00012871563542324817, | |
| "loss": 4.4546, | |
| "num_input_tokens_seen": 311044352, | |
| "step": 53250 | |
| }, | |
| { | |
| "epoch": 0.588465416636821, | |
| "grad_norm": 1.8414585590362549, | |
| "learning_rate": 0.00012862747402912265, | |
| "loss": 4.4625, | |
| "num_input_tokens_seen": 311919424, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 0.5901184093801828, | |
| "grad_norm": 1.724381685256958, | |
| "learning_rate": 0.00012853931263499715, | |
| "loss": 4.4632, | |
| "num_input_tokens_seen": 312803712, | |
| "step": 53550 | |
| }, | |
| { | |
| "epoch": 0.5917714021235447, | |
| "grad_norm": 1.7701301574707031, | |
| "learning_rate": 0.00012845115124087163, | |
| "loss": 4.4609, | |
| "num_input_tokens_seen": 313672800, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 0.5934243948669066, | |
| "grad_norm": 1.8755768537521362, | |
| "learning_rate": 0.00012836298984674613, | |
| "loss": 4.461, | |
| "num_input_tokens_seen": 314543776, | |
| "step": 53850 | |
| }, | |
| { | |
| "epoch": 0.5950773876102684, | |
| "grad_norm": 1.8842816352844238, | |
| "learning_rate": 0.0001282748284526206, | |
| "loss": 4.462, | |
| "num_input_tokens_seen": 315413216, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.5967303803536302, | |
| "grad_norm": 1.8173580169677734, | |
| "learning_rate": 0.0001281866670584951, | |
| "loss": 4.4595, | |
| "num_input_tokens_seen": 316286592, | |
| "step": 54150 | |
| }, | |
| { | |
| "epoch": 0.5983833730969921, | |
| "grad_norm": 1.8613582849502563, | |
| "learning_rate": 0.00012809850566436958, | |
| "loss": 4.4729, | |
| "num_input_tokens_seen": 317171968, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 0.6000363658403539, | |
| "grad_norm": 1.8345390558242798, | |
| "learning_rate": 0.00012801034427024408, | |
| "loss": 4.4558, | |
| "num_input_tokens_seen": 318069504, | |
| "step": 54450 | |
| }, | |
| { | |
| "epoch": 0.6016893585837159, | |
| "grad_norm": 1.9001188278198242, | |
| "learning_rate": 0.00012792218287611856, | |
| "loss": 4.4493, | |
| "num_input_tokens_seen": 318929088, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 0.6033423513270777, | |
| "grad_norm": 1.7820019721984863, | |
| "learning_rate": 0.00012783402148199306, | |
| "loss": 4.4529, | |
| "num_input_tokens_seen": 319802400, | |
| "step": 54750 | |
| }, | |
| { | |
| "epoch": 0.6049953440704395, | |
| "grad_norm": 1.8836514949798584, | |
| "learning_rate": 0.00012774586008786754, | |
| "loss": 4.4601, | |
| "num_input_tokens_seen": 320667168, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 0.6066483368138014, | |
| "grad_norm": 1.820078730583191, | |
| "learning_rate": 0.00012765828643636953, | |
| "loss": 4.4583, | |
| "num_input_tokens_seen": 321544160, | |
| "step": 55050 | |
| }, | |
| { | |
| "epoch": 0.6083013295571632, | |
| "grad_norm": 1.7549668550491333, | |
| "learning_rate": 0.000127570125042244, | |
| "loss": 4.4507, | |
| "num_input_tokens_seen": 322413504, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 0.6099543223005252, | |
| "grad_norm": 1.819643497467041, | |
| "learning_rate": 0.0001274819636481185, | |
| "loss": 4.4572, | |
| "num_input_tokens_seen": 323301120, | |
| "step": 55350 | |
| }, | |
| { | |
| "epoch": 0.611607315043887, | |
| "grad_norm": 1.8832948207855225, | |
| "learning_rate": 0.00012739380225399298, | |
| "loss": 4.4499, | |
| "num_input_tokens_seen": 324179040, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.6132603077872488, | |
| "grad_norm": 1.9329428672790527, | |
| "learning_rate": 0.00012730564085986748, | |
| "loss": 4.4598, | |
| "num_input_tokens_seen": 325044704, | |
| "step": 55650 | |
| }, | |
| { | |
| "epoch": 0.6149133005306107, | |
| "grad_norm": 1.8368948698043823, | |
| "learning_rate": 0.00012721747946574196, | |
| "loss": 4.4636, | |
| "num_input_tokens_seen": 325903360, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 0.6165662932739725, | |
| "grad_norm": 1.8610767126083374, | |
| "learning_rate": 0.00012712931807161646, | |
| "loss": 4.4602, | |
| "num_input_tokens_seen": 326791648, | |
| "step": 55950 | |
| }, | |
| { | |
| "epoch": 0.6182192860173343, | |
| "grad_norm": 1.853129506111145, | |
| "learning_rate": 0.00012704115667749093, | |
| "loss": 4.4581, | |
| "num_input_tokens_seen": 327669216, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 0.6198722787606963, | |
| "grad_norm": 1.8630894422531128, | |
| "learning_rate": 0.0001269529952833654, | |
| "loss": 4.4584, | |
| "num_input_tokens_seen": 328547424, | |
| "step": 56250 | |
| }, | |
| { | |
| "epoch": 0.6215252715040581, | |
| "grad_norm": 1.8581258058547974, | |
| "learning_rate": 0.0001268648338892399, | |
| "loss": 4.4632, | |
| "num_input_tokens_seen": 329414400, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 0.62317826424742, | |
| "grad_norm": 1.8294817209243774, | |
| "learning_rate": 0.00012677667249511439, | |
| "loss": 4.4634, | |
| "num_input_tokens_seen": 330297376, | |
| "step": 56550 | |
| }, | |
| { | |
| "epoch": 0.6248312569907818, | |
| "grad_norm": 1.9625203609466553, | |
| "learning_rate": 0.0001266885111009889, | |
| "loss": 4.4598, | |
| "num_input_tokens_seen": 331181792, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 0.6264842497341436, | |
| "grad_norm": 1.821718454360962, | |
| "learning_rate": 0.00012660034970686336, | |
| "loss": 4.4549, | |
| "num_input_tokens_seen": 332056416, | |
| "step": 56850 | |
| }, | |
| { | |
| "epoch": 0.6281372424775056, | |
| "grad_norm": 1.8366010189056396, | |
| "learning_rate": 0.00012651218831273786, | |
| "loss": 4.4418, | |
| "num_input_tokens_seen": 332908864, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.6297902352208674, | |
| "grad_norm": 1.858789086341858, | |
| "learning_rate": 0.00012642402691861234, | |
| "loss": 4.4592, | |
| "num_input_tokens_seen": 333791520, | |
| "step": 57150 | |
| }, | |
| { | |
| "epoch": 0.6314432279642292, | |
| "grad_norm": 1.9188382625579834, | |
| "learning_rate": 0.00012633586552448684, | |
| "loss": 4.4531, | |
| "num_input_tokens_seen": 334675488, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 0.6330962207075911, | |
| "grad_norm": 1.8480638265609741, | |
| "learning_rate": 0.00012624770413036132, | |
| "loss": 4.4557, | |
| "num_input_tokens_seen": 335569664, | |
| "step": 57450 | |
| }, | |
| { | |
| "epoch": 0.6347492134509529, | |
| "grad_norm": 1.8409630060195923, | |
| "learning_rate": 0.00012615954273623582, | |
| "loss": 4.454, | |
| "num_input_tokens_seen": 336438752, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 0.6364022061943148, | |
| "grad_norm": 1.7734564542770386, | |
| "learning_rate": 0.0001260713813421103, | |
| "loss": 4.4587, | |
| "num_input_tokens_seen": 337318464, | |
| "step": 57750 | |
| }, | |
| { | |
| "epoch": 0.6380551989376767, | |
| "grad_norm": 1.8258734941482544, | |
| "learning_rate": 0.0001259832199479848, | |
| "loss": 4.4501, | |
| "num_input_tokens_seen": 338196416, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 0.6397081916810385, | |
| "grad_norm": 1.8730100393295288, | |
| "learning_rate": 0.00012589505855385927, | |
| "loss": 4.4508, | |
| "num_input_tokens_seen": 339066272, | |
| "step": 58050 | |
| }, | |
| { | |
| "epoch": 0.6413611844244004, | |
| "grad_norm": 1.7968626022338867, | |
| "learning_rate": 0.00012580689715973375, | |
| "loss": 4.4465, | |
| "num_input_tokens_seen": 339940576, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 0.6430141771677622, | |
| "grad_norm": 1.8305721282958984, | |
| "learning_rate": 0.00012571873576560825, | |
| "loss": 4.4452, | |
| "num_input_tokens_seen": 340827872, | |
| "step": 58350 | |
| }, | |
| { | |
| "epoch": 0.644667169911124, | |
| "grad_norm": 1.8106398582458496, | |
| "learning_rate": 0.00012563057437148272, | |
| "loss": 4.4436, | |
| "num_input_tokens_seen": 341710720, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.646320162654486, | |
| "grad_norm": 1.8428856134414673, | |
| "learning_rate": 0.00012554300071998474, | |
| "loss": 4.4607, | |
| "num_input_tokens_seen": 342592992, | |
| "step": 58650 | |
| }, | |
| { | |
| "epoch": 0.6479731553978478, | |
| "grad_norm": 1.89970064163208, | |
| "learning_rate": 0.00012545483932585922, | |
| "loss": 4.446, | |
| "num_input_tokens_seen": 343458496, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 0.6496261481412097, | |
| "grad_norm": 1.887024998664856, | |
| "learning_rate": 0.00012536667793173372, | |
| "loss": 4.4438, | |
| "num_input_tokens_seen": 344324192, | |
| "step": 58950 | |
| }, | |
| { | |
| "epoch": 0.6512791408845715, | |
| "grad_norm": 1.751080870628357, | |
| "learning_rate": 0.0001252785165376082, | |
| "loss": 4.4439, | |
| "num_input_tokens_seen": 345204320, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 0.6529321336279333, | |
| "grad_norm": 1.8455328941345215, | |
| "learning_rate": 0.0001251903551434827, | |
| "loss": 4.4446, | |
| "num_input_tokens_seen": 346100960, | |
| "step": 59250 | |
| }, | |
| { | |
| "epoch": 0.6545851263712952, | |
| "grad_norm": 1.9079509973526, | |
| "learning_rate": 0.00012510219374935717, | |
| "loss": 4.4441, | |
| "num_input_tokens_seen": 346981376, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 0.6562381191146571, | |
| "grad_norm": 1.8034120798110962, | |
| "learning_rate": 0.00012501403235523167, | |
| "loss": 4.4555, | |
| "num_input_tokens_seen": 347855584, | |
| "step": 59550 | |
| }, | |
| { | |
| "epoch": 0.657891111858019, | |
| "grad_norm": 1.7936707735061646, | |
| "learning_rate": 0.00012492587096110615, | |
| "loss": 4.4493, | |
| "num_input_tokens_seen": 348733664, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 0.6595441046013808, | |
| "grad_norm": 1.80596923828125, | |
| "learning_rate": 0.00012483770956698065, | |
| "loss": 4.4445, | |
| "num_input_tokens_seen": 349592128, | |
| "step": 59850 | |
| }, | |
| { | |
| "epoch": 0.6611970973447426, | |
| "grad_norm": 1.7837984561920166, | |
| "learning_rate": 0.00012474954817285512, | |
| "loss": 4.4472, | |
| "num_input_tokens_seen": 350464672, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.6628500900881045, | |
| "grad_norm": 1.8550629615783691, | |
| "learning_rate": 0.0001246613867787296, | |
| "loss": 4.4436, | |
| "num_input_tokens_seen": 351360576, | |
| "step": 60150 | |
| }, | |
| { | |
| "epoch": 0.6645030828314664, | |
| "grad_norm": 1.8099464178085327, | |
| "learning_rate": 0.0001245738131272316, | |
| "loss": 4.4439, | |
| "num_input_tokens_seen": 352250944, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 0.6661560755748283, | |
| "grad_norm": 1.869233250617981, | |
| "learning_rate": 0.0001244856517331061, | |
| "loss": 4.45, | |
| "num_input_tokens_seen": 353120608, | |
| "step": 60450 | |
| }, | |
| { | |
| "epoch": 0.6678090683181901, | |
| "grad_norm": 1.8628960847854614, | |
| "learning_rate": 0.00012439749033898057, | |
| "loss": 4.4446, | |
| "num_input_tokens_seen": 353986944, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 0.6694620610615519, | |
| "grad_norm": 1.7935791015625, | |
| "learning_rate": 0.00012430932894485504, | |
| "loss": 4.4481, | |
| "num_input_tokens_seen": 354851456, | |
| "step": 60750 | |
| }, | |
| { | |
| "epoch": 0.6711150538049138, | |
| "grad_norm": 1.919735074043274, | |
| "learning_rate": 0.00012422116755072955, | |
| "loss": 4.4491, | |
| "num_input_tokens_seen": 355735616, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 0.6727680465482756, | |
| "grad_norm": 1.9296785593032837, | |
| "learning_rate": 0.00012413300615660402, | |
| "loss": 4.4384, | |
| "num_input_tokens_seen": 356613408, | |
| "step": 61050 | |
| }, | |
| { | |
| "epoch": 0.6744210392916375, | |
| "grad_norm": 1.8167061805725098, | |
| "learning_rate": 0.00012404484476247852, | |
| "loss": 4.4326, | |
| "num_input_tokens_seen": 357463840, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 0.6760740320349994, | |
| "grad_norm": 1.86695396900177, | |
| "learning_rate": 0.000123956683368353, | |
| "loss": 4.4501, | |
| "num_input_tokens_seen": 358354464, | |
| "step": 61350 | |
| }, | |
| { | |
| "epoch": 0.6777270247783612, | |
| "grad_norm": 1.8627629280090332, | |
| "learning_rate": 0.0001238685219742275, | |
| "loss": 4.4496, | |
| "num_input_tokens_seen": 359222016, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.6793800175217231, | |
| "grad_norm": 1.8496758937835693, | |
| "learning_rate": 0.00012378036058010197, | |
| "loss": 4.4505, | |
| "num_input_tokens_seen": 360112096, | |
| "step": 61650 | |
| }, | |
| { | |
| "epoch": 0.6810330102650849, | |
| "grad_norm": 1.8193156719207764, | |
| "learning_rate": 0.00012369219918597645, | |
| "loss": 4.452, | |
| "num_input_tokens_seen": 360995520, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 0.6826860030084468, | |
| "grad_norm": 1.7519707679748535, | |
| "learning_rate": 0.00012360403779185095, | |
| "loss": 4.4439, | |
| "num_input_tokens_seen": 361873184, | |
| "step": 61950 | |
| }, | |
| { | |
| "epoch": 0.6843389957518087, | |
| "grad_norm": 1.9227124452590942, | |
| "learning_rate": 0.00012351587639772543, | |
| "loss": 4.4416, | |
| "num_input_tokens_seen": 362749312, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 0.6859919884951705, | |
| "grad_norm": 1.8492848873138428, | |
| "learning_rate": 0.00012342771500359993, | |
| "loss": 4.4541, | |
| "num_input_tokens_seen": 363635936, | |
| "step": 62250 | |
| }, | |
| { | |
| "epoch": 0.6876449812385323, | |
| "grad_norm": 1.946057677268982, | |
| "learning_rate": 0.0001233395536094744, | |
| "loss": 4.435, | |
| "num_input_tokens_seen": 364500576, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 0.6892979739818942, | |
| "grad_norm": 1.8880736827850342, | |
| "learning_rate": 0.0001232513922153489, | |
| "loss": 4.4442, | |
| "num_input_tokens_seen": 365363744, | |
| "step": 62550 | |
| }, | |
| { | |
| "epoch": 0.690950966725256, | |
| "grad_norm": 1.864534854888916, | |
| "learning_rate": 0.00012316323082122338, | |
| "loss": 4.4398, | |
| "num_input_tokens_seen": 366253600, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 0.692603959468618, | |
| "grad_norm": 1.8077435493469238, | |
| "learning_rate": 0.00012307506942709788, | |
| "loss": 4.4462, | |
| "num_input_tokens_seen": 367119136, | |
| "step": 62850 | |
| }, | |
| { | |
| "epoch": 0.6942569522119798, | |
| "grad_norm": 1.8797168731689453, | |
| "learning_rate": 0.00012298690803297236, | |
| "loss": 4.4535, | |
| "num_input_tokens_seen": 367998656, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.6959099449553416, | |
| "grad_norm": 1.9124201536178589, | |
| "learning_rate": 0.00012289874663884686, | |
| "loss": 4.4314, | |
| "num_input_tokens_seen": 368873888, | |
| "step": 63150 | |
| }, | |
| { | |
| "epoch": 0.6975629376987035, | |
| "grad_norm": 1.919708013534546, | |
| "learning_rate": 0.00012281058524472134, | |
| "loss": 4.4524, | |
| "num_input_tokens_seen": 369761216, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 0.6992159304420653, | |
| "grad_norm": 1.8248168230056763, | |
| "learning_rate": 0.00012272242385059584, | |
| "loss": 4.4422, | |
| "num_input_tokens_seen": 370638688, | |
| "step": 63450 | |
| }, | |
| { | |
| "epoch": 0.7008689231854273, | |
| "grad_norm": 1.810051441192627, | |
| "learning_rate": 0.0001226342624564703, | |
| "loss": 4.4313, | |
| "num_input_tokens_seen": 371541344, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 0.7025219159287891, | |
| "grad_norm": 1.8361635208129883, | |
| "learning_rate": 0.00012254610106234481, | |
| "loss": 4.436, | |
| "num_input_tokens_seen": 372415168, | |
| "step": 63750 | |
| }, | |
| { | |
| "epoch": 0.7041749086721509, | |
| "grad_norm": 1.8005433082580566, | |
| "learning_rate": 0.0001224579396682193, | |
| "loss": 4.4353, | |
| "num_input_tokens_seen": 373283872, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 0.7058279014155128, | |
| "grad_norm": 1.8291569948196411, | |
| "learning_rate": 0.0001223697782740938, | |
| "loss": 4.4486, | |
| "num_input_tokens_seen": 374156960, | |
| "step": 64050 | |
| }, | |
| { | |
| "epoch": 0.7074808941588746, | |
| "grad_norm": 1.6987590789794922, | |
| "learning_rate": 0.00012228161687996827, | |
| "loss": 4.4402, | |
| "num_input_tokens_seen": 375045632, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 0.7091338869022366, | |
| "grad_norm": 1.8456915616989136, | |
| "learning_rate": 0.00012219345548584277, | |
| "loss": 4.4502, | |
| "num_input_tokens_seen": 375936576, | |
| "step": 64350 | |
| }, | |
| { | |
| "epoch": 0.7107868796455984, | |
| "grad_norm": 1.9141839742660522, | |
| "learning_rate": 0.00012210529409171724, | |
| "loss": 4.4521, | |
| "num_input_tokens_seen": 376816512, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.7124398723889602, | |
| "grad_norm": 1.8822457790374756, | |
| "learning_rate": 0.00012201713269759175, | |
| "loss": 4.4347, | |
| "num_input_tokens_seen": 377684448, | |
| "step": 64650 | |
| }, | |
| { | |
| "epoch": 0.7140928651323221, | |
| "grad_norm": 1.8143234252929688, | |
| "learning_rate": 0.00012192897130346622, | |
| "loss": 4.4336, | |
| "num_input_tokens_seen": 378553120, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 0.7157458578756839, | |
| "grad_norm": 1.8877683877944946, | |
| "learning_rate": 0.00012184080990934071, | |
| "loss": 4.4425, | |
| "num_input_tokens_seen": 379413888, | |
| "step": 64950 | |
| }, | |
| { | |
| "epoch": 0.7173988506190457, | |
| "grad_norm": 1.8746610879898071, | |
| "learning_rate": 0.0001217526485152152, | |
| "loss": 4.4417, | |
| "num_input_tokens_seen": 380290304, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 0.7190518433624077, | |
| "grad_norm": 2.0395500659942627, | |
| "learning_rate": 0.00012166448712108969, | |
| "loss": 4.4423, | |
| "num_input_tokens_seen": 381185920, | |
| "step": 65250 | |
| }, | |
| { | |
| "epoch": 0.7207048361057695, | |
| "grad_norm": 1.992492914199829, | |
| "learning_rate": 0.00012157632572696418, | |
| "loss": 4.4484, | |
| "num_input_tokens_seen": 382075808, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 0.7223578288491314, | |
| "grad_norm": 1.8621459007263184, | |
| "learning_rate": 0.00012148816433283866, | |
| "loss": 4.4274, | |
| "num_input_tokens_seen": 382955232, | |
| "step": 65550 | |
| }, | |
| { | |
| "epoch": 0.7240108215924932, | |
| "grad_norm": 1.8787345886230469, | |
| "learning_rate": 0.00012140000293871315, | |
| "loss": 4.4378, | |
| "num_input_tokens_seen": 383834592, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 0.725663814335855, | |
| "grad_norm": 1.8640894889831543, | |
| "learning_rate": 0.00012131184154458764, | |
| "loss": 4.4557, | |
| "num_input_tokens_seen": 384710016, | |
| "step": 65850 | |
| }, | |
| { | |
| "epoch": 0.727316807079217, | |
| "grad_norm": 1.918143630027771, | |
| "learning_rate": 0.00012122368015046212, | |
| "loss": 4.4467, | |
| "num_input_tokens_seen": 385593120, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.7289697998225788, | |
| "grad_norm": 1.8295505046844482, | |
| "learning_rate": 0.00012113551875633662, | |
| "loss": 4.4257, | |
| "num_input_tokens_seen": 386460160, | |
| "step": 66150 | |
| }, | |
| { | |
| "epoch": 0.7306227925659406, | |
| "grad_norm": 1.880216360092163, | |
| "learning_rate": 0.00012104794510483861, | |
| "loss": 4.4312, | |
| "num_input_tokens_seen": 387328000, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 0.7322757853093025, | |
| "grad_norm": 1.818788766860962, | |
| "learning_rate": 0.00012095978371071308, | |
| "loss": 4.4402, | |
| "num_input_tokens_seen": 388200192, | |
| "step": 66450 | |
| }, | |
| { | |
| "epoch": 0.7339287780526643, | |
| "grad_norm": 1.82147216796875, | |
| "learning_rate": 0.00012087162231658759, | |
| "loss": 4.4468, | |
| "num_input_tokens_seen": 389079264, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 0.7355817707960262, | |
| "grad_norm": 1.8930702209472656, | |
| "learning_rate": 0.00012078346092246206, | |
| "loss": 4.4362, | |
| "num_input_tokens_seen": 389974112, | |
| "step": 66750 | |
| }, | |
| { | |
| "epoch": 0.7372347635393881, | |
| "grad_norm": 1.8484946489334106, | |
| "learning_rate": 0.00012069529952833656, | |
| "loss": 4.4409, | |
| "num_input_tokens_seen": 390875168, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 0.7388877562827499, | |
| "grad_norm": 1.894093632698059, | |
| "learning_rate": 0.00012060713813421104, | |
| "loss": 4.4197, | |
| "num_input_tokens_seen": 391736384, | |
| "step": 67050 | |
| }, | |
| { | |
| "epoch": 0.7405407490261118, | |
| "grad_norm": 1.918149471282959, | |
| "learning_rate": 0.00012051897674008553, | |
| "loss": 4.4487, | |
| "num_input_tokens_seen": 392626688, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 0.7421937417694736, | |
| "grad_norm": 1.8563427925109863, | |
| "learning_rate": 0.00012043081534596002, | |
| "loss": 4.4375, | |
| "num_input_tokens_seen": 393508640, | |
| "step": 67350 | |
| }, | |
| { | |
| "epoch": 0.7438467345128355, | |
| "grad_norm": 1.8275529146194458, | |
| "learning_rate": 0.0001203426539518345, | |
| "loss": 4.4333, | |
| "num_input_tokens_seen": 394397120, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 0.7454997272561974, | |
| "grad_norm": 1.824823260307312, | |
| "learning_rate": 0.00012025449255770899, | |
| "loss": 4.4213, | |
| "num_input_tokens_seen": 395273408, | |
| "step": 67650 | |
| }, | |
| { | |
| "epoch": 0.7471527199995592, | |
| "grad_norm": 1.7815489768981934, | |
| "learning_rate": 0.00012016633116358348, | |
| "loss": 4.4295, | |
| "num_input_tokens_seen": 396151584, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 0.7488057127429211, | |
| "grad_norm": 1.9288073778152466, | |
| "learning_rate": 0.00012007816976945797, | |
| "loss": 4.4348, | |
| "num_input_tokens_seen": 397006880, | |
| "step": 67950 | |
| }, | |
| { | |
| "epoch": 0.7504587054862829, | |
| "grad_norm": 1.866746425628662, | |
| "learning_rate": 0.00011999000837533245, | |
| "loss": 4.4306, | |
| "num_input_tokens_seen": 397879072, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 0.7521116982296447, | |
| "grad_norm": 1.8168858289718628, | |
| "learning_rate": 0.00011990184698120693, | |
| "loss": 4.4321, | |
| "num_input_tokens_seen": 398772672, | |
| "step": 68250 | |
| }, | |
| { | |
| "epoch": 0.7537646909730066, | |
| "grad_norm": 1.7801350355148315, | |
| "learning_rate": 0.00011981368558708142, | |
| "loss": 4.4358, | |
| "num_input_tokens_seen": 399663136, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 0.7554176837163685, | |
| "grad_norm": 1.9442716836929321, | |
| "learning_rate": 0.00011972611193558343, | |
| "loss": 4.4357, | |
| "num_input_tokens_seen": 400543936, | |
| "step": 68550 | |
| }, | |
| { | |
| "epoch": 0.7570706764597304, | |
| "grad_norm": 1.8754234313964844, | |
| "learning_rate": 0.0001196379505414579, | |
| "loss": 4.4279, | |
| "num_input_tokens_seen": 401411136, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 0.7587236692030922, | |
| "grad_norm": 1.8986996412277222, | |
| "learning_rate": 0.0001195497891473324, | |
| "loss": 4.4345, | |
| "num_input_tokens_seen": 402290464, | |
| "step": 68850 | |
| }, | |
| { | |
| "epoch": 0.760376661946454, | |
| "grad_norm": 1.8807158470153809, | |
| "learning_rate": 0.00011946162775320688, | |
| "loss": 4.4329, | |
| "num_input_tokens_seen": 403176768, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.7620296546898159, | |
| "grad_norm": 1.8661843538284302, | |
| "learning_rate": 0.00011937346635908138, | |
| "loss": 4.4327, | |
| "num_input_tokens_seen": 404053888, | |
| "step": 69150 | |
| }, | |
| { | |
| "epoch": 0.7636826474331778, | |
| "grad_norm": 1.9022386074066162, | |
| "learning_rate": 0.00011928530496495586, | |
| "loss": 4.4304, | |
| "num_input_tokens_seen": 404951328, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 0.7653356401765397, | |
| "grad_norm": 1.9497708082199097, | |
| "learning_rate": 0.00011919714357083035, | |
| "loss": 4.4319, | |
| "num_input_tokens_seen": 405824128, | |
| "step": 69450 | |
| }, | |
| { | |
| "epoch": 0.7669886329199015, | |
| "grad_norm": 1.7283419370651245, | |
| "learning_rate": 0.00011910898217670483, | |
| "loss": 4.4222, | |
| "num_input_tokens_seen": 406694592, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 0.7686416256632633, | |
| "grad_norm": 1.8692352771759033, | |
| "learning_rate": 0.00011902082078257931, | |
| "loss": 4.4257, | |
| "num_input_tokens_seen": 407577856, | |
| "step": 69750 | |
| }, | |
| { | |
| "epoch": 0.7702946184066252, | |
| "grad_norm": 1.918215036392212, | |
| "learning_rate": 0.00011893265938845381, | |
| "loss": 4.4275, | |
| "num_input_tokens_seen": 408455424, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 0.771947611149987, | |
| "grad_norm": 1.8184279203414917, | |
| "learning_rate": 0.00011884449799432829, | |
| "loss": 4.4287, | |
| "num_input_tokens_seen": 409330752, | |
| "step": 70050 | |
| }, | |
| { | |
| "epoch": 0.773600603893349, | |
| "grad_norm": 1.846740961074829, | |
| "learning_rate": 0.00011875633660020279, | |
| "loss": 4.4244, | |
| "num_input_tokens_seen": 410215104, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 0.7752535966367108, | |
| "grad_norm": 1.9468152523040771, | |
| "learning_rate": 0.00011866817520607726, | |
| "loss": 4.4223, | |
| "num_input_tokens_seen": 411089696, | |
| "step": 70350 | |
| }, | |
| { | |
| "epoch": 0.7769065893800726, | |
| "grad_norm": 1.87180495262146, | |
| "learning_rate": 0.00011858001381195175, | |
| "loss": 4.4511, | |
| "num_input_tokens_seen": 411988000, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 0.7785595821234345, | |
| "grad_norm": 1.8375773429870605, | |
| "learning_rate": 0.00011849185241782624, | |
| "loss": 4.4361, | |
| "num_input_tokens_seen": 412876544, | |
| "step": 70650 | |
| }, | |
| { | |
| "epoch": 0.7802125748667963, | |
| "grad_norm": 1.7592004537582397, | |
| "learning_rate": 0.00011840369102370073, | |
| "loss": 4.4272, | |
| "num_input_tokens_seen": 413737824, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 0.7818655676101582, | |
| "grad_norm": 1.9243676662445068, | |
| "learning_rate": 0.00011831552962957522, | |
| "loss": 4.4343, | |
| "num_input_tokens_seen": 414613184, | |
| "step": 70950 | |
| }, | |
| { | |
| "epoch": 0.7835185603535201, | |
| "grad_norm": 1.9014674425125122, | |
| "learning_rate": 0.0001182273682354497, | |
| "loss": 4.4217, | |
| "num_input_tokens_seen": 415494144, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 0.7851715530968819, | |
| "grad_norm": 1.8528156280517578, | |
| "learning_rate": 0.0001181397945839517, | |
| "loss": 4.4323, | |
| "num_input_tokens_seen": 416354240, | |
| "step": 71250 | |
| }, | |
| { | |
| "epoch": 0.7868245458402437, | |
| "grad_norm": 1.7702356576919556, | |
| "learning_rate": 0.0001180516331898262, | |
| "loss": 4.4335, | |
| "num_input_tokens_seen": 417214944, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 0.7884775385836056, | |
| "grad_norm": 1.893778920173645, | |
| "learning_rate": 0.00011796347179570067, | |
| "loss": 4.4288, | |
| "num_input_tokens_seen": 418073984, | |
| "step": 71550 | |
| }, | |
| { | |
| "epoch": 0.7901305313269674, | |
| "grad_norm": 1.8179432153701782, | |
| "learning_rate": 0.00011787531040157515, | |
| "loss": 4.4161, | |
| "num_input_tokens_seen": 418956256, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 0.7917835240703294, | |
| "grad_norm": 1.8786159753799438, | |
| "learning_rate": 0.00011778714900744965, | |
| "loss": 4.4224, | |
| "num_input_tokens_seen": 419832544, | |
| "step": 71850 | |
| }, | |
| { | |
| "epoch": 0.7934365168136912, | |
| "grad_norm": 1.864493727684021, | |
| "learning_rate": 0.00011769898761332413, | |
| "loss": 4.4294, | |
| "num_input_tokens_seen": 420706176, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.795089509557053, | |
| "grad_norm": 1.7827798128128052, | |
| "learning_rate": 0.00011761082621919863, | |
| "loss": 4.4265, | |
| "num_input_tokens_seen": 421594880, | |
| "step": 72150 | |
| }, | |
| { | |
| "epoch": 0.7967425023004149, | |
| "grad_norm": 1.8714325428009033, | |
| "learning_rate": 0.0001175226648250731, | |
| "loss": 4.4428, | |
| "num_input_tokens_seen": 422456256, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 0.7983954950437767, | |
| "grad_norm": 1.8954764604568481, | |
| "learning_rate": 0.0001174345034309476, | |
| "loss": 4.4198, | |
| "num_input_tokens_seen": 423334208, | |
| "step": 72450 | |
| }, | |
| { | |
| "epoch": 0.8000484877871387, | |
| "grad_norm": 1.9334732294082642, | |
| "learning_rate": 0.00011734634203682208, | |
| "loss": 4.4285, | |
| "num_input_tokens_seen": 424227104, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 0.8017014805305005, | |
| "grad_norm": 1.8234983682632446, | |
| "learning_rate": 0.00011725818064269657, | |
| "loss": 4.438, | |
| "num_input_tokens_seen": 425093536, | |
| "step": 72750 | |
| }, | |
| { | |
| "epoch": 0.8033544732738623, | |
| "grad_norm": 1.8719639778137207, | |
| "learning_rate": 0.00011717001924857106, | |
| "loss": 4.432, | |
| "num_input_tokens_seen": 425967904, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 0.8050074660172242, | |
| "grad_norm": 1.879062533378601, | |
| "learning_rate": 0.00011708185785444555, | |
| "loss": 4.4157, | |
| "num_input_tokens_seen": 426848192, | |
| "step": 73050 | |
| }, | |
| { | |
| "epoch": 0.806660458760586, | |
| "grad_norm": 1.8409887552261353, | |
| "learning_rate": 0.00011699369646032003, | |
| "loss": 4.4173, | |
| "num_input_tokens_seen": 427730528, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 0.8083134515039478, | |
| "grad_norm": 1.9242078065872192, | |
| "learning_rate": 0.00011690553506619452, | |
| "loss": 4.4296, | |
| "num_input_tokens_seen": 428621792, | |
| "step": 73350 | |
| }, | |
| { | |
| "epoch": 0.8099664442473098, | |
| "grad_norm": 1.8767496347427368, | |
| "learning_rate": 0.00011681737367206901, | |
| "loss": 4.4245, | |
| "num_input_tokens_seen": 429494624, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 0.8116194369906716, | |
| "grad_norm": 1.8519647121429443, | |
| "learning_rate": 0.0001167292122779435, | |
| "loss": 4.4254, | |
| "num_input_tokens_seen": 430360704, | |
| "step": 73650 | |
| }, | |
| { | |
| "epoch": 0.8132724297340335, | |
| "grad_norm": 1.9251487255096436, | |
| "learning_rate": 0.00011664105088381798, | |
| "loss": 4.4362, | |
| "num_input_tokens_seen": 431239616, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 0.8149254224773953, | |
| "grad_norm": 1.8970694541931152, | |
| "learning_rate": 0.00011655288948969248, | |
| "loss": 4.4261, | |
| "num_input_tokens_seen": 432109120, | |
| "step": 73950 | |
| }, | |
| { | |
| "epoch": 0.8165784152207571, | |
| "grad_norm": 1.8284028768539429, | |
| "learning_rate": 0.00011646472809556695, | |
| "loss": 4.4406, | |
| "num_input_tokens_seen": 433005440, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 0.8182314079641191, | |
| "grad_norm": 1.7933986186981201, | |
| "learning_rate": 0.00011637656670144145, | |
| "loss": 4.4333, | |
| "num_input_tokens_seen": 433891456, | |
| "step": 74250 | |
| }, | |
| { | |
| "epoch": 0.8198844007074809, | |
| "grad_norm": 1.802509069442749, | |
| "learning_rate": 0.00011628840530731593, | |
| "loss": 4.4201, | |
| "num_input_tokens_seen": 434769856, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 0.8215373934508428, | |
| "grad_norm": 1.7515144348144531, | |
| "learning_rate": 0.00011620024391319043, | |
| "loss": 4.4225, | |
| "num_input_tokens_seen": 435665920, | |
| "step": 74550 | |
| }, | |
| { | |
| "epoch": 0.8231903861942046, | |
| "grad_norm": 1.8373006582260132, | |
| "learning_rate": 0.00011611208251906491, | |
| "loss": 4.4265, | |
| "num_input_tokens_seen": 436549984, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 0.8248433789375664, | |
| "grad_norm": 1.8570173978805542, | |
| "learning_rate": 0.00011602392112493941, | |
| "loss": 4.4196, | |
| "num_input_tokens_seen": 437427456, | |
| "step": 74850 | |
| }, | |
| { | |
| "epoch": 0.8264963716809283, | |
| "grad_norm": 1.9485052824020386, | |
| "learning_rate": 0.00011593575973081388, | |
| "loss": 4.4235, | |
| "num_input_tokens_seen": 438316576, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.8281493644242902, | |
| "grad_norm": 1.8972394466400146, | |
| "learning_rate": 0.00011584818607931588, | |
| "loss": 4.4231, | |
| "num_input_tokens_seen": 439211648, | |
| "step": 75150 | |
| }, | |
| { | |
| "epoch": 0.829802357167652, | |
| "grad_norm": 1.778745412826538, | |
| "learning_rate": 0.00011576002468519036, | |
| "loss": 4.423, | |
| "num_input_tokens_seen": 440086912, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 0.8314553499110139, | |
| "grad_norm": 1.923743486404419, | |
| "learning_rate": 0.00011567245103369236, | |
| "loss": 4.4112, | |
| "num_input_tokens_seen": 440976736, | |
| "step": 75450 | |
| }, | |
| { | |
| "epoch": 0.8331083426543757, | |
| "grad_norm": 1.8902959823608398, | |
| "learning_rate": 0.00011558428963956683, | |
| "loss": 4.4171, | |
| "num_input_tokens_seen": 441827264, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 0.8347613353977376, | |
| "grad_norm": 1.882279396057129, | |
| "learning_rate": 0.00011549612824544133, | |
| "loss": 4.4386, | |
| "num_input_tokens_seen": 442687328, | |
| "step": 75750 | |
| }, | |
| { | |
| "epoch": 0.8364143281410995, | |
| "grad_norm": 1.8508954048156738, | |
| "learning_rate": 0.00011540796685131581, | |
| "loss": 4.4261, | |
| "num_input_tokens_seen": 443558176, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 0.8380673208844613, | |
| "grad_norm": 1.8582794666290283, | |
| "learning_rate": 0.00011531980545719031, | |
| "loss": 4.4214, | |
| "num_input_tokens_seen": 444448512, | |
| "step": 76050 | |
| }, | |
| { | |
| "epoch": 0.8397203136278232, | |
| "grad_norm": 1.8337671756744385, | |
| "learning_rate": 0.00011523164406306478, | |
| "loss": 4.4257, | |
| "num_input_tokens_seen": 445311808, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 0.841373306371185, | |
| "grad_norm": 1.8980998992919922, | |
| "learning_rate": 0.00011514348266893929, | |
| "loss": 4.4294, | |
| "num_input_tokens_seen": 446200832, | |
| "step": 76350 | |
| }, | |
| { | |
| "epoch": 0.8430262991145469, | |
| "grad_norm": 1.8506239652633667, | |
| "learning_rate": 0.00011505532127481376, | |
| "loss": 4.4205, | |
| "num_input_tokens_seen": 447081376, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 0.8446792918579088, | |
| "grad_norm": 1.8824795484542847, | |
| "learning_rate": 0.00011496715988068826, | |
| "loss": 4.4213, | |
| "num_input_tokens_seen": 447960352, | |
| "step": 76650 | |
| }, | |
| { | |
| "epoch": 0.8463322846012706, | |
| "grad_norm": 1.8223339319229126, | |
| "learning_rate": 0.00011487899848656274, | |
| "loss": 4.4267, | |
| "num_input_tokens_seen": 448832096, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 0.8479852773446325, | |
| "grad_norm": 1.8224749565124512, | |
| "learning_rate": 0.00011479083709243724, | |
| "loss": 4.4181, | |
| "num_input_tokens_seen": 449706720, | |
| "step": 76950 | |
| }, | |
| { | |
| "epoch": 0.8496382700879943, | |
| "grad_norm": 1.903432011604309, | |
| "learning_rate": 0.00011470267569831172, | |
| "loss": 4.4309, | |
| "num_input_tokens_seen": 450578752, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 0.8512912628313561, | |
| "grad_norm": 1.8261497020721436, | |
| "learning_rate": 0.0001146145143041862, | |
| "loss": 4.4195, | |
| "num_input_tokens_seen": 451441120, | |
| "step": 77250 | |
| }, | |
| { | |
| "epoch": 0.852944255574718, | |
| "grad_norm": 1.8583135604858398, | |
| "learning_rate": 0.00011452635291006069, | |
| "loss": 4.4198, | |
| "num_input_tokens_seen": 452318560, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 0.8545972483180799, | |
| "grad_norm": 1.8936694860458374, | |
| "learning_rate": 0.00011443819151593518, | |
| "loss": 4.4287, | |
| "num_input_tokens_seen": 453195136, | |
| "step": 77550 | |
| }, | |
| { | |
| "epoch": 0.8562502410614418, | |
| "grad_norm": 1.9256082773208618, | |
| "learning_rate": 0.00011435003012180967, | |
| "loss": 4.4156, | |
| "num_input_tokens_seen": 454055456, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 0.8579032338048036, | |
| "grad_norm": 1.8237937688827515, | |
| "learning_rate": 0.00011426186872768416, | |
| "loss": 4.4348, | |
| "num_input_tokens_seen": 454932800, | |
| "step": 77850 | |
| }, | |
| { | |
| "epoch": 0.8595562265481654, | |
| "grad_norm": 1.8298827409744263, | |
| "learning_rate": 0.00011417370733355865, | |
| "loss": 4.4178, | |
| "num_input_tokens_seen": 455826208, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.8612092192915273, | |
| "grad_norm": 1.895670771598816, | |
| "learning_rate": 0.00011408554593943314, | |
| "loss": 4.4164, | |
| "num_input_tokens_seen": 456726848, | |
| "step": 78150 | |
| }, | |
| { | |
| "epoch": 0.8628622120348892, | |
| "grad_norm": 1.750807523727417, | |
| "learning_rate": 0.00011399738454530761, | |
| "loss": 4.4051, | |
| "num_input_tokens_seen": 457606464, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 0.8645152047782511, | |
| "grad_norm": 1.8419345617294312, | |
| "learning_rate": 0.00011390922315118211, | |
| "loss": 4.4249, | |
| "num_input_tokens_seen": 458484896, | |
| "step": 78450 | |
| }, | |
| { | |
| "epoch": 0.8661681975216129, | |
| "grad_norm": 2.033911943435669, | |
| "learning_rate": 0.00011382106175705659, | |
| "loss": 4.421, | |
| "num_input_tokens_seen": 459353824, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 0.8678211902649747, | |
| "grad_norm": 1.9020805358886719, | |
| "learning_rate": 0.00011373290036293109, | |
| "loss": 4.4016, | |
| "num_input_tokens_seen": 460221184, | |
| "step": 78750 | |
| }, | |
| { | |
| "epoch": 0.8694741830083366, | |
| "grad_norm": 1.91862952709198, | |
| "learning_rate": 0.00011364473896880557, | |
| "loss": 4.4093, | |
| "num_input_tokens_seen": 461087744, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 0.8711271757516984, | |
| "grad_norm": 1.7994396686553955, | |
| "learning_rate": 0.00011355657757468007, | |
| "loss": 4.4281, | |
| "num_input_tokens_seen": 461960160, | |
| "step": 79050 | |
| }, | |
| { | |
| "epoch": 0.8727801684950603, | |
| "grad_norm": 1.7911181449890137, | |
| "learning_rate": 0.00011346841618055454, | |
| "loss": 4.4229, | |
| "num_input_tokens_seen": 462838144, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 0.8744331612384222, | |
| "grad_norm": 1.923474907875061, | |
| "learning_rate": 0.00011338025478642904, | |
| "loss": 4.4103, | |
| "num_input_tokens_seen": 463703328, | |
| "step": 79350 | |
| }, | |
| { | |
| "epoch": 0.876086153981784, | |
| "grad_norm": 1.994814157485962, | |
| "learning_rate": 0.00011329268113493102, | |
| "loss": 4.4128, | |
| "num_input_tokens_seen": 464568896, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 0.8777391467251459, | |
| "grad_norm": 1.875200867652893, | |
| "learning_rate": 0.00011320451974080551, | |
| "loss": 4.4224, | |
| "num_input_tokens_seen": 465434144, | |
| "step": 79650 | |
| }, | |
| { | |
| "epoch": 0.8793921394685077, | |
| "grad_norm": 1.8729829788208008, | |
| "learning_rate": 0.00011311635834668, | |
| "loss": 4.4274, | |
| "num_input_tokens_seen": 466293984, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 0.8810451322118696, | |
| "grad_norm": 1.772687315940857, | |
| "learning_rate": 0.00011302819695255449, | |
| "loss": 4.4178, | |
| "num_input_tokens_seen": 467169280, | |
| "step": 79950 | |
| }, | |
| { | |
| "epoch": 0.8826981249552315, | |
| "grad_norm": 1.8293451070785522, | |
| "learning_rate": 0.00011294003555842898, | |
| "loss": 4.412, | |
| "num_input_tokens_seen": 468023552, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 0.8843511176985933, | |
| "grad_norm": 1.9000316858291626, | |
| "learning_rate": 0.00011285187416430346, | |
| "loss": 4.4114, | |
| "num_input_tokens_seen": 468883168, | |
| "step": 80250 | |
| }, | |
| { | |
| "epoch": 0.8860041104419552, | |
| "grad_norm": 1.8056668043136597, | |
| "learning_rate": 0.00011276371277017795, | |
| "loss": 4.4225, | |
| "num_input_tokens_seen": 469761120, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 0.887657103185317, | |
| "grad_norm": 1.7813293933868408, | |
| "learning_rate": 0.00011267555137605243, | |
| "loss": 4.4176, | |
| "num_input_tokens_seen": 470629344, | |
| "step": 80550 | |
| }, | |
| { | |
| "epoch": 0.8893100959286788, | |
| "grad_norm": 1.8244847059249878, | |
| "learning_rate": 0.00011258738998192693, | |
| "loss": 4.4082, | |
| "num_input_tokens_seen": 471489280, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 0.8909630886720408, | |
| "grad_norm": 1.8946529626846313, | |
| "learning_rate": 0.00011249981633042892, | |
| "loss": 4.4162, | |
| "num_input_tokens_seen": 472365504, | |
| "step": 80850 | |
| }, | |
| { | |
| "epoch": 0.8926160814154026, | |
| "grad_norm": 1.870685338973999, | |
| "learning_rate": 0.0001124116549363034, | |
| "loss": 4.4009, | |
| "num_input_tokens_seen": 473238752, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.8942690741587644, | |
| "grad_norm": 1.9169375896453857, | |
| "learning_rate": 0.0001123234935421779, | |
| "loss": 4.4176, | |
| "num_input_tokens_seen": 474122880, | |
| "step": 81150 | |
| }, | |
| { | |
| "epoch": 0.8959220669021263, | |
| "grad_norm": 1.9780856370925903, | |
| "learning_rate": 0.00011223533214805237, | |
| "loss": 4.401, | |
| "num_input_tokens_seen": 475002240, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 0.8975750596454881, | |
| "grad_norm": 1.8493030071258545, | |
| "learning_rate": 0.00011214717075392688, | |
| "loss": 4.4091, | |
| "num_input_tokens_seen": 475882624, | |
| "step": 81450 | |
| }, | |
| { | |
| "epoch": 0.8992280523888501, | |
| "grad_norm": 1.8798983097076416, | |
| "learning_rate": 0.00011205900935980135, | |
| "loss": 4.4113, | |
| "num_input_tokens_seen": 476749664, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 0.9008810451322119, | |
| "grad_norm": 1.8249197006225586, | |
| "learning_rate": 0.00011197084796567584, | |
| "loss": 4.4059, | |
| "num_input_tokens_seen": 477650784, | |
| "step": 81750 | |
| }, | |
| { | |
| "epoch": 0.9025340378755737, | |
| "grad_norm": 1.9157739877700806, | |
| "learning_rate": 0.00011188268657155033, | |
| "loss": 4.4109, | |
| "num_input_tokens_seen": 478523840, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 0.9041870306189356, | |
| "grad_norm": 1.9503858089447021, | |
| "learning_rate": 0.00011179452517742482, | |
| "loss": 4.4139, | |
| "num_input_tokens_seen": 479399296, | |
| "step": 82050 | |
| }, | |
| { | |
| "epoch": 0.9058400233622974, | |
| "grad_norm": 1.8298823833465576, | |
| "learning_rate": 0.0001117063637832993, | |
| "loss": 4.4123, | |
| "num_input_tokens_seen": 480262240, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 0.9074930161056592, | |
| "grad_norm": 1.9161386489868164, | |
| "learning_rate": 0.0001116182023891738, | |
| "loss": 4.4058, | |
| "num_input_tokens_seen": 481141056, | |
| "step": 82350 | |
| }, | |
| { | |
| "epoch": 0.9091460088490212, | |
| "grad_norm": 1.872722864151001, | |
| "learning_rate": 0.00011153004099504828, | |
| "loss": 4.4279, | |
| "num_input_tokens_seen": 482014112, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 0.910799001592383, | |
| "grad_norm": 1.8831090927124023, | |
| "learning_rate": 0.00011144187960092277, | |
| "loss": 4.4121, | |
| "num_input_tokens_seen": 482898336, | |
| "step": 82650 | |
| }, | |
| { | |
| "epoch": 0.9124519943357449, | |
| "grad_norm": 1.8128923177719116, | |
| "learning_rate": 0.00011135371820679725, | |
| "loss": 4.4105, | |
| "num_input_tokens_seen": 483773760, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 0.9141049870791067, | |
| "grad_norm": 1.8982397317886353, | |
| "learning_rate": 0.00011126555681267175, | |
| "loss": 4.4234, | |
| "num_input_tokens_seen": 484671008, | |
| "step": 82950 | |
| }, | |
| { | |
| "epoch": 0.9157579798224685, | |
| "grad_norm": 1.8295831680297852, | |
| "learning_rate": 0.00011117739541854622, | |
| "loss": 4.4227, | |
| "num_input_tokens_seen": 485553984, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 0.9174109725658305, | |
| "grad_norm": 1.8975720405578613, | |
| "learning_rate": 0.00011108923402442071, | |
| "loss": 4.4176, | |
| "num_input_tokens_seen": 486416672, | |
| "step": 83250 | |
| }, | |
| { | |
| "epoch": 0.9190639653091923, | |
| "grad_norm": 1.8207321166992188, | |
| "learning_rate": 0.0001110010726302952, | |
| "loss": 4.424, | |
| "num_input_tokens_seen": 487286816, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 0.9207169580525542, | |
| "grad_norm": 1.9241523742675781, | |
| "learning_rate": 0.00011091291123616969, | |
| "loss": 4.4129, | |
| "num_input_tokens_seen": 488157088, | |
| "step": 83550 | |
| }, | |
| { | |
| "epoch": 0.922369950795916, | |
| "grad_norm": 1.8391443490982056, | |
| "learning_rate": 0.00011082474984204418, | |
| "loss": 4.4036, | |
| "num_input_tokens_seen": 489008320, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 0.9240229435392778, | |
| "grad_norm": 1.9244701862335205, | |
| "learning_rate": 0.00011073658844791865, | |
| "loss": 4.4215, | |
| "num_input_tokens_seen": 489887328, | |
| "step": 83850 | |
| }, | |
| { | |
| "epoch": 0.9256759362826397, | |
| "grad_norm": 1.8949611186981201, | |
| "learning_rate": 0.00011064842705379315, | |
| "loss": 4.4205, | |
| "num_input_tokens_seen": 490765504, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.9273289290260016, | |
| "grad_norm": 1.810594081878662, | |
| "learning_rate": 0.00011056026565966763, | |
| "loss": 4.4149, | |
| "num_input_tokens_seen": 491650144, | |
| "step": 84150 | |
| }, | |
| { | |
| "epoch": 0.9289819217693635, | |
| "grad_norm": 1.8556066751480103, | |
| "learning_rate": 0.00011047210426554213, | |
| "loss": 4.4102, | |
| "num_input_tokens_seen": 492539968, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 0.9306349145127253, | |
| "grad_norm": 1.8486409187316895, | |
| "learning_rate": 0.00011038394287141661, | |
| "loss": 4.4231, | |
| "num_input_tokens_seen": 493424352, | |
| "step": 84450 | |
| }, | |
| { | |
| "epoch": 0.9322879072560871, | |
| "grad_norm": 1.8193395137786865, | |
| "learning_rate": 0.00011029578147729111, | |
| "loss": 4.4195, | |
| "num_input_tokens_seen": 494301152, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 0.933940899999449, | |
| "grad_norm": 1.8344619274139404, | |
| "learning_rate": 0.00011020762008316558, | |
| "loss": 4.4075, | |
| "num_input_tokens_seen": 495177600, | |
| "step": 84750 | |
| }, | |
| { | |
| "epoch": 0.9355938927428109, | |
| "grad_norm": 1.781654953956604, | |
| "learning_rate": 0.00011012004643166758, | |
| "loss": 4.4075, | |
| "num_input_tokens_seen": 496047680, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 0.9372468854861727, | |
| "grad_norm": 1.935810923576355, | |
| "learning_rate": 0.00011003188503754206, | |
| "loss": 4.408, | |
| "num_input_tokens_seen": 496919488, | |
| "step": 85050 | |
| }, | |
| { | |
| "epoch": 0.9388998782295346, | |
| "grad_norm": 1.8130574226379395, | |
| "learning_rate": 0.00010994372364341655, | |
| "loss": 4.4152, | |
| "num_input_tokens_seen": 497821280, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 0.9405528709728964, | |
| "grad_norm": 1.9481176137924194, | |
| "learning_rate": 0.00010985556224929104, | |
| "loss": 4.4115, | |
| "num_input_tokens_seen": 498694560, | |
| "step": 85350 | |
| }, | |
| { | |
| "epoch": 0.9422058637162583, | |
| "grad_norm": 1.8938475847244263, | |
| "learning_rate": 0.00010976740085516553, | |
| "loss": 4.4077, | |
| "num_input_tokens_seen": 499570016, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 0.9438588564596201, | |
| "grad_norm": 1.8449296951293945, | |
| "learning_rate": 0.00010967923946104002, | |
| "loss": 4.4043, | |
| "num_input_tokens_seen": 500436288, | |
| "step": 85650 | |
| }, | |
| { | |
| "epoch": 0.945511849202982, | |
| "grad_norm": 1.775891661643982, | |
| "learning_rate": 0.00010959166580954201, | |
| "loss": 4.4112, | |
| "num_input_tokens_seen": 501298944, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 0.9471648419463439, | |
| "grad_norm": 1.827708125114441, | |
| "learning_rate": 0.00010950350441541651, | |
| "loss": 4.4088, | |
| "num_input_tokens_seen": 502206976, | |
| "step": 85950 | |
| }, | |
| { | |
| "epoch": 0.9488178346897057, | |
| "grad_norm": 1.8833259344100952, | |
| "learning_rate": 0.00010941534302129099, | |
| "loss": 4.4107, | |
| "num_input_tokens_seen": 503083488, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 0.9504708274330675, | |
| "grad_norm": 1.8116602897644043, | |
| "learning_rate": 0.00010932718162716549, | |
| "loss": 4.4109, | |
| "num_input_tokens_seen": 503978240, | |
| "step": 86250 | |
| }, | |
| { | |
| "epoch": 0.9521238201764294, | |
| "grad_norm": 1.8248368501663208, | |
| "learning_rate": 0.00010923902023303996, | |
| "loss": 4.4041, | |
| "num_input_tokens_seen": 504859744, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 0.9537768129197913, | |
| "grad_norm": 1.862371802330017, | |
| "learning_rate": 0.00010915085883891444, | |
| "loss": 4.4221, | |
| "num_input_tokens_seen": 505740576, | |
| "step": 86550 | |
| }, | |
| { | |
| "epoch": 0.9554298056631532, | |
| "grad_norm": 1.8358848094940186, | |
| "learning_rate": 0.00010906269744478894, | |
| "loss": 4.4051, | |
| "num_input_tokens_seen": 506615680, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 0.957082798406515, | |
| "grad_norm": 1.8686786890029907, | |
| "learning_rate": 0.00010897453605066342, | |
| "loss": 4.41, | |
| "num_input_tokens_seen": 507477824, | |
| "step": 86850 | |
| }, | |
| { | |
| "epoch": 0.9587357911498768, | |
| "grad_norm": 1.833525538444519, | |
| "learning_rate": 0.00010888637465653792, | |
| "loss": 4.4188, | |
| "num_input_tokens_seen": 508371904, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.9603887838932387, | |
| "grad_norm": 1.9611468315124512, | |
| "learning_rate": 0.00010879821326241239, | |
| "loss": 4.4034, | |
| "num_input_tokens_seen": 509250272, | |
| "step": 87150 | |
| }, | |
| { | |
| "epoch": 0.9620417766366006, | |
| "grad_norm": 1.6934946775436401, | |
| "learning_rate": 0.00010871005186828688, | |
| "loss": 4.4067, | |
| "num_input_tokens_seen": 510129568, | |
| "step": 87300 | |
| }, | |
| { | |
| "epoch": 0.9636947693799625, | |
| "grad_norm": 1.8400757312774658, | |
| "learning_rate": 0.00010862189047416137, | |
| "loss": 4.4, | |
| "num_input_tokens_seen": 510995328, | |
| "step": 87450 | |
| }, | |
| { | |
| "epoch": 0.9653477621233243, | |
| "grad_norm": 1.8682547807693481, | |
| "learning_rate": 0.00010853372908003586, | |
| "loss": 4.4026, | |
| "num_input_tokens_seen": 511880416, | |
| "step": 87600 | |
| }, | |
| { | |
| "epoch": 0.9670007548666861, | |
| "grad_norm": 1.8408825397491455, | |
| "learning_rate": 0.00010844556768591035, | |
| "loss": 4.4019, | |
| "num_input_tokens_seen": 512759072, | |
| "step": 87750 | |
| }, | |
| { | |
| "epoch": 0.968653747610048, | |
| "grad_norm": 1.9082870483398438, | |
| "learning_rate": 0.00010835740629178484, | |
| "loss": 4.4076, | |
| "num_input_tokens_seen": 513640896, | |
| "step": 87900 | |
| }, | |
| { | |
| "epoch": 0.9703067403534098, | |
| "grad_norm": 1.9512287378311157, | |
| "learning_rate": 0.00010826983264028683, | |
| "loss": 4.4217, | |
| "num_input_tokens_seen": 514532256, | |
| "step": 88050 | |
| }, | |
| { | |
| "epoch": 0.9719597330967717, | |
| "grad_norm": 1.9278032779693604, | |
| "learning_rate": 0.0001081816712461613, | |
| "loss": 4.4217, | |
| "num_input_tokens_seen": 515412864, | |
| "step": 88200 | |
| }, | |
| { | |
| "epoch": 0.9736127258401336, | |
| "grad_norm": 1.814817190170288, | |
| "learning_rate": 0.0001080935098520358, | |
| "loss": 4.4178, | |
| "num_input_tokens_seen": 516301408, | |
| "step": 88350 | |
| }, | |
| { | |
| "epoch": 0.9752657185834954, | |
| "grad_norm": 2.0495548248291016, | |
| "learning_rate": 0.00010800534845791028, | |
| "loss": 4.4101, | |
| "num_input_tokens_seen": 517179648, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 0.9769187113268573, | |
| "grad_norm": 1.8378854990005493, | |
| "learning_rate": 0.00010791718706378478, | |
| "loss": 4.4031, | |
| "num_input_tokens_seen": 518064288, | |
| "step": 88650 | |
| }, | |
| { | |
| "epoch": 0.9785717040702191, | |
| "grad_norm": 1.8407827615737915, | |
| "learning_rate": 0.00010782902566965926, | |
| "loss": 4.4135, | |
| "num_input_tokens_seen": 518947776, | |
| "step": 88800 | |
| }, | |
| { | |
| "epoch": 0.980224696813581, | |
| "grad_norm": 1.845199704170227, | |
| "learning_rate": 0.00010774086427553376, | |
| "loss": 4.4, | |
| "num_input_tokens_seen": 519822560, | |
| "step": 88950 | |
| }, | |
| { | |
| "epoch": 0.9818776895569429, | |
| "grad_norm": 1.8627071380615234, | |
| "learning_rate": 0.00010765270288140823, | |
| "loss": 4.4125, | |
| "num_input_tokens_seen": 520709888, | |
| "step": 89100 | |
| }, | |
| { | |
| "epoch": 0.9835306823003047, | |
| "grad_norm": 1.826648235321045, | |
| "learning_rate": 0.00010756454148728274, | |
| "loss": 4.4006, | |
| "num_input_tokens_seen": 521586080, | |
| "step": 89250 | |
| }, | |
| { | |
| "epoch": 0.9851836750436666, | |
| "grad_norm": 1.9315438270568848, | |
| "learning_rate": 0.00010747638009315721, | |
| "loss": 4.4104, | |
| "num_input_tokens_seen": 522450944, | |
| "step": 89400 | |
| }, | |
| { | |
| "epoch": 0.9868366677870284, | |
| "grad_norm": 1.8507201671600342, | |
| "learning_rate": 0.0001073882186990317, | |
| "loss": 4.412, | |
| "num_input_tokens_seen": 523335744, | |
| "step": 89550 | |
| }, | |
| { | |
| "epoch": 0.9884896605303902, | |
| "grad_norm": 1.8950568437576294, | |
| "learning_rate": 0.00010730005730490619, | |
| "loss": 4.4106, | |
| "num_input_tokens_seen": 524216960, | |
| "step": 89700 | |
| }, | |
| { | |
| "epoch": 0.9901426532737522, | |
| "grad_norm": 1.92140531539917, | |
| "learning_rate": 0.00010721189591078068, | |
| "loss": 4.4001, | |
| "num_input_tokens_seen": 525081088, | |
| "step": 89850 | |
| }, | |
| { | |
| "epoch": 0.991795646017114, | |
| "grad_norm": 1.9179210662841797, | |
| "learning_rate": 0.00010712373451665516, | |
| "loss": 4.4044, | |
| "num_input_tokens_seen": 525964384, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.9934486387604758, | |
| "grad_norm": 1.8168158531188965, | |
| "learning_rate": 0.00010703557312252965, | |
| "loss": 4.4082, | |
| "num_input_tokens_seen": 526852256, | |
| "step": 90150 | |
| }, | |
| { | |
| "epoch": 0.9951016315038377, | |
| "grad_norm": 2.0058753490448, | |
| "learning_rate": 0.00010694741172840414, | |
| "loss": 4.4061, | |
| "num_input_tokens_seen": 527721152, | |
| "step": 90300 | |
| }, | |
| { | |
| "epoch": 0.9967546242471995, | |
| "grad_norm": 2.0036473274230957, | |
| "learning_rate": 0.00010685925033427863, | |
| "loss": 4.4013, | |
| "num_input_tokens_seen": 528601472, | |
| "step": 90450 | |
| }, | |
| { | |
| "epoch": 0.9984076169905615, | |
| "grad_norm": 1.8912723064422607, | |
| "learning_rate": 0.0001067710889401531, | |
| "loss": 4.408, | |
| "num_input_tokens_seen": 529485344, | |
| "step": 90600 | |
| }, | |
| { | |
| "epoch": 1.0000606097339233, | |
| "grad_norm": 1.8539482355117798, | |
| "learning_rate": 0.00010668292754602761, | |
| "loss": 4.4072, | |
| "num_input_tokens_seen": 530388834, | |
| "step": 90750 | |
| }, | |
| { | |
| "epoch": 1.001713602477285, | |
| "grad_norm": 1.9648711681365967, | |
| "learning_rate": 0.00010659476615190208, | |
| "loss": 4.4023, | |
| "num_input_tokens_seen": 531261986, | |
| "step": 90900 | |
| }, | |
| { | |
| "epoch": 1.003366595220647, | |
| "grad_norm": 1.8683501482009888, | |
| "learning_rate": 0.00010650660475777658, | |
| "loss": 4.3953, | |
| "num_input_tokens_seen": 532138626, | |
| "step": 91050 | |
| }, | |
| { | |
| "epoch": 1.005019587964009, | |
| "grad_norm": 1.9149645566940308, | |
| "learning_rate": 0.00010641844336365106, | |
| "loss": 4.3907, | |
| "num_input_tokens_seen": 533008418, | |
| "step": 91200 | |
| }, | |
| { | |
| "epoch": 1.0066725807073706, | |
| "grad_norm": 1.804408073425293, | |
| "learning_rate": 0.00010633028196952556, | |
| "loss": 4.4053, | |
| "num_input_tokens_seen": 533881122, | |
| "step": 91350 | |
| }, | |
| { | |
| "epoch": 1.0083255734507326, | |
| "grad_norm": 1.8145511150360107, | |
| "learning_rate": 0.00010624212057540004, | |
| "loss": 4.3993, | |
| "num_input_tokens_seen": 534752738, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 1.0099785661940943, | |
| "grad_norm": 1.8206557035446167, | |
| "learning_rate": 0.00010615395918127454, | |
| "loss": 4.3954, | |
| "num_input_tokens_seen": 535622338, | |
| "step": 91650 | |
| }, | |
| { | |
| "epoch": 1.0116315589374563, | |
| "grad_norm": 1.880231261253357, | |
| "learning_rate": 0.00010606579778714901, | |
| "loss": 4.4002, | |
| "num_input_tokens_seen": 536488386, | |
| "step": 91800 | |
| }, | |
| { | |
| "epoch": 1.0132845516808182, | |
| "grad_norm": 1.8914505243301392, | |
| "learning_rate": 0.00010597763639302352, | |
| "loss": 4.3961, | |
| "num_input_tokens_seen": 537374658, | |
| "step": 91950 | |
| }, | |
| { | |
| "epoch": 1.01493754442418, | |
| "grad_norm": 1.9163919687271118, | |
| "learning_rate": 0.0001058900627415255, | |
| "loss": 4.3973, | |
| "num_input_tokens_seen": 538244194, | |
| "step": 92100 | |
| }, | |
| { | |
| "epoch": 1.0165905371675419, | |
| "grad_norm": 1.9003725051879883, | |
| "learning_rate": 0.00010580190134739998, | |
| "loss": 4.3957, | |
| "num_input_tokens_seen": 539130914, | |
| "step": 92250 | |
| }, | |
| { | |
| "epoch": 1.0182435299109036, | |
| "grad_norm": 1.838493824005127, | |
| "learning_rate": 0.00010571373995327447, | |
| "loss": 4.3878, | |
| "num_input_tokens_seen": 540022850, | |
| "step": 92400 | |
| }, | |
| { | |
| "epoch": 1.0198965226542656, | |
| "grad_norm": 1.9080275297164917, | |
| "learning_rate": 0.00010562557855914896, | |
| "loss": 4.3917, | |
| "num_input_tokens_seen": 540895874, | |
| "step": 92550 | |
| }, | |
| { | |
| "epoch": 1.0215495153976275, | |
| "grad_norm": 1.8060060739517212, | |
| "learning_rate": 0.00010553741716502345, | |
| "loss": 4.3953, | |
| "num_input_tokens_seen": 541762658, | |
| "step": 92700 | |
| }, | |
| { | |
| "epoch": 1.0232025081409892, | |
| "grad_norm": 1.903151273727417, | |
| "learning_rate": 0.00010544925577089792, | |
| "loss": 4.3952, | |
| "num_input_tokens_seen": 542643138, | |
| "step": 92850 | |
| }, | |
| { | |
| "epoch": 1.0248555008843512, | |
| "grad_norm": 1.9957008361816406, | |
| "learning_rate": 0.00010536109437677243, | |
| "loss": 4.3952, | |
| "num_input_tokens_seen": 543505570, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 1.026508493627713, | |
| "grad_norm": 1.8897976875305176, | |
| "learning_rate": 0.0001052729329826469, | |
| "loss": 4.395, | |
| "num_input_tokens_seen": 544378466, | |
| "step": 93150 | |
| }, | |
| { | |
| "epoch": 1.0281614863710749, | |
| "grad_norm": 1.895654320716858, | |
| "learning_rate": 0.0001051847715885214, | |
| "loss": 4.4016, | |
| "num_input_tokens_seen": 545256738, | |
| "step": 93300 | |
| }, | |
| { | |
| "epoch": 1.0298144791144366, | |
| "grad_norm": 1.9977262020111084, | |
| "learning_rate": 0.00010509661019439588, | |
| "loss": 4.3994, | |
| "num_input_tokens_seen": 546150498, | |
| "step": 93450 | |
| }, | |
| { | |
| "epoch": 1.0314674718577985, | |
| "grad_norm": 1.82341468334198, | |
| "learning_rate": 0.00010500844880027038, | |
| "loss": 4.4003, | |
| "num_input_tokens_seen": 547021922, | |
| "step": 93600 | |
| }, | |
| { | |
| "epoch": 1.0331204646011605, | |
| "grad_norm": 1.7573907375335693, | |
| "learning_rate": 0.00010492028740614485, | |
| "loss": 4.3936, | |
| "num_input_tokens_seen": 547888450, | |
| "step": 93750 | |
| }, | |
| { | |
| "epoch": 1.0347734573445222, | |
| "grad_norm": 2.011516571044922, | |
| "learning_rate": 0.00010483212601201936, | |
| "loss": 4.3861, | |
| "num_input_tokens_seen": 548752514, | |
| "step": 93900 | |
| }, | |
| { | |
| "epoch": 1.0364264500878841, | |
| "grad_norm": 1.8368171453475952, | |
| "learning_rate": 0.00010474396461789383, | |
| "loss": 4.3975, | |
| "num_input_tokens_seen": 549641218, | |
| "step": 94050 | |
| }, | |
| { | |
| "epoch": 1.0380794428312459, | |
| "grad_norm": 2.0658929347991943, | |
| "learning_rate": 0.00010465639096639582, | |
| "loss": 4.4042, | |
| "num_input_tokens_seen": 550521378, | |
| "step": 94200 | |
| }, | |
| { | |
| "epoch": 1.0397324355746078, | |
| "grad_norm": 1.8516744375228882, | |
| "learning_rate": 0.00010456822957227031, | |
| "loss": 4.3937, | |
| "num_input_tokens_seen": 551403138, | |
| "step": 94350 | |
| }, | |
| { | |
| "epoch": 1.0413854283179698, | |
| "grad_norm": 1.9704523086547852, | |
| "learning_rate": 0.0001044800681781448, | |
| "loss": 4.3892, | |
| "num_input_tokens_seen": 552268866, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 1.0430384210613315, | |
| "grad_norm": 1.8856583833694458, | |
| "learning_rate": 0.00010439190678401929, | |
| "loss": 4.3969, | |
| "num_input_tokens_seen": 553139522, | |
| "step": 94650 | |
| }, | |
| { | |
| "epoch": 1.0446914138046934, | |
| "grad_norm": 1.9823240041732788, | |
| "learning_rate": 0.00010430374538989378, | |
| "loss": 4.3937, | |
| "num_input_tokens_seen": 554009858, | |
| "step": 94800 | |
| }, | |
| { | |
| "epoch": 1.0463444065480552, | |
| "grad_norm": 1.8391404151916504, | |
| "learning_rate": 0.00010421558399576827, | |
| "loss": 4.3891, | |
| "num_input_tokens_seen": 554896962, | |
| "step": 94950 | |
| }, | |
| { | |
| "epoch": 1.047997399291417, | |
| "grad_norm": 1.829777717590332, | |
| "learning_rate": 0.00010412742260164274, | |
| "loss": 4.3996, | |
| "num_input_tokens_seen": 555778274, | |
| "step": 95100 | |
| }, | |
| { | |
| "epoch": 1.049650392034779, | |
| "grad_norm": 1.884190320968628, | |
| "learning_rate": 0.00010403926120751724, | |
| "loss": 4.3899, | |
| "num_input_tokens_seen": 556658210, | |
| "step": 95250 | |
| }, | |
| { | |
| "epoch": 1.0513033847781408, | |
| "grad_norm": 1.8368123769760132, | |
| "learning_rate": 0.00010395109981339172, | |
| "loss": 4.3989, | |
| "num_input_tokens_seen": 557549442, | |
| "step": 95400 | |
| }, | |
| { | |
| "epoch": 1.0529563775215027, | |
| "grad_norm": 1.7985849380493164, | |
| "learning_rate": 0.00010386293841926622, | |
| "loss": 4.3868, | |
| "num_input_tokens_seen": 558417634, | |
| "step": 95550 | |
| }, | |
| { | |
| "epoch": 1.0546093702648645, | |
| "grad_norm": 1.8913172483444214, | |
| "learning_rate": 0.0001037747770251407, | |
| "loss": 4.4031, | |
| "num_input_tokens_seen": 559314882, | |
| "step": 95700 | |
| }, | |
| { | |
| "epoch": 1.0562623630082264, | |
| "grad_norm": 1.9179192781448364, | |
| "learning_rate": 0.0001036866156310152, | |
| "loss": 4.3812, | |
| "num_input_tokens_seen": 560207298, | |
| "step": 95850 | |
| }, | |
| { | |
| "epoch": 1.0579153557515883, | |
| "grad_norm": 1.8890949487686157, | |
| "learning_rate": 0.00010359845423688967, | |
| "loss": 4.3916, | |
| "num_input_tokens_seen": 561097570, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.05956834849495, | |
| "grad_norm": 1.7995752096176147, | |
| "learning_rate": 0.00010351088058539166, | |
| "loss": 4.3933, | |
| "num_input_tokens_seen": 561973218, | |
| "step": 96150 | |
| }, | |
| { | |
| "epoch": 1.061221341238312, | |
| "grad_norm": 1.928031086921692, | |
| "learning_rate": 0.00010342330693389365, | |
| "loss": 4.3914, | |
| "num_input_tokens_seen": 562851074, | |
| "step": 96300 | |
| }, | |
| { | |
| "epoch": 1.0628743339816737, | |
| "grad_norm": 1.94650137424469, | |
| "learning_rate": 0.00010333514553976814, | |
| "loss": 4.3766, | |
| "num_input_tokens_seen": 563725506, | |
| "step": 96450 | |
| }, | |
| { | |
| "epoch": 1.0645273267250357, | |
| "grad_norm": 1.8535209894180298, | |
| "learning_rate": 0.00010324698414564263, | |
| "loss": 4.3916, | |
| "num_input_tokens_seen": 564576034, | |
| "step": 96600 | |
| }, | |
| { | |
| "epoch": 1.0661803194683976, | |
| "grad_norm": 1.9456048011779785, | |
| "learning_rate": 0.00010315882275151712, | |
| "loss": 4.3975, | |
| "num_input_tokens_seen": 565446626, | |
| "step": 96750 | |
| }, | |
| { | |
| "epoch": 1.0678333122117594, | |
| "grad_norm": 1.8319114446640015, | |
| "learning_rate": 0.0001030706613573916, | |
| "loss": 4.3977, | |
| "num_input_tokens_seen": 566321378, | |
| "step": 96900 | |
| }, | |
| { | |
| "epoch": 1.0694863049551213, | |
| "grad_norm": 2.1267592906951904, | |
| "learning_rate": 0.0001029824999632661, | |
| "loss": 4.3896, | |
| "num_input_tokens_seen": 567203778, | |
| "step": 97050 | |
| }, | |
| { | |
| "epoch": 1.071139297698483, | |
| "grad_norm": 1.8523855209350586, | |
| "learning_rate": 0.00010289433856914057, | |
| "loss": 4.3868, | |
| "num_input_tokens_seen": 568083906, | |
| "step": 97200 | |
| }, | |
| { | |
| "epoch": 1.072792290441845, | |
| "grad_norm": 1.882645606994629, | |
| "learning_rate": 0.00010280617717501507, | |
| "loss": 4.3976, | |
| "num_input_tokens_seen": 568970690, | |
| "step": 97350 | |
| }, | |
| { | |
| "epoch": 1.0744452831852067, | |
| "grad_norm": 1.9347394704818726, | |
| "learning_rate": 0.00010271801578088955, | |
| "loss": 4.3905, | |
| "num_input_tokens_seen": 569844482, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 1.0760982759285687, | |
| "grad_norm": 1.855491280555725, | |
| "learning_rate": 0.00010262985438676405, | |
| "loss": 4.3886, | |
| "num_input_tokens_seen": 570717602, | |
| "step": 97650 | |
| }, | |
| { | |
| "epoch": 1.0777512686719306, | |
| "grad_norm": 1.8031153678894043, | |
| "learning_rate": 0.00010254169299263853, | |
| "loss": 4.3807, | |
| "num_input_tokens_seen": 571591586, | |
| "step": 97800 | |
| }, | |
| { | |
| "epoch": 1.0794042614152923, | |
| "grad_norm": 1.9792248010635376, | |
| "learning_rate": 0.00010245353159851303, | |
| "loss": 4.389, | |
| "num_input_tokens_seen": 572476162, | |
| "step": 97950 | |
| }, | |
| { | |
| "epoch": 1.0810572541586543, | |
| "grad_norm": 1.9110472202301025, | |
| "learning_rate": 0.0001023653702043875, | |
| "loss": 4.3889, | |
| "num_input_tokens_seen": 573353346, | |
| "step": 98100 | |
| }, | |
| { | |
| "epoch": 1.082710246902016, | |
| "grad_norm": 1.9655945301055908, | |
| "learning_rate": 0.000102277208810262, | |
| "loss": 4.3808, | |
| "num_input_tokens_seen": 574237986, | |
| "step": 98250 | |
| }, | |
| { | |
| "epoch": 1.084363239645378, | |
| "grad_norm": 1.806372880935669, | |
| "learning_rate": 0.00010218904741613648, | |
| "loss": 4.389, | |
| "num_input_tokens_seen": 575113346, | |
| "step": 98400 | |
| }, | |
| { | |
| "epoch": 1.08601623238874, | |
| "grad_norm": 1.9266657829284668, | |
| "learning_rate": 0.00010210147376463847, | |
| "loss": 4.3957, | |
| "num_input_tokens_seen": 576010818, | |
| "step": 98550 | |
| }, | |
| { | |
| "epoch": 1.0876692251321016, | |
| "grad_norm": 1.8409209251403809, | |
| "learning_rate": 0.00010201331237051296, | |
| "loss": 4.3949, | |
| "num_input_tokens_seen": 576872610, | |
| "step": 98700 | |
| }, | |
| { | |
| "epoch": 1.0893222178754636, | |
| "grad_norm": 1.7804383039474487, | |
| "learning_rate": 0.00010192515097638745, | |
| "loss": 4.3835, | |
| "num_input_tokens_seen": 577737090, | |
| "step": 98850 | |
| }, | |
| { | |
| "epoch": 1.0909752106188253, | |
| "grad_norm": 1.8269861936569214, | |
| "learning_rate": 0.00010183698958226194, | |
| "loss": 4.3967, | |
| "num_input_tokens_seen": 578610178, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 1.0926282033621872, | |
| "grad_norm": 1.9065062999725342, | |
| "learning_rate": 0.00010174882818813641, | |
| "loss": 4.395, | |
| "num_input_tokens_seen": 579483074, | |
| "step": 99150 | |
| }, | |
| { | |
| "epoch": 1.0942811961055492, | |
| "grad_norm": 1.8511546850204468, | |
| "learning_rate": 0.00010166066679401092, | |
| "loss": 4.3847, | |
| "num_input_tokens_seen": 580339138, | |
| "step": 99300 | |
| }, | |
| { | |
| "epoch": 1.095934188848911, | |
| "grad_norm": 1.9003854990005493, | |
| "learning_rate": 0.00010157250539988539, | |
| "loss": 4.3878, | |
| "num_input_tokens_seen": 581214146, | |
| "step": 99450 | |
| }, | |
| { | |
| "epoch": 1.0975871815922729, | |
| "grad_norm": 1.9078856706619263, | |
| "learning_rate": 0.00010148434400575989, | |
| "loss": 4.3976, | |
| "num_input_tokens_seen": 582094658, | |
| "step": 99600 | |
| }, | |
| { | |
| "epoch": 1.0992401743356346, | |
| "grad_norm": 1.8750337362289429, | |
| "learning_rate": 0.00010139618261163437, | |
| "loss": 4.3999, | |
| "num_input_tokens_seen": 582981922, | |
| "step": 99750 | |
| }, | |
| { | |
| "epoch": 1.1008931670789965, | |
| "grad_norm": 1.9243488311767578, | |
| "learning_rate": 0.00010130802121750887, | |
| "loss": 4.3879, | |
| "num_input_tokens_seen": 583869026, | |
| "step": 99900 | |
| }, | |
| { | |
| "epoch": 1.1025461598223583, | |
| "grad_norm": 1.8446391820907593, | |
| "learning_rate": 0.00010121985982338334, | |
| "loss": 4.3894, | |
| "num_input_tokens_seen": 584749826, | |
| "step": 100050 | |
| }, | |
| { | |
| "epoch": 1.1041991525657202, | |
| "grad_norm": 1.726158857345581, | |
| "learning_rate": 0.00010113169842925785, | |
| "loss": 4.3985, | |
| "num_input_tokens_seen": 585630274, | |
| "step": 100200 | |
| }, | |
| { | |
| "epoch": 1.1058521453090822, | |
| "grad_norm": 1.8227604627609253, | |
| "learning_rate": 0.00010104353703513232, | |
| "loss": 4.3906, | |
| "num_input_tokens_seen": 586484930, | |
| "step": 100350 | |
| }, | |
| { | |
| "epoch": 1.1075051380524439, | |
| "grad_norm": 1.9156420230865479, | |
| "learning_rate": 0.00010095537564100682, | |
| "loss": 4.3893, | |
| "num_input_tokens_seen": 587352738, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 1.1091581307958058, | |
| "grad_norm": 1.8385225534439087, | |
| "learning_rate": 0.0001008678019895088, | |
| "loss": 4.3994, | |
| "num_input_tokens_seen": 588239810, | |
| "step": 100650 | |
| }, | |
| { | |
| "epoch": 1.1108111235391678, | |
| "grad_norm": 1.9076261520385742, | |
| "learning_rate": 0.00010077964059538329, | |
| "loss": 4.3922, | |
| "num_input_tokens_seen": 589116514, | |
| "step": 100800 | |
| }, | |
| { | |
| "epoch": 1.1124641162825295, | |
| "grad_norm": 1.8701651096343994, | |
| "learning_rate": 0.00010069147920125778, | |
| "loss": 4.4015, | |
| "num_input_tokens_seen": 589983426, | |
| "step": 100950 | |
| }, | |
| { | |
| "epoch": 1.1141171090258915, | |
| "grad_norm": 1.9545180797576904, | |
| "learning_rate": 0.00010060331780713227, | |
| "loss": 4.3978, | |
| "num_input_tokens_seen": 590856994, | |
| "step": 101100 | |
| }, | |
| { | |
| "epoch": 1.1157701017692532, | |
| "grad_norm": 1.9418137073516846, | |
| "learning_rate": 0.00010051515641300676, | |
| "loss": 4.3893, | |
| "num_input_tokens_seen": 591735490, | |
| "step": 101250 | |
| }, | |
| { | |
| "epoch": 1.1174230945126151, | |
| "grad_norm": 1.892683982849121, | |
| "learning_rate": 0.00010042699501888123, | |
| "loss": 4.3833, | |
| "num_input_tokens_seen": 592622626, | |
| "step": 101400 | |
| }, | |
| { | |
| "epoch": 1.1190760872559768, | |
| "grad_norm": 1.830404281616211, | |
| "learning_rate": 0.00010033883362475573, | |
| "loss": 4.3939, | |
| "num_input_tokens_seen": 593500354, | |
| "step": 101550 | |
| }, | |
| { | |
| "epoch": 1.1207290799993388, | |
| "grad_norm": 1.8536481857299805, | |
| "learning_rate": 0.00010025067223063021, | |
| "loss": 4.3826, | |
| "num_input_tokens_seen": 594383234, | |
| "step": 101700 | |
| }, | |
| { | |
| "epoch": 1.1223820727427007, | |
| "grad_norm": 1.84872567653656, | |
| "learning_rate": 0.00010016251083650471, | |
| "loss": 4.3847, | |
| "num_input_tokens_seen": 595255266, | |
| "step": 101850 | |
| }, | |
| { | |
| "epoch": 1.1240350654860625, | |
| "grad_norm": 1.8653180599212646, | |
| "learning_rate": 0.00010007434944237918, | |
| "loss": 4.392, | |
| "num_input_tokens_seen": 596135586, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 1.1256880582294244, | |
| "grad_norm": 1.8534561395645142, | |
| "learning_rate": 9.998618804825369e-05, | |
| "loss": 4.3862, | |
| "num_input_tokens_seen": 597009218, | |
| "step": 102150 | |
| }, | |
| { | |
| "epoch": 1.1273410509727861, | |
| "grad_norm": 1.8982864618301392, | |
| "learning_rate": 9.989802665412816e-05, | |
| "loss": 4.3969, | |
| "num_input_tokens_seen": 597873026, | |
| "step": 102300 | |
| }, | |
| { | |
| "epoch": 1.128994043716148, | |
| "grad_norm": 1.9212620258331299, | |
| "learning_rate": 9.980986526000266e-05, | |
| "loss": 4.3872, | |
| "num_input_tokens_seen": 598748322, | |
| "step": 102450 | |
| }, | |
| { | |
| "epoch": 1.13064703645951, | |
| "grad_norm": 1.8133482933044434, | |
| "learning_rate": 9.972170386587714e-05, | |
| "loss": 4.3801, | |
| "num_input_tokens_seen": 599625410, | |
| "step": 102600 | |
| }, | |
| { | |
| "epoch": 1.1323000292028718, | |
| "grad_norm": 1.8521312475204468, | |
| "learning_rate": 9.963354247175164e-05, | |
| "loss": 4.3867, | |
| "num_input_tokens_seen": 600489762, | |
| "step": 102750 | |
| }, | |
| { | |
| "epoch": 1.1339530219462337, | |
| "grad_norm": 2.050074577331543, | |
| "learning_rate": 9.954538107762612e-05, | |
| "loss": 4.3813, | |
| "num_input_tokens_seen": 601357666, | |
| "step": 102900 | |
| }, | |
| { | |
| "epoch": 1.1356060146895954, | |
| "grad_norm": 1.8785549402236938, | |
| "learning_rate": 9.945721968350062e-05, | |
| "loss": 4.3799, | |
| "num_input_tokens_seen": 602239362, | |
| "step": 103050 | |
| }, | |
| { | |
| "epoch": 1.1372590074329574, | |
| "grad_norm": 1.9237360954284668, | |
| "learning_rate": 9.93690582893751e-05, | |
| "loss": 4.3902, | |
| "num_input_tokens_seen": 603119650, | |
| "step": 103200 | |
| }, | |
| { | |
| "epoch": 1.1389120001763193, | |
| "grad_norm": 1.8664278984069824, | |
| "learning_rate": 9.928089689524957e-05, | |
| "loss": 4.3905, | |
| "num_input_tokens_seen": 603985666, | |
| "step": 103350 | |
| }, | |
| { | |
| "epoch": 1.140564992919681, | |
| "grad_norm": 1.812515139579773, | |
| "learning_rate": 9.919273550112407e-05, | |
| "loss": 4.3757, | |
| "num_input_tokens_seen": 604874530, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 1.142217985663043, | |
| "grad_norm": 1.9093918800354004, | |
| "learning_rate": 9.910457410699855e-05, | |
| "loss": 4.4058, | |
| "num_input_tokens_seen": 605755394, | |
| "step": 103650 | |
| }, | |
| { | |
| "epoch": 1.1438709784064047, | |
| "grad_norm": 1.9712496995925903, | |
| "learning_rate": 9.901641271287305e-05, | |
| "loss": 4.3848, | |
| "num_input_tokens_seen": 606649794, | |
| "step": 103800 | |
| }, | |
| { | |
| "epoch": 1.1455239711497667, | |
| "grad_norm": 1.9102181196212769, | |
| "learning_rate": 9.892825131874752e-05, | |
| "loss": 4.3926, | |
| "num_input_tokens_seen": 607513858, | |
| "step": 103950 | |
| }, | |
| { | |
| "epoch": 1.1471769638931284, | |
| "grad_norm": 1.7749512195587158, | |
| "learning_rate": 9.884008992462201e-05, | |
| "loss": 4.3906, | |
| "num_input_tokens_seen": 608391202, | |
| "step": 104100 | |
| }, | |
| { | |
| "epoch": 1.1488299566364903, | |
| "grad_norm": 1.8394023180007935, | |
| "learning_rate": 9.87519285304965e-05, | |
| "loss": 4.3814, | |
| "num_input_tokens_seen": 609282018, | |
| "step": 104250 | |
| }, | |
| { | |
| "epoch": 1.1504829493798523, | |
| "grad_norm": 1.9161593914031982, | |
| "learning_rate": 9.866376713637099e-05, | |
| "loss": 4.3947, | |
| "num_input_tokens_seen": 610168514, | |
| "step": 104400 | |
| }, | |
| { | |
| "epoch": 1.152135942123214, | |
| "grad_norm": 1.930790901184082, | |
| "learning_rate": 9.857560574224548e-05, | |
| "loss": 4.3928, | |
| "num_input_tokens_seen": 611052354, | |
| "step": 104550 | |
| }, | |
| { | |
| "epoch": 1.153788934866576, | |
| "grad_norm": 1.836146354675293, | |
| "learning_rate": 9.848803209074748e-05, | |
| "loss": 4.3977, | |
| "num_input_tokens_seen": 611926498, | |
| "step": 104700 | |
| }, | |
| { | |
| "epoch": 1.155441927609938, | |
| "grad_norm": 1.7802364826202393, | |
| "learning_rate": 9.839987069662196e-05, | |
| "loss": 4.3921, | |
| "num_input_tokens_seen": 612818210, | |
| "step": 104850 | |
| }, | |
| { | |
| "epoch": 1.1570949203532996, | |
| "grad_norm": 1.9587794542312622, | |
| "learning_rate": 9.831170930249643e-05, | |
| "loss": 4.3925, | |
| "num_input_tokens_seen": 613694850, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.1587479130966616, | |
| "grad_norm": 1.9676165580749512, | |
| "learning_rate": 9.822354790837093e-05, | |
| "loss": 4.3782, | |
| "num_input_tokens_seen": 614583618, | |
| "step": 105150 | |
| }, | |
| { | |
| "epoch": 1.1604009058400233, | |
| "grad_norm": 1.8942914009094238, | |
| "learning_rate": 9.813538651424541e-05, | |
| "loss": 4.3792, | |
| "num_input_tokens_seen": 615478530, | |
| "step": 105300 | |
| }, | |
| { | |
| "epoch": 1.1620538985833853, | |
| "grad_norm": 1.8436447381973267, | |
| "learning_rate": 9.804722512011991e-05, | |
| "loss": 4.3848, | |
| "num_input_tokens_seen": 616374914, | |
| "step": 105450 | |
| }, | |
| { | |
| "epoch": 1.163706891326747, | |
| "grad_norm": 1.9150909185409546, | |
| "learning_rate": 9.795906372599439e-05, | |
| "loss": 4.381, | |
| "num_input_tokens_seen": 617260162, | |
| "step": 105600 | |
| }, | |
| { | |
| "epoch": 1.165359884070109, | |
| "grad_norm": 2.0403525829315186, | |
| "learning_rate": 9.787090233186889e-05, | |
| "loss": 4.3835, | |
| "num_input_tokens_seen": 618136386, | |
| "step": 105750 | |
| }, | |
| { | |
| "epoch": 1.1670128768134709, | |
| "grad_norm": 1.8062185049057007, | |
| "learning_rate": 9.778274093774336e-05, | |
| "loss": 4.3821, | |
| "num_input_tokens_seen": 619009282, | |
| "step": 105900 | |
| }, | |
| { | |
| "epoch": 1.1686658695568326, | |
| "grad_norm": 1.9948753118515015, | |
| "learning_rate": 9.769457954361787e-05, | |
| "loss": 4.3911, | |
| "num_input_tokens_seen": 619886722, | |
| "step": 106050 | |
| }, | |
| { | |
| "epoch": 1.1703188623001946, | |
| "grad_norm": 1.8109992742538452, | |
| "learning_rate": 9.760641814949234e-05, | |
| "loss": 4.3791, | |
| "num_input_tokens_seen": 620758178, | |
| "step": 106200 | |
| }, | |
| { | |
| "epoch": 1.1719718550435563, | |
| "grad_norm": 1.9707014560699463, | |
| "learning_rate": 9.751825675536684e-05, | |
| "loss": 4.3809, | |
| "num_input_tokens_seen": 621629506, | |
| "step": 106350 | |
| }, | |
| { | |
| "epoch": 1.1736248477869182, | |
| "grad_norm": 1.9458143711090088, | |
| "learning_rate": 9.743009536124132e-05, | |
| "loss": 4.3952, | |
| "num_input_tokens_seen": 622496418, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 1.17527784053028, | |
| "grad_norm": 1.9349957704544067, | |
| "learning_rate": 9.734310945237081e-05, | |
| "loss": 4.379, | |
| "num_input_tokens_seen": 623395010, | |
| "step": 106650 | |
| }, | |
| { | |
| "epoch": 1.176930833273642, | |
| "grad_norm": 1.9133590459823608, | |
| "learning_rate": 9.725494805824531e-05, | |
| "loss": 4.3689, | |
| "num_input_tokens_seen": 624262434, | |
| "step": 106800 | |
| }, | |
| { | |
| "epoch": 1.1785838260170038, | |
| "grad_norm": 1.9451539516448975, | |
| "learning_rate": 9.716678666411979e-05, | |
| "loss": 4.3863, | |
| "num_input_tokens_seen": 625153506, | |
| "step": 106950 | |
| }, | |
| { | |
| "epoch": 1.1802368187603656, | |
| "grad_norm": 2.0072357654571533, | |
| "learning_rate": 9.707862526999429e-05, | |
| "loss": 4.378, | |
| "num_input_tokens_seen": 626026690, | |
| "step": 107100 | |
| }, | |
| { | |
| "epoch": 1.1818898115037275, | |
| "grad_norm": 1.7655397653579712, | |
| "learning_rate": 9.699046387586877e-05, | |
| "loss": 4.3801, | |
| "num_input_tokens_seen": 626902594, | |
| "step": 107250 | |
| }, | |
| { | |
| "epoch": 1.1835428042470895, | |
| "grad_norm": 1.9583156108856201, | |
| "learning_rate": 9.690230248174325e-05, | |
| "loss": 4.3902, | |
| "num_input_tokens_seen": 627796194, | |
| "step": 107400 | |
| }, | |
| { | |
| "epoch": 1.1851957969904512, | |
| "grad_norm": 1.7717612981796265, | |
| "learning_rate": 9.681414108761774e-05, | |
| "loss": 4.3812, | |
| "num_input_tokens_seen": 628675970, | |
| "step": 107550 | |
| }, | |
| { | |
| "epoch": 1.1868487897338131, | |
| "grad_norm": 1.9090009927749634, | |
| "learning_rate": 9.672597969349223e-05, | |
| "loss": 4.3889, | |
| "num_input_tokens_seen": 629549794, | |
| "step": 107700 | |
| }, | |
| { | |
| "epoch": 1.1885017824771749, | |
| "grad_norm": 1.8910843133926392, | |
| "learning_rate": 9.663781829936672e-05, | |
| "loss": 4.3913, | |
| "num_input_tokens_seen": 630437378, | |
| "step": 107850 | |
| }, | |
| { | |
| "epoch": 1.1901547752205368, | |
| "grad_norm": 1.840728521347046, | |
| "learning_rate": 9.654965690524121e-05, | |
| "loss": 4.3792, | |
| "num_input_tokens_seen": 631313666, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 1.1918077679638985, | |
| "grad_norm": 1.8772791624069214, | |
| "learning_rate": 9.64614955111157e-05, | |
| "loss": 4.3813, | |
| "num_input_tokens_seen": 632194466, | |
| "step": 108150 | |
| }, | |
| { | |
| "epoch": 1.1934607607072605, | |
| "grad_norm": 1.9666273593902588, | |
| "learning_rate": 9.637333411699017e-05, | |
| "loss": 4.3716, | |
| "num_input_tokens_seen": 633058978, | |
| "step": 108300 | |
| }, | |
| { | |
| "epoch": 1.1951137534506224, | |
| "grad_norm": 1.930409550666809, | |
| "learning_rate": 9.628517272286466e-05, | |
| "loss": 4.3934, | |
| "num_input_tokens_seen": 633935458, | |
| "step": 108450 | |
| }, | |
| { | |
| "epoch": 1.1967667461939842, | |
| "grad_norm": 1.8000093698501587, | |
| "learning_rate": 9.619701132873915e-05, | |
| "loss": 4.3794, | |
| "num_input_tokens_seen": 634825634, | |
| "step": 108600 | |
| }, | |
| { | |
| "epoch": 1.198419738937346, | |
| "grad_norm": 1.8369793891906738, | |
| "learning_rate": 9.610884993461364e-05, | |
| "loss": 4.386, | |
| "num_input_tokens_seen": 635701666, | |
| "step": 108750 | |
| }, | |
| { | |
| "epoch": 1.2000727316807078, | |
| "grad_norm": 1.9381849765777588, | |
| "learning_rate": 9.602068854048813e-05, | |
| "loss": 4.3824, | |
| "num_input_tokens_seen": 636568994, | |
| "step": 108900 | |
| }, | |
| { | |
| "epoch": 1.2017257244240698, | |
| "grad_norm": 1.8089631795883179, | |
| "learning_rate": 9.593252714636261e-05, | |
| "loss": 4.3733, | |
| "num_input_tokens_seen": 637444034, | |
| "step": 109050 | |
| }, | |
| { | |
| "epoch": 1.2033787171674317, | |
| "grad_norm": 1.7429847717285156, | |
| "learning_rate": 9.584436575223709e-05, | |
| "loss": 4.3766, | |
| "num_input_tokens_seen": 638321634, | |
| "step": 109200 | |
| }, | |
| { | |
| "epoch": 1.2050317099107934, | |
| "grad_norm": 1.9182720184326172, | |
| "learning_rate": 9.575620435811159e-05, | |
| "loss": 4.3724, | |
| "num_input_tokens_seen": 639189538, | |
| "step": 109350 | |
| }, | |
| { | |
| "epoch": 1.2066847026541554, | |
| "grad_norm": 1.9700244665145874, | |
| "learning_rate": 9.566804296398607e-05, | |
| "loss": 4.3859, | |
| "num_input_tokens_seen": 640080354, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 1.2083376953975171, | |
| "grad_norm": 1.86391019821167, | |
| "learning_rate": 9.557988156986057e-05, | |
| "loss": 4.3875, | |
| "num_input_tokens_seen": 640977634, | |
| "step": 109650 | |
| }, | |
| { | |
| "epoch": 1.209990688140879, | |
| "grad_norm": 1.9451704025268555, | |
| "learning_rate": 9.549230791836256e-05, | |
| "loss": 4.3928, | |
| "num_input_tokens_seen": 641871874, | |
| "step": 109800 | |
| }, | |
| { | |
| "epoch": 1.211643680884241, | |
| "grad_norm": 2.063884735107422, | |
| "learning_rate": 9.540414652423704e-05, | |
| "loss": 4.3704, | |
| "num_input_tokens_seen": 642751170, | |
| "step": 109950 | |
| }, | |
| { | |
| "epoch": 1.2132966736276027, | |
| "grad_norm": 1.8499351739883423, | |
| "learning_rate": 9.531598513011154e-05, | |
| "loss": 4.3886, | |
| "num_input_tokens_seen": 643629698, | |
| "step": 110100 | |
| }, | |
| { | |
| "epoch": 1.2149496663709647, | |
| "grad_norm": 1.9735474586486816, | |
| "learning_rate": 9.522782373598601e-05, | |
| "loss": 4.3854, | |
| "num_input_tokens_seen": 644509698, | |
| "step": 110250 | |
| }, | |
| { | |
| "epoch": 1.2166026591143264, | |
| "grad_norm": 1.9430962800979614, | |
| "learning_rate": 9.513966234186051e-05, | |
| "loss": 4.3905, | |
| "num_input_tokens_seen": 645395394, | |
| "step": 110400 | |
| }, | |
| { | |
| "epoch": 1.2182556518576884, | |
| "grad_norm": 1.9608047008514404, | |
| "learning_rate": 9.505150094773499e-05, | |
| "loss": 4.383, | |
| "num_input_tokens_seen": 646254626, | |
| "step": 110550 | |
| }, | |
| { | |
| "epoch": 1.21990864460105, | |
| "grad_norm": 1.9237737655639648, | |
| "learning_rate": 9.4963927296237e-05, | |
| "loss": 4.3886, | |
| "num_input_tokens_seen": 647146658, | |
| "step": 110700 | |
| }, | |
| { | |
| "epoch": 1.221561637344412, | |
| "grad_norm": 1.9678759574890137, | |
| "learning_rate": 9.487576590211147e-05, | |
| "loss": 4.3858, | |
| "num_input_tokens_seen": 648004962, | |
| "step": 110850 | |
| }, | |
| { | |
| "epoch": 1.223214630087774, | |
| "grad_norm": 1.8643629550933838, | |
| "learning_rate": 9.478760450798597e-05, | |
| "loss": 4.3718, | |
| "num_input_tokens_seen": 648877602, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 1.2248676228311357, | |
| "grad_norm": 1.8100017309188843, | |
| "learning_rate": 9.469944311386045e-05, | |
| "loss": 4.38, | |
| "num_input_tokens_seen": 649743970, | |
| "step": 111150 | |
| }, | |
| { | |
| "epoch": 1.2265206155744977, | |
| "grad_norm": 1.8271883726119995, | |
| "learning_rate": 9.461128171973495e-05, | |
| "loss": 4.3911, | |
| "num_input_tokens_seen": 650620130, | |
| "step": 111300 | |
| }, | |
| { | |
| "epoch": 1.2281736083178596, | |
| "grad_norm": 1.9749687910079956, | |
| "learning_rate": 9.452312032560942e-05, | |
| "loss": 4.3715, | |
| "num_input_tokens_seen": 651492738, | |
| "step": 111450 | |
| }, | |
| { | |
| "epoch": 1.2298266010612213, | |
| "grad_norm": 1.9666537046432495, | |
| "learning_rate": 9.44349589314839e-05, | |
| "loss": 4.3823, | |
| "num_input_tokens_seen": 652359170, | |
| "step": 111600 | |
| }, | |
| { | |
| "epoch": 1.2314795938045833, | |
| "grad_norm": 1.9260027408599854, | |
| "learning_rate": 9.43467975373584e-05, | |
| "loss": 4.3862, | |
| "num_input_tokens_seen": 653229570, | |
| "step": 111750 | |
| }, | |
| { | |
| "epoch": 1.233132586547945, | |
| "grad_norm": 1.8240337371826172, | |
| "learning_rate": 9.425863614323288e-05, | |
| "loss": 4.3771, | |
| "num_input_tokens_seen": 654109090, | |
| "step": 111900 | |
| }, | |
| { | |
| "epoch": 1.234785579291307, | |
| "grad_norm": 1.957507848739624, | |
| "learning_rate": 9.417047474910738e-05, | |
| "loss": 4.3817, | |
| "num_input_tokens_seen": 654980482, | |
| "step": 112050 | |
| }, | |
| { | |
| "epoch": 1.2364385720346687, | |
| "grad_norm": 1.8944330215454102, | |
| "learning_rate": 9.408231335498185e-05, | |
| "loss": 4.3812, | |
| "num_input_tokens_seen": 655849634, | |
| "step": 112200 | |
| }, | |
| { | |
| "epoch": 1.2380915647780306, | |
| "grad_norm": 1.8677889108657837, | |
| "learning_rate": 9.399415196085636e-05, | |
| "loss": 4.3803, | |
| "num_input_tokens_seen": 656736738, | |
| "step": 112350 | |
| }, | |
| { | |
| "epoch": 1.2397445575213926, | |
| "grad_norm": 1.8283082246780396, | |
| "learning_rate": 9.390599056673083e-05, | |
| "loss": 4.3933, | |
| "num_input_tokens_seen": 657615938, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 1.2413975502647543, | |
| "grad_norm": 1.9106853008270264, | |
| "learning_rate": 9.381782917260533e-05, | |
| "loss": 4.3847, | |
| "num_input_tokens_seen": 658494850, | |
| "step": 112650 | |
| }, | |
| { | |
| "epoch": 1.2430505430081162, | |
| "grad_norm": 1.8882030248641968, | |
| "learning_rate": 9.372966777847981e-05, | |
| "loss": 4.3862, | |
| "num_input_tokens_seen": 659363618, | |
| "step": 112800 | |
| }, | |
| { | |
| "epoch": 1.244703535751478, | |
| "grad_norm": 1.964934229850769, | |
| "learning_rate": 9.36415063843543e-05, | |
| "loss": 4.3805, | |
| "num_input_tokens_seen": 660234946, | |
| "step": 112950 | |
| }, | |
| { | |
| "epoch": 1.24635652849484, | |
| "grad_norm": 1.8856420516967773, | |
| "learning_rate": 9.355334499022878e-05, | |
| "loss": 4.3794, | |
| "num_input_tokens_seen": 661115810, | |
| "step": 113100 | |
| }, | |
| { | |
| "epoch": 1.2480095212382019, | |
| "grad_norm": 1.8618583679199219, | |
| "learning_rate": 9.346518359610327e-05, | |
| "loss": 4.3883, | |
| "num_input_tokens_seen": 661994434, | |
| "step": 113250 | |
| }, | |
| { | |
| "epoch": 1.2496625139815636, | |
| "grad_norm": 1.9158508777618408, | |
| "learning_rate": 9.337702220197776e-05, | |
| "loss": 4.3739, | |
| "num_input_tokens_seen": 662868834, | |
| "step": 113400 | |
| }, | |
| { | |
| "epoch": 1.2513155067249255, | |
| "grad_norm": 1.8499860763549805, | |
| "learning_rate": 9.328886080785225e-05, | |
| "loss": 4.379, | |
| "num_input_tokens_seen": 663752002, | |
| "step": 113550 | |
| }, | |
| { | |
| "epoch": 1.2529684994682873, | |
| "grad_norm": 1.8565645217895508, | |
| "learning_rate": 9.320069941372673e-05, | |
| "loss": 4.3854, | |
| "num_input_tokens_seen": 664622402, | |
| "step": 113700 | |
| }, | |
| { | |
| "epoch": 1.2546214922116492, | |
| "grad_norm": 2.060188055038452, | |
| "learning_rate": 9.311253801960123e-05, | |
| "loss": 4.3758, | |
| "num_input_tokens_seen": 665495618, | |
| "step": 113850 | |
| }, | |
| { | |
| "epoch": 1.2562744849550112, | |
| "grad_norm": 1.892635464668274, | |
| "learning_rate": 9.30243766254757e-05, | |
| "loss": 4.3884, | |
| "num_input_tokens_seen": 666361922, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 1.2579274776983729, | |
| "grad_norm": 1.9154144525527954, | |
| "learning_rate": 9.29362152313502e-05, | |
| "loss": 4.3752, | |
| "num_input_tokens_seen": 667241410, | |
| "step": 114150 | |
| }, | |
| { | |
| "epoch": 1.2595804704417348, | |
| "grad_norm": 1.9253753423690796, | |
| "learning_rate": 9.284805383722468e-05, | |
| "loss": 4.3875, | |
| "num_input_tokens_seen": 668132226, | |
| "step": 114300 | |
| }, | |
| { | |
| "epoch": 1.2612334631850965, | |
| "grad_norm": 1.9465709924697876, | |
| "learning_rate": 9.275989244309918e-05, | |
| "loss": 4.3742, | |
| "num_input_tokens_seen": 669015202, | |
| "step": 114450 | |
| }, | |
| { | |
| "epoch": 1.2628864559284585, | |
| "grad_norm": 1.9070016145706177, | |
| "learning_rate": 9.267173104897366e-05, | |
| "loss": 4.3737, | |
| "num_input_tokens_seen": 669892578, | |
| "step": 114600 | |
| }, | |
| { | |
| "epoch": 1.2645394486718202, | |
| "grad_norm": 1.9075013399124146, | |
| "learning_rate": 9.258356965484816e-05, | |
| "loss": 4.3789, | |
| "num_input_tokens_seen": 670773314, | |
| "step": 114750 | |
| }, | |
| { | |
| "epoch": 1.2661924414151822, | |
| "grad_norm": 1.8648816347122192, | |
| "learning_rate": 9.249540826072263e-05, | |
| "loss": 4.3583, | |
| "num_input_tokens_seen": 671644514, | |
| "step": 114900 | |
| }, | |
| { | |
| "epoch": 1.2678454341585441, | |
| "grad_norm": 1.9572055339813232, | |
| "learning_rate": 9.240724686659714e-05, | |
| "loss": 4.3871, | |
| "num_input_tokens_seen": 672523202, | |
| "step": 115050 | |
| }, | |
| { | |
| "epoch": 1.2694984269019058, | |
| "grad_norm": 1.9419187307357788, | |
| "learning_rate": 9.231908547247161e-05, | |
| "loss": 4.3802, | |
| "num_input_tokens_seen": 673387298, | |
| "step": 115200 | |
| }, | |
| { | |
| "epoch": 1.2711514196452678, | |
| "grad_norm": 1.9556363821029663, | |
| "learning_rate": 9.223092407834611e-05, | |
| "loss": 4.3922, | |
| "num_input_tokens_seen": 674262786, | |
| "step": 115350 | |
| }, | |
| { | |
| "epoch": 1.2728044123886297, | |
| "grad_norm": 1.8693435192108154, | |
| "learning_rate": 9.214276268422059e-05, | |
| "loss": 4.3719, | |
| "num_input_tokens_seen": 675145058, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 1.2744574051319915, | |
| "grad_norm": 1.9475206136703491, | |
| "learning_rate": 9.205460129009508e-05, | |
| "loss": 4.38, | |
| "num_input_tokens_seen": 676008962, | |
| "step": 115650 | |
| }, | |
| { | |
| "epoch": 1.2761103978753534, | |
| "grad_norm": 1.8718332052230835, | |
| "learning_rate": 9.196643989596957e-05, | |
| "loss": 4.3734, | |
| "num_input_tokens_seen": 676887042, | |
| "step": 115800 | |
| }, | |
| { | |
| "epoch": 1.2777633906187151, | |
| "grad_norm": 1.8318613767623901, | |
| "learning_rate": 9.187827850184405e-05, | |
| "loss": 4.3857, | |
| "num_input_tokens_seen": 677766690, | |
| "step": 115950 | |
| } | |
| ], | |
| "logging_steps": 150, | |
| "max_steps": 272232, | |
| "num_input_tokens_seen": 678060130, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.04696823656832e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |