| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9404915912031049, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0129366106080207, | |
| "grad_norm": 4.402749538421631, | |
| "learning_rate": 3.8809831824062096e-07, | |
| "loss": 1.5887, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0258732212160414, | |
| "grad_norm": 2.115481376647949, | |
| "learning_rate": 7.761966364812419e-07, | |
| "loss": 1.6039, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03880983182406209, | |
| "grad_norm": 4.390326023101807, | |
| "learning_rate": 1.1642949547218628e-06, | |
| "loss": 1.2713, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0517464424320828, | |
| "grad_norm": 2.4916300773620605, | |
| "learning_rate": 1.5523932729624839e-06, | |
| "loss": 1.4527, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0646830530401035, | |
| "grad_norm": 1.259100317955017, | |
| "learning_rate": 1.940491591203105e-06, | |
| "loss": 1.3702, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07761966364812418, | |
| "grad_norm": 4.703212738037109, | |
| "learning_rate": 2.3285899094437256e-06, | |
| "loss": 1.6409, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09055627425614489, | |
| "grad_norm": 6.5729146003723145, | |
| "learning_rate": 2.7166882276843466e-06, | |
| "loss": 1.6568, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1034928848641656, | |
| "grad_norm": 4.498919486999512, | |
| "learning_rate": 3.1047865459249677e-06, | |
| "loss": 1.4528, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11642949547218628, | |
| "grad_norm": 1.7919808626174927, | |
| "learning_rate": 3.492884864165589e-06, | |
| "loss": 1.3359, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.129366106080207, | |
| "grad_norm": 1.8573850393295288, | |
| "learning_rate": 3.88098318240621e-06, | |
| "loss": 1.0611, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1423027166882277, | |
| "grad_norm": 1.8852155208587646, | |
| "learning_rate": 4.2690815006468305e-06, | |
| "loss": 0.8434, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15523932729624837, | |
| "grad_norm": 1.1542340517044067, | |
| "learning_rate": 4.657179818887451e-06, | |
| "loss": 0.839, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.16817593790426907, | |
| "grad_norm": 2.5517771244049072, | |
| "learning_rate": 5.045278137128073e-06, | |
| "loss": 0.7732, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.18111254851228978, | |
| "grad_norm": 2.299227476119995, | |
| "learning_rate": 5.433376455368693e-06, | |
| "loss": 0.7517, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.19404915912031048, | |
| "grad_norm": 1.0255972146987915, | |
| "learning_rate": 5.821474773609315e-06, | |
| "loss": 0.74, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2069857697283312, | |
| "grad_norm": 6.213005542755127, | |
| "learning_rate": 6.2095730918499354e-06, | |
| "loss": 0.6561, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21992238033635186, | |
| "grad_norm": 1.065950632095337, | |
| "learning_rate": 6.597671410090556e-06, | |
| "loss": 0.6735, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.23285899094437257, | |
| "grad_norm": 1.7846940755844116, | |
| "learning_rate": 6.985769728331178e-06, | |
| "loss": 0.5362, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24579560155239327, | |
| "grad_norm": 1.3279622793197632, | |
| "learning_rate": 7.373868046571798e-06, | |
| "loss": 0.6241, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.258732212160414, | |
| "grad_norm": 2.3642659187316895, | |
| "learning_rate": 7.76196636481242e-06, | |
| "loss": 0.5634, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2716688227684347, | |
| "grad_norm": 1.5506231784820557, | |
| "learning_rate": 8.15006468305304e-06, | |
| "loss": 0.4842, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2846054333764554, | |
| "grad_norm": 1.9322525262832642, | |
| "learning_rate": 8.538163001293661e-06, | |
| "loss": 0.5793, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2975420439844761, | |
| "grad_norm": 2.907057523727417, | |
| "learning_rate": 8.926261319534283e-06, | |
| "loss": 0.6017, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.31047865459249674, | |
| "grad_norm": 1.1939823627471924, | |
| "learning_rate": 9.314359637774902e-06, | |
| "loss": 0.5463, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.32341526520051744, | |
| "grad_norm": 1.6144232749938965, | |
| "learning_rate": 9.702457956015523e-06, | |
| "loss": 0.5068, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.33635187580853815, | |
| "grad_norm": 1.599927306175232, | |
| "learning_rate": 1.0090556274256145e-05, | |
| "loss": 0.4741, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.34928848641655885, | |
| "grad_norm": 1.0453033447265625, | |
| "learning_rate": 1.0478654592496766e-05, | |
| "loss": 0.444, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.36222509702457956, | |
| "grad_norm": 1.6979962587356567, | |
| "learning_rate": 1.0866752910737387e-05, | |
| "loss": 0.5465, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.37516170763260026, | |
| "grad_norm": 1.794843316078186, | |
| "learning_rate": 1.1254851228978009e-05, | |
| "loss": 0.4947, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.38809831824062097, | |
| "grad_norm": 1.308774709701538, | |
| "learning_rate": 1.164294954721863e-05, | |
| "loss": 0.5153, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.40103492884864167, | |
| "grad_norm": 1.2728034257888794, | |
| "learning_rate": 1.203104786545925e-05, | |
| "loss": 0.5684, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4139715394566624, | |
| "grad_norm": 1.312259316444397, | |
| "learning_rate": 1.2419146183699871e-05, | |
| "loss": 0.4749, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4269081500646831, | |
| "grad_norm": 1.1889984607696533, | |
| "learning_rate": 1.2807244501940493e-05, | |
| "loss": 0.4884, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4398447606727037, | |
| "grad_norm": 1.4888752698898315, | |
| "learning_rate": 1.3195342820181112e-05, | |
| "loss": 0.4353, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.45278137128072443, | |
| "grad_norm": 1.481899380683899, | |
| "learning_rate": 1.3583441138421733e-05, | |
| "loss": 0.4649, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.46571798188874514, | |
| "grad_norm": 1.5792471170425415, | |
| "learning_rate": 1.3971539456662355e-05, | |
| "loss": 0.4314, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.47865459249676584, | |
| "grad_norm": 6.622572422027588, | |
| "learning_rate": 1.4359637774902976e-05, | |
| "loss": 0.6105, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.49159120310478654, | |
| "grad_norm": 2.20646333694458, | |
| "learning_rate": 1.4747736093143596e-05, | |
| "loss": 0.5326, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5045278137128072, | |
| "grad_norm": 1.741729974746704, | |
| "learning_rate": 1.5135834411384215e-05, | |
| "loss": 0.5013, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.517464424320828, | |
| "grad_norm": 1.5974177122116089, | |
| "learning_rate": 1.552393272962484e-05, | |
| "loss": 0.4441, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5304010349288486, | |
| "grad_norm": 1.5022289752960205, | |
| "learning_rate": 1.591203104786546e-05, | |
| "loss": 0.477, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5433376455368694, | |
| "grad_norm": 2.8963606357574463, | |
| "learning_rate": 1.630012936610608e-05, | |
| "loss": 0.4674, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.55627425614489, | |
| "grad_norm": 1.0391566753387451, | |
| "learning_rate": 1.66882276843467e-05, | |
| "loss": 0.4624, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5692108667529108, | |
| "grad_norm": 2.012328624725342, | |
| "learning_rate": 1.7076326002587322e-05, | |
| "loss": 0.4798, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5821474773609314, | |
| "grad_norm": 1.6585012674331665, | |
| "learning_rate": 1.7464424320827943e-05, | |
| "loss": 0.3837, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5950840879689522, | |
| "grad_norm": 2.2663848400115967, | |
| "learning_rate": 1.7852522639068567e-05, | |
| "loss": 0.4888, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.6080206985769728, | |
| "grad_norm": 1.234695553779602, | |
| "learning_rate": 1.8240620957309184e-05, | |
| "loss": 0.3898, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6209573091849935, | |
| "grad_norm": 1.9593554735183716, | |
| "learning_rate": 1.8628719275549805e-05, | |
| "loss": 0.4126, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6338939197930142, | |
| "grad_norm": 1.539140224456787, | |
| "learning_rate": 1.901681759379043e-05, | |
| "loss": 0.3865, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6468305304010349, | |
| "grad_norm": 1.70127534866333, | |
| "learning_rate": 1.9404915912031046e-05, | |
| "loss": 0.3849, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6468305304010349, | |
| "eval_loss": 0.49836617708206177, | |
| "eval_runtime": 53.9941, | |
| "eval_samples_per_second": 3.704, | |
| "eval_steps_per_second": 1.852, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6597671410090556, | |
| "grad_norm": 1.2516582012176514, | |
| "learning_rate": 1.979301423027167e-05, | |
| "loss": 0.4551, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6727037516170763, | |
| "grad_norm": 2.031634569168091, | |
| "learning_rate": 2.018111254851229e-05, | |
| "loss": 0.4455, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.685640362225097, | |
| "grad_norm": 1.4083653688430786, | |
| "learning_rate": 2.056921086675291e-05, | |
| "loss": 0.3805, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6985769728331177, | |
| "grad_norm": 1.8752052783966064, | |
| "learning_rate": 2.0957309184993532e-05, | |
| "loss": 0.4295, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.7115135834411385, | |
| "grad_norm": 2.337958574295044, | |
| "learning_rate": 2.1345407503234156e-05, | |
| "loss": 0.3906, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7244501940491591, | |
| "grad_norm": 1.7030471563339233, | |
| "learning_rate": 2.1733505821474773e-05, | |
| "loss": 0.4151, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7373868046571799, | |
| "grad_norm": 2.75461745262146, | |
| "learning_rate": 2.2121604139715397e-05, | |
| "loss": 0.4353, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7503234152652005, | |
| "grad_norm": 1.3487416505813599, | |
| "learning_rate": 2.2509702457956018e-05, | |
| "loss": 0.3256, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7632600258732212, | |
| "grad_norm": 2.2425625324249268, | |
| "learning_rate": 2.2897800776196635e-05, | |
| "loss": 0.3754, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7761966364812419, | |
| "grad_norm": 2.3429338932037354, | |
| "learning_rate": 2.328589909443726e-05, | |
| "loss": 0.4642, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7891332470892626, | |
| "grad_norm": 1.7922463417053223, | |
| "learning_rate": 2.3673997412677876e-05, | |
| "loss": 0.4097, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.8020698576972833, | |
| "grad_norm": 1.4449383020401, | |
| "learning_rate": 2.40620957309185e-05, | |
| "loss": 0.4068, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.815006468305304, | |
| "grad_norm": 2.2355751991271973, | |
| "learning_rate": 2.445019404915912e-05, | |
| "loss": 0.4196, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.8279430789133247, | |
| "grad_norm": 1.9109554290771484, | |
| "learning_rate": 2.4838292367399742e-05, | |
| "loss": 0.4531, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8408796895213454, | |
| "grad_norm": 2.0991272926330566, | |
| "learning_rate": 2.5226390685640362e-05, | |
| "loss": 0.4161, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8538163001293662, | |
| "grad_norm": 3.535731554031372, | |
| "learning_rate": 2.5614489003880986e-05, | |
| "loss": 0.3607, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8667529107373868, | |
| "grad_norm": 1.3505184650421143, | |
| "learning_rate": 2.6002587322121604e-05, | |
| "loss": 0.401, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.8796895213454075, | |
| "grad_norm": 1.0390079021453857, | |
| "learning_rate": 2.6390685640362224e-05, | |
| "loss": 0.411, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8926261319534282, | |
| "grad_norm": 4.166248798370361, | |
| "learning_rate": 2.677878395860285e-05, | |
| "loss": 0.456, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.9055627425614489, | |
| "grad_norm": 1.9140669107437134, | |
| "learning_rate": 2.7166882276843466e-05, | |
| "loss": 0.4109, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.9184993531694696, | |
| "grad_norm": 1.4948009252548218, | |
| "learning_rate": 2.755498059508409e-05, | |
| "loss": 0.4113, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.9314359637774903, | |
| "grad_norm": 1.2608532905578613, | |
| "learning_rate": 2.794307891332471e-05, | |
| "loss": 0.4074, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.944372574385511, | |
| "grad_norm": 1.6317986249923706, | |
| "learning_rate": 2.833117723156533e-05, | |
| "loss": 0.4994, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.9573091849935317, | |
| "grad_norm": 2.5210256576538086, | |
| "learning_rate": 2.871927554980595e-05, | |
| "loss": 0.3803, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9702457956015524, | |
| "grad_norm": 1.3882018327713013, | |
| "learning_rate": 2.9107373868046576e-05, | |
| "loss": 0.3962, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9831824062095731, | |
| "grad_norm": 2.999624013900757, | |
| "learning_rate": 2.9495472186287193e-05, | |
| "loss": 0.3772, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9961190168175937, | |
| "grad_norm": 1.3309364318847656, | |
| "learning_rate": 2.9883570504527814e-05, | |
| "loss": 0.3445, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.0090556274256144, | |
| "grad_norm": 1.9435688257217407, | |
| "learning_rate": 2.99996206183792e-05, | |
| "loss": 0.3399, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.0219922380336353, | |
| "grad_norm": 1.2193248271942139, | |
| "learning_rate": 2.999776246888373e-05, | |
| "loss": 0.3159, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.034928848641656, | |
| "grad_norm": 1.2065479755401611, | |
| "learning_rate": 2.999435606075697e-05, | |
| "loss": 0.3086, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0478654592496766, | |
| "grad_norm": 2.735750198364258, | |
| "learning_rate": 2.9989401745651436e-05, | |
| "loss": 0.3718, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.0608020698576972, | |
| "grad_norm": 2.377659320831299, | |
| "learning_rate": 2.998290003501415e-05, | |
| "loss": 0.2935, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.073738680465718, | |
| "grad_norm": 1.961264967918396, | |
| "learning_rate": 2.997485160003388e-05, | |
| "loss": 0.3441, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.0866752910737387, | |
| "grad_norm": 1.8460434675216675, | |
| "learning_rate": 2.9965257271571833e-05, | |
| "loss": 0.3485, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.0996119016817594, | |
| "grad_norm": 1.7050330638885498, | |
| "learning_rate": 2.995411804007586e-05, | |
| "loss": 0.3739, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.11254851228978, | |
| "grad_norm": 2.2543892860412598, | |
| "learning_rate": 2.994143505547826e-05, | |
| "loss": 0.307, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.1254851228978007, | |
| "grad_norm": 3.6111979484558105, | |
| "learning_rate": 2.9927209627077032e-05, | |
| "loss": 0.2837, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.1384217335058215, | |
| "grad_norm": 1.4579052925109863, | |
| "learning_rate": 2.9911443223400712e-05, | |
| "loss": 0.2957, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.1513583441138422, | |
| "grad_norm": 2.5956053733825684, | |
| "learning_rate": 2.9894137472056805e-05, | |
| "loss": 0.2659, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.1642949547218628, | |
| "grad_norm": 2.876161813735962, | |
| "learning_rate": 2.9875294159563723e-05, | |
| "loss": 0.3203, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.1772315653298835, | |
| "grad_norm": 2.269209384918213, | |
| "learning_rate": 2.9854915231166383e-05, | |
| "loss": 0.3527, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.1901681759379044, | |
| "grad_norm": 1.9031386375427246, | |
| "learning_rate": 2.983300279063539e-05, | |
| "loss": 0.3527, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.203104786545925, | |
| "grad_norm": 1.621424913406372, | |
| "learning_rate": 2.9809559100049852e-05, | |
| "loss": 0.2666, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.2160413971539457, | |
| "grad_norm": 4.12821626663208, | |
| "learning_rate": 2.9784586579563867e-05, | |
| "loss": 0.2957, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.2289780077619663, | |
| "grad_norm": 2.230564832687378, | |
| "learning_rate": 2.9758087807156683e-05, | |
| "loss": 0.3305, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.2419146183699872, | |
| "grad_norm": 2.618791103363037, | |
| "learning_rate": 2.9730065518366562e-05, | |
| "loss": 0.3508, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.2548512289780078, | |
| "grad_norm": 2.047571897506714, | |
| "learning_rate": 2.9700522606008392e-05, | |
| "loss": 0.2711, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.2677878395860285, | |
| "grad_norm": 2.2815372943878174, | |
| "learning_rate": 2.9669462119875037e-05, | |
| "loss": 0.3719, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.2807244501940491, | |
| "grad_norm": 2.5117783546447754, | |
| "learning_rate": 2.963688726642252e-05, | |
| "loss": 0.2837, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.2936610608020698, | |
| "grad_norm": 1.2821422815322876, | |
| "learning_rate": 2.9602801408439003e-05, | |
| "loss": 0.3029, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.2936610608020698, | |
| "eval_loss": 0.46682319045066833, | |
| "eval_runtime": 53.9865, | |
| "eval_samples_per_second": 3.705, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.3065976714100906, | |
| "grad_norm": 1.465987205505371, | |
| "learning_rate": 2.956720806469762e-05, | |
| "loss": 0.3424, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.3195342820181113, | |
| "grad_norm": 2.9073352813720703, | |
| "learning_rate": 2.9530110909593264e-05, | |
| "loss": 0.3734, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.332470892626132, | |
| "grad_norm": 1.9318575859069824, | |
| "learning_rate": 2.949151377276323e-05, | |
| "loss": 0.3153, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.3454075032341526, | |
| "grad_norm": 2.4026870727539062, | |
| "learning_rate": 2.94514206386919e-05, | |
| "loss": 0.2888, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.3583441138421732, | |
| "grad_norm": 1.4837349653244019, | |
| "learning_rate": 2.9409835646299393e-05, | |
| "loss": 0.221, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.371280724450194, | |
| "grad_norm": 1.4667383432388306, | |
| "learning_rate": 2.9366763088514306e-05, | |
| "loss": 0.2935, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.3842173350582148, | |
| "grad_norm": 1.7328715324401855, | |
| "learning_rate": 2.932220741183055e-05, | |
| "loss": 0.3634, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.3971539456662354, | |
| "grad_norm": 1.5297213792800903, | |
| "learning_rate": 2.9276173215848297e-05, | |
| "loss": 0.282, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.4100905562742563, | |
| "grad_norm": 1.0233724117279053, | |
| "learning_rate": 2.9228665252799187e-05, | |
| "loss": 0.3941, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.4230271668822767, | |
| "grad_norm": 1.3520108461380005, | |
| "learning_rate": 2.917968842705572e-05, | |
| "loss": 0.3211, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.4359637774902976, | |
| "grad_norm": 2.3806064128875732, | |
| "learning_rate": 2.9129247794624977e-05, | |
| "loss": 0.2752, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.4489003880983182, | |
| "grad_norm": 1.543283224105835, | |
| "learning_rate": 2.907734856262666e-05, | |
| "loss": 0.3198, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.4618369987063389, | |
| "grad_norm": 4.661839962005615, | |
| "learning_rate": 2.9023996088755573e-05, | |
| "loss": 0.3588, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.4747736093143597, | |
| "grad_norm": 0.8752655386924744, | |
| "learning_rate": 2.8969195880728497e-05, | |
| "loss": 0.3085, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.4877102199223804, | |
| "grad_norm": 1.2036000490188599, | |
| "learning_rate": 2.891295359571565e-05, | |
| "loss": 0.2737, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.500646830530401, | |
| "grad_norm": 1.5076147317886353, | |
| "learning_rate": 2.8855275039756653e-05, | |
| "loss": 0.2985, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.5135834411384217, | |
| "grad_norm": 1.462025761604309, | |
| "learning_rate": 2.879616616716118e-05, | |
| "loss": 0.3275, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.5265200517464423, | |
| "grad_norm": 3.9805407524108887, | |
| "learning_rate": 2.873563307989427e-05, | |
| "loss": 0.267, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.5394566623544632, | |
| "grad_norm": 1.7805012464523315, | |
| "learning_rate": 2.8673682026946385e-05, | |
| "loss": 0.2511, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.5523932729624839, | |
| "grad_norm": 2.0648598670959473, | |
| "learning_rate": 2.8610319403688362e-05, | |
| "loss": 0.3148, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.5653298835705045, | |
| "grad_norm": 1.9050356149673462, | |
| "learning_rate": 2.854555175121114e-05, | |
| "loss": 0.3273, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.5782664941785254, | |
| "grad_norm": 2.525097370147705, | |
| "learning_rate": 2.847938575565055e-05, | |
| "loss": 0.2969, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.5912031047865458, | |
| "grad_norm": 2.5983824729919434, | |
| "learning_rate": 2.8411828247497072e-05, | |
| "loss": 0.2368, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.6041397153945667, | |
| "grad_norm": 1.126298189163208, | |
| "learning_rate": 2.83428862008907e-05, | |
| "loss": 0.2437, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.6170763260025873, | |
| "grad_norm": 2.4499635696411133, | |
| "learning_rate": 2.827256673290099e-05, | |
| "loss": 0.269, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.630012936610608, | |
| "grad_norm": 1.302224040031433, | |
| "learning_rate": 2.8200877102792354e-05, | |
| "loss": 0.2963, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.6429495472186288, | |
| "grad_norm": 3.0382964611053467, | |
| "learning_rate": 2.8127824711274648e-05, | |
| "loss": 0.2381, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.6558861578266493, | |
| "grad_norm": 1.313506007194519, | |
| "learning_rate": 2.8053417099739195e-05, | |
| "loss": 0.2552, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.6688227684346701, | |
| "grad_norm": 1.7527904510498047, | |
| "learning_rate": 2.7977661949480256e-05, | |
| "loss": 0.2691, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.6817593790426908, | |
| "grad_norm": 2.4050045013427734, | |
| "learning_rate": 2.7900567080902077e-05, | |
| "loss": 0.2874, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.6946959896507114, | |
| "grad_norm": 1.7919877767562866, | |
| "learning_rate": 2.7822140452711557e-05, | |
| "loss": 0.2413, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.7076326002587323, | |
| "grad_norm": 2.414724349975586, | |
| "learning_rate": 2.774239016109666e-05, | |
| "loss": 0.291, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.720569210866753, | |
| "grad_norm": 1.6505646705627441, | |
| "learning_rate": 2.766132443889063e-05, | |
| "loss": 0.3146, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.7335058214747736, | |
| "grad_norm": 2.0308473110198975, | |
| "learning_rate": 2.757895165472208e-05, | |
| "loss": 0.3366, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.7464424320827943, | |
| "grad_norm": 1.5665441751480103, | |
| "learning_rate": 2.7495280312151075e-05, | |
| "loss": 0.3427, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.759379042690815, | |
| "grad_norm": 1.963440179824829, | |
| "learning_rate": 2.74103190487913e-05, | |
| "loss": 0.2648, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.7723156532988358, | |
| "grad_norm": 2.129335403442383, | |
| "learning_rate": 2.732407663541837e-05, | |
| "loss": 0.3138, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.7852522639068564, | |
| "grad_norm": 2.803375005722046, | |
| "learning_rate": 2.7236561975064396e-05, | |
| "loss": 0.3078, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.798188874514877, | |
| "grad_norm": 2.7263729572296143, | |
| "learning_rate": 2.7147784102098906e-05, | |
| "loss": 0.269, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.811125485122898, | |
| "grad_norm": 2.3668291568756104, | |
| "learning_rate": 2.7057752181296207e-05, | |
| "loss": 0.2619, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.8240620957309184, | |
| "grad_norm": 2.556081533432007, | |
| "learning_rate": 2.6966475506889274e-05, | |
| "loss": 0.3413, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.8369987063389392, | |
| "grad_norm": 2.335906744003296, | |
| "learning_rate": 2.687396350161028e-05, | |
| "loss": 0.3316, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.84993531694696, | |
| "grad_norm": 1.4382126331329346, | |
| "learning_rate": 2.6780225715717873e-05, | |
| "loss": 0.2713, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.8628719275549805, | |
| "grad_norm": 1.600113868713379, | |
| "learning_rate": 2.6685271826011267e-05, | |
| "loss": 0.373, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.8758085381630014, | |
| "grad_norm": 5.542492866516113, | |
| "learning_rate": 2.658911163483128e-05, | |
| "loss": 0.3024, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.8887451487710218, | |
| "grad_norm": 2.238302707672119, | |
| "learning_rate": 2.649175506904843e-05, | |
| "loss": 0.2843, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.9016817593790427, | |
| "grad_norm": 2.0862436294555664, | |
| "learning_rate": 2.6393212179038136e-05, | |
| "loss": 0.3868, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.9146183699870634, | |
| "grad_norm": 1.8203462362289429, | |
| "learning_rate": 2.6293493137643202e-05, | |
| "loss": 0.2422, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.927554980595084, | |
| "grad_norm": 1.6436854600906372, | |
| "learning_rate": 2.619260823912364e-05, | |
| "loss": 0.2936, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.9404915912031049, | |
| "grad_norm": 1.905551791191101, | |
| "learning_rate": 2.609056789809399e-05, | |
| "loss": 0.336, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.9404915912031049, | |
| "eval_loss": 0.4133800268173218, | |
| "eval_runtime": 54.0053, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3865, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 8.751317925557699e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |