| { | |
| "best_metric": 0.796756082345602, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat\\checkpoint-3062", | |
| "epoch": 14.948571428571428, | |
| "eval_steps": 500, | |
| "global_step": 3270, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045714285714285714, | |
| "grad_norm": 13.994832992553711, | |
| "learning_rate": 1.5290519877675841e-06, | |
| "loss": 2.7494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09142857142857143, | |
| "grad_norm": 7.420119762420654, | |
| "learning_rate": 3.0581039755351682e-06, | |
| "loss": 2.7395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13714285714285715, | |
| "grad_norm": 5.467243194580078, | |
| "learning_rate": 4.587155963302753e-06, | |
| "loss": 2.7049, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 7.835602760314941, | |
| "learning_rate": 6.1162079510703365e-06, | |
| "loss": 2.6367, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 13.763399124145508, | |
| "learning_rate": 7.645259938837921e-06, | |
| "loss": 2.5592, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2742857142857143, | |
| "grad_norm": 10.583270072937012, | |
| "learning_rate": 9.174311926605506e-06, | |
| "loss": 2.4444, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 19.168621063232422, | |
| "learning_rate": 1.070336391437309e-05, | |
| "loss": 2.3336, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "grad_norm": 20.13259506225586, | |
| "learning_rate": 1.2232415902140673e-05, | |
| "loss": 2.1877, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4114285714285714, | |
| "grad_norm": 28.141359329223633, | |
| "learning_rate": 1.3761467889908258e-05, | |
| "loss": 2.0578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 36.60035705566406, | |
| "learning_rate": 1.5290519877675842e-05, | |
| "loss": 1.9729, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5028571428571429, | |
| "grad_norm": 27.167247772216797, | |
| "learning_rate": 1.6819571865443427e-05, | |
| "loss": 1.884, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5485714285714286, | |
| "grad_norm": 21.56601905822754, | |
| "learning_rate": 1.834862385321101e-05, | |
| "loss": 1.7821, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5942857142857143, | |
| "grad_norm": 18.523468017578125, | |
| "learning_rate": 1.9877675840978592e-05, | |
| "loss": 1.8148, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 14.976977348327637, | |
| "learning_rate": 2.140672782874618e-05, | |
| "loss": 1.6829, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 14.441283226013184, | |
| "learning_rate": 2.2935779816513765e-05, | |
| "loss": 1.6312, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7314285714285714, | |
| "grad_norm": 17.649080276489258, | |
| "learning_rate": 2.4464831804281346e-05, | |
| "loss": 1.6482, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7771428571428571, | |
| "grad_norm": 19.691490173339844, | |
| "learning_rate": 2.5993883792048927e-05, | |
| "loss": 1.5693, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8228571428571428, | |
| "grad_norm": 12.245804786682129, | |
| "learning_rate": 2.7522935779816515e-05, | |
| "loss": 1.6267, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8685714285714285, | |
| "grad_norm": 24.526466369628906, | |
| "learning_rate": 2.90519877675841e-05, | |
| "loss": 1.5964, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 14.706289291381836, | |
| "learning_rate": 3.0581039755351684e-05, | |
| "loss": 1.6017, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 12.513092041015625, | |
| "learning_rate": 3.211009174311927e-05, | |
| "loss": 1.5891, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9965714285714286, | |
| "eval_accuracy": 0.5723019338739863, | |
| "eval_loss": 1.383291244506836, | |
| "eval_runtime": 74.6009, | |
| "eval_samples_per_second": 107.438, | |
| "eval_steps_per_second": 3.365, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.0057142857142858, | |
| "grad_norm": 9.570089340209961, | |
| "learning_rate": 3.363914373088685e-05, | |
| "loss": 1.4337, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0514285714285714, | |
| "grad_norm": 29.601459503173828, | |
| "learning_rate": 3.516819571865443e-05, | |
| "loss": 1.4987, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0971428571428572, | |
| "grad_norm": 14.568526268005371, | |
| "learning_rate": 3.669724770642202e-05, | |
| "loss": 1.4594, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 9.901498794555664, | |
| "learning_rate": 3.822629969418961e-05, | |
| "loss": 1.4964, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1885714285714286, | |
| "grad_norm": 11.662745475769043, | |
| "learning_rate": 3.9755351681957185e-05, | |
| "loss": 1.4872, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2342857142857142, | |
| "grad_norm": 8.338129043579102, | |
| "learning_rate": 4.1284403669724776e-05, | |
| "loss": 1.3592, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 12.640501022338867, | |
| "learning_rate": 4.281345565749236e-05, | |
| "loss": 1.4165, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.3257142857142856, | |
| "grad_norm": 9.851750373840332, | |
| "learning_rate": 4.434250764525994e-05, | |
| "loss": 1.4671, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 9.80663013458252, | |
| "learning_rate": 4.587155963302753e-05, | |
| "loss": 1.4069, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.4171428571428573, | |
| "grad_norm": 10.75167179107666, | |
| "learning_rate": 4.740061162079511e-05, | |
| "loss": 1.3966, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.4628571428571429, | |
| "grad_norm": 9.546366691589355, | |
| "learning_rate": 4.892966360856269e-05, | |
| "loss": 1.3365, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.5085714285714285, | |
| "grad_norm": 11.726640701293945, | |
| "learning_rate": 4.994903160040775e-05, | |
| "loss": 1.4017, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.5542857142857143, | |
| "grad_norm": 9.12558650970459, | |
| "learning_rate": 4.977913693510024e-05, | |
| "loss": 1.3402, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 7.8366804122924805, | |
| "learning_rate": 4.9609242269792734e-05, | |
| "loss": 1.3675, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.6457142857142857, | |
| "grad_norm": 7.4768805503845215, | |
| "learning_rate": 4.943934760448522e-05, | |
| "loss": 1.3559, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.6914285714285713, | |
| "grad_norm": 8.65304183959961, | |
| "learning_rate": 4.926945293917771e-05, | |
| "loss": 1.3973, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.737142857142857, | |
| "grad_norm": 8.800814628601074, | |
| "learning_rate": 4.9099558273870206e-05, | |
| "loss": 1.2501, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.782857142857143, | |
| "grad_norm": 14.658060073852539, | |
| "learning_rate": 4.892966360856269e-05, | |
| "loss": 1.287, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 9.586373329162598, | |
| "learning_rate": 4.8759768943255185e-05, | |
| "loss": 1.3249, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.8742857142857143, | |
| "grad_norm": 12.57496166229248, | |
| "learning_rate": 4.858987427794767e-05, | |
| "loss": 1.3564, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 9.330473899841309, | |
| "learning_rate": 4.8419979612640164e-05, | |
| "loss": 1.2967, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.9657142857142857, | |
| "grad_norm": 8.545197486877441, | |
| "learning_rate": 4.8250084947332657e-05, | |
| "loss": 1.2997, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.9977142857142858, | |
| "eval_accuracy": 0.6699937616968185, | |
| "eval_loss": 1.0830751657485962, | |
| "eval_runtime": 74.7614, | |
| "eval_samples_per_second": 107.208, | |
| "eval_steps_per_second": 3.357, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 2.0114285714285716, | |
| "grad_norm": 7.490045547485352, | |
| "learning_rate": 4.808019028202514e-05, | |
| "loss": 1.258, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.057142857142857, | |
| "grad_norm": 8.006925582885742, | |
| "learning_rate": 4.7910295616717635e-05, | |
| "loss": 1.168, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.1028571428571428, | |
| "grad_norm": 12.528056144714355, | |
| "learning_rate": 4.774040095141013e-05, | |
| "loss": 1.2195, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.1485714285714286, | |
| "grad_norm": 9.448918342590332, | |
| "learning_rate": 4.7570506286102614e-05, | |
| "loss": 1.2242, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.1942857142857144, | |
| "grad_norm": 7.972462177276611, | |
| "learning_rate": 4.740061162079511e-05, | |
| "loss": 1.1925, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 10.068849563598633, | |
| "learning_rate": 4.72307169554876e-05, | |
| "loss": 1.2521, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 9.536931037902832, | |
| "learning_rate": 4.706082229018009e-05, | |
| "loss": 1.2375, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.3314285714285714, | |
| "grad_norm": 7.058177471160889, | |
| "learning_rate": 4.6890927624872586e-05, | |
| "loss": 1.1762, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.3771428571428572, | |
| "grad_norm": 8.200982093811035, | |
| "learning_rate": 4.672103295956507e-05, | |
| "loss": 1.259, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.422857142857143, | |
| "grad_norm": 6.11261510848999, | |
| "learning_rate": 4.6551138294257565e-05, | |
| "loss": 1.2291, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.4685714285714284, | |
| "grad_norm": 8.771502494812012, | |
| "learning_rate": 4.638124362895006e-05, | |
| "loss": 1.2237, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.5142857142857142, | |
| "grad_norm": 11.995628356933594, | |
| "learning_rate": 4.6211348963642544e-05, | |
| "loss": 1.2349, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 8.15999698638916, | |
| "learning_rate": 4.604145429833504e-05, | |
| "loss": 1.1786, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.605714285714286, | |
| "grad_norm": 7.252849578857422, | |
| "learning_rate": 4.587155963302753e-05, | |
| "loss": 1.1285, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.6514285714285712, | |
| "grad_norm": 8.760148048400879, | |
| "learning_rate": 4.5701664967720016e-05, | |
| "loss": 1.074, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.697142857142857, | |
| "grad_norm": 5.591124057769775, | |
| "learning_rate": 4.553177030241251e-05, | |
| "loss": 1.104, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.742857142857143, | |
| "grad_norm": 7.468674659729004, | |
| "learning_rate": 4.5361875637104995e-05, | |
| "loss": 1.1936, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.7885714285714287, | |
| "grad_norm": 7.683737754821777, | |
| "learning_rate": 4.519198097179749e-05, | |
| "loss": 1.1574, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.8342857142857145, | |
| "grad_norm": 12.986687660217285, | |
| "learning_rate": 4.502208630648998e-05, | |
| "loss": 1.1513, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 8.037307739257812, | |
| "learning_rate": 4.4852191641182466e-05, | |
| "loss": 1.1537, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.9257142857142857, | |
| "grad_norm": 8.727031707763672, | |
| "learning_rate": 4.468229697587496e-05, | |
| "loss": 1.1823, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.9714285714285715, | |
| "grad_norm": 7.474994659423828, | |
| "learning_rate": 4.451240231056745e-05, | |
| "loss": 1.1166, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.998857142857143, | |
| "eval_accuracy": 0.6958203368683719, | |
| "eval_loss": 0.9937148094177246, | |
| "eval_runtime": 75.7204, | |
| "eval_samples_per_second": 105.85, | |
| "eval_steps_per_second": 3.315, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 3.0171428571428573, | |
| "grad_norm": 5.9896016120910645, | |
| "learning_rate": 4.434250764525994e-05, | |
| "loss": 1.1378, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.0628571428571427, | |
| "grad_norm": 5.852768898010254, | |
| "learning_rate": 4.417261297995243e-05, | |
| "loss": 1.0542, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.1085714285714285, | |
| "grad_norm": 7.916086673736572, | |
| "learning_rate": 4.400271831464492e-05, | |
| "loss": 1.0331, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.1542857142857144, | |
| "grad_norm": 8.959929466247559, | |
| "learning_rate": 4.383282364933741e-05, | |
| "loss": 1.0943, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 6.69697904586792, | |
| "learning_rate": 4.36629289840299e-05, | |
| "loss": 1.0978, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.2457142857142856, | |
| "grad_norm": 7.420085430145264, | |
| "learning_rate": 4.349303431872239e-05, | |
| "loss": 1.0588, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.2914285714285714, | |
| "grad_norm": 10.829694747924805, | |
| "learning_rate": 4.332313965341488e-05, | |
| "loss": 1.0838, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.337142857142857, | |
| "grad_norm": 6.954169273376465, | |
| "learning_rate": 4.3153244988107375e-05, | |
| "loss": 1.1126, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.382857142857143, | |
| "grad_norm": 6.538149833679199, | |
| "learning_rate": 4.298335032279987e-05, | |
| "loss": 1.1049, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 11.640555381774902, | |
| "learning_rate": 4.281345565749236e-05, | |
| "loss": 1.0577, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.474285714285714, | |
| "grad_norm": 7.022554397583008, | |
| "learning_rate": 4.264356099218485e-05, | |
| "loss": 1.1454, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 9.619643211364746, | |
| "learning_rate": 4.247366632687734e-05, | |
| "loss": 1.0374, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.565714285714286, | |
| "grad_norm": 8.229997634887695, | |
| "learning_rate": 4.230377166156983e-05, | |
| "loss": 1.0354, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.611428571428571, | |
| "grad_norm": 8.94089126586914, | |
| "learning_rate": 4.213387699626232e-05, | |
| "loss": 1.1144, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.657142857142857, | |
| "grad_norm": 7.949928283691406, | |
| "learning_rate": 4.196398233095481e-05, | |
| "loss": 1.0678, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.702857142857143, | |
| "grad_norm": 6.979115009307861, | |
| "learning_rate": 4.1794087665647304e-05, | |
| "loss": 1.0945, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.7485714285714287, | |
| "grad_norm": 8.669636726379395, | |
| "learning_rate": 4.162419300033979e-05, | |
| "loss": 1.0521, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.7942857142857145, | |
| "grad_norm": 6.849328994750977, | |
| "learning_rate": 4.145429833503228e-05, | |
| "loss": 1.0513, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 7.107924461364746, | |
| "learning_rate": 4.1284403669724776e-05, | |
| "loss": 1.0477, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.8857142857142857, | |
| "grad_norm": 6.533900737762451, | |
| "learning_rate": 4.111450900441726e-05, | |
| "loss": 1.0513, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.9314285714285715, | |
| "grad_norm": 6.826801776885986, | |
| "learning_rate": 4.0944614339109755e-05, | |
| "loss": 1.0932, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.977142857142857, | |
| "grad_norm": 6.449113845825195, | |
| "learning_rate": 4.077471967380224e-05, | |
| "loss": 1.0464, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7231441048034934, | |
| "eval_loss": 0.9180014729499817, | |
| "eval_runtime": 74.9581, | |
| "eval_samples_per_second": 106.926, | |
| "eval_steps_per_second": 3.349, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 4.022857142857143, | |
| "grad_norm": 6.743358135223389, | |
| "learning_rate": 4.0604825008494734e-05, | |
| "loss": 1.0845, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.0685714285714285, | |
| "grad_norm": 6.779079437255859, | |
| "learning_rate": 4.043493034318723e-05, | |
| "loss": 1.0415, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.114285714285714, | |
| "grad_norm": 8.849162101745605, | |
| "learning_rate": 4.026503567787971e-05, | |
| "loss": 1.0487, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 7.157181739807129, | |
| "learning_rate": 4.0095141012572206e-05, | |
| "loss": 1.0647, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.2057142857142855, | |
| "grad_norm": 8.016735076904297, | |
| "learning_rate": 3.99252463472647e-05, | |
| "loss": 1.0493, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.251428571428572, | |
| "grad_norm": 8.14920711517334, | |
| "learning_rate": 3.9755351681957185e-05, | |
| "loss": 1.0228, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.297142857142857, | |
| "grad_norm": 6.980301856994629, | |
| "learning_rate": 3.958545701664968e-05, | |
| "loss": 0.9977, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.3428571428571425, | |
| "grad_norm": 6.754297256469727, | |
| "learning_rate": 3.941556235134217e-05, | |
| "loss": 1.025, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.388571428571429, | |
| "grad_norm": 6.082598686218262, | |
| "learning_rate": 3.9245667686034656e-05, | |
| "loss": 0.9734, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.434285714285714, | |
| "grad_norm": 9.236204147338867, | |
| "learning_rate": 3.907577302072715e-05, | |
| "loss": 0.9897, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 6.07050085067749, | |
| "learning_rate": 3.890587835541964e-05, | |
| "loss": 1.0549, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.525714285714286, | |
| "grad_norm": 8.898210525512695, | |
| "learning_rate": 3.8735983690112135e-05, | |
| "loss": 1.0703, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 6.365227699279785, | |
| "learning_rate": 3.856608902480463e-05, | |
| "loss": 0.9674, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.617142857142857, | |
| "grad_norm": 6.180821895599365, | |
| "learning_rate": 3.8396194359497114e-05, | |
| "loss": 0.9661, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.662857142857143, | |
| "grad_norm": 7.927034854888916, | |
| "learning_rate": 3.822629969418961e-05, | |
| "loss": 1.025, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.708571428571428, | |
| "grad_norm": 6.064193248748779, | |
| "learning_rate": 3.80564050288821e-05, | |
| "loss": 1.0494, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.7542857142857144, | |
| "grad_norm": 7.2729668617248535, | |
| "learning_rate": 3.7886510363574586e-05, | |
| "loss": 1.0002, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 8.703302383422852, | |
| "learning_rate": 3.771661569826708e-05, | |
| "loss": 1.001, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.845714285714286, | |
| "grad_norm": 5.9366583824157715, | |
| "learning_rate": 3.7546721032959565e-05, | |
| "loss": 0.8903, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.8914285714285715, | |
| "grad_norm": 10.52004337310791, | |
| "learning_rate": 3.737682636765206e-05, | |
| "loss": 1.0021, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.937142857142857, | |
| "grad_norm": 6.183305740356445, | |
| "learning_rate": 3.720693170234455e-05, | |
| "loss": 0.9574, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.982857142857143, | |
| "grad_norm": 7.366205215454102, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.982, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.996571428571428, | |
| "eval_accuracy": 0.743231441048035, | |
| "eval_loss": 0.8399370312690735, | |
| "eval_runtime": 75.6387, | |
| "eval_samples_per_second": 105.964, | |
| "eval_steps_per_second": 3.318, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 5.0285714285714285, | |
| "grad_norm": 6.932504177093506, | |
| "learning_rate": 3.686714237172953e-05, | |
| "loss": 1.0264, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.074285714285715, | |
| "grad_norm": 5.84490966796875, | |
| "learning_rate": 3.669724770642202e-05, | |
| "loss": 0.9594, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "grad_norm": 6.8914475440979, | |
| "learning_rate": 3.652735304111451e-05, | |
| "loss": 0.918, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 5.1657142857142855, | |
| "grad_norm": 6.1007161140441895, | |
| "learning_rate": 3.6357458375807e-05, | |
| "loss": 1.0036, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 5.211428571428572, | |
| "grad_norm": 8.02859115600586, | |
| "learning_rate": 3.6187563710499494e-05, | |
| "loss": 0.9655, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.257142857142857, | |
| "grad_norm": 7.857163906097412, | |
| "learning_rate": 3.601766904519198e-05, | |
| "loss": 0.9567, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.3028571428571425, | |
| "grad_norm": 7.495018005371094, | |
| "learning_rate": 3.584777437988447e-05, | |
| "loss": 0.9226, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 5.348571428571429, | |
| "grad_norm": 8.65245532989502, | |
| "learning_rate": 3.567787971457696e-05, | |
| "loss": 0.8992, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 5.394285714285714, | |
| "grad_norm": 8.458373069763184, | |
| "learning_rate": 3.550798504926945e-05, | |
| "loss": 0.9539, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "grad_norm": 6.742293357849121, | |
| "learning_rate": 3.5338090383961945e-05, | |
| "loss": 0.9382, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 5.485714285714286, | |
| "grad_norm": 6.219183921813965, | |
| "learning_rate": 3.516819571865443e-05, | |
| "loss": 0.9673, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.531428571428571, | |
| "grad_norm": 6.372159004211426, | |
| "learning_rate": 3.4998301053346924e-05, | |
| "loss": 0.9558, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 5.577142857142857, | |
| "grad_norm": 9.132979393005371, | |
| "learning_rate": 3.482840638803942e-05, | |
| "loss": 0.9738, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 5.622857142857143, | |
| "grad_norm": 10.370519638061523, | |
| "learning_rate": 3.465851172273191e-05, | |
| "loss": 0.9576, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 5.668571428571429, | |
| "grad_norm": 6.819110870361328, | |
| "learning_rate": 3.44886170574244e-05, | |
| "loss": 0.9086, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 5.857959747314453, | |
| "learning_rate": 3.431872239211689e-05, | |
| "loss": 0.8758, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "grad_norm": 8.476204872131348, | |
| "learning_rate": 3.414882772680938e-05, | |
| "loss": 0.9147, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 5.805714285714286, | |
| "grad_norm": 6.7867865562438965, | |
| "learning_rate": 3.3978933061501874e-05, | |
| "loss": 0.9843, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 5.851428571428571, | |
| "grad_norm": 8.020210266113281, | |
| "learning_rate": 3.380903839619436e-05, | |
| "loss": 1.0334, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 5.897142857142857, | |
| "grad_norm": 7.1987199783325195, | |
| "learning_rate": 3.363914373088685e-05, | |
| "loss": 1.0116, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 5.942857142857143, | |
| "grad_norm": 6.633023738861084, | |
| "learning_rate": 3.3469249065579346e-05, | |
| "loss": 0.9476, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.988571428571428, | |
| "grad_norm": 7.582513332366943, | |
| "learning_rate": 3.329935440027183e-05, | |
| "loss": 0.9472, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 5.997714285714285, | |
| "eval_accuracy": 0.7535870243293824, | |
| "eval_loss": 0.8126731514930725, | |
| "eval_runtime": 71.4321, | |
| "eval_samples_per_second": 112.204, | |
| "eval_steps_per_second": 3.514, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 6.034285714285715, | |
| "grad_norm": 8.917913436889648, | |
| "learning_rate": 3.3129459734964325e-05, | |
| "loss": 0.8892, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "grad_norm": 11.498839378356934, | |
| "learning_rate": 3.295956506965682e-05, | |
| "loss": 0.8989, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 6.1257142857142854, | |
| "grad_norm": 6.905866622924805, | |
| "learning_rate": 3.2789670404349304e-05, | |
| "loss": 0.8923, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 6.171428571428572, | |
| "grad_norm": 5.6410417556762695, | |
| "learning_rate": 3.26197757390418e-05, | |
| "loss": 0.9276, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.217142857142857, | |
| "grad_norm": 8.219051361083984, | |
| "learning_rate": 3.244988107373428e-05, | |
| "loss": 0.9223, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 6.2628571428571425, | |
| "grad_norm": 6.403746128082275, | |
| "learning_rate": 3.2279986408426776e-05, | |
| "loss": 0.9082, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 6.308571428571429, | |
| "grad_norm": 5.092130184173584, | |
| "learning_rate": 3.211009174311927e-05, | |
| "loss": 0.8609, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 6.354285714285714, | |
| "grad_norm": 7.074675559997559, | |
| "learning_rate": 3.1940197077811755e-05, | |
| "loss": 0.908, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 7.3398332595825195, | |
| "learning_rate": 3.177030241250425e-05, | |
| "loss": 0.9756, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.445714285714286, | |
| "grad_norm": 8.28463363647461, | |
| "learning_rate": 3.160040774719674e-05, | |
| "loss": 0.9251, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 6.491428571428571, | |
| "grad_norm": 11.502705574035645, | |
| "learning_rate": 3.1430513081889227e-05, | |
| "loss": 0.8992, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 6.537142857142857, | |
| "grad_norm": 6.942375659942627, | |
| "learning_rate": 3.126061841658172e-05, | |
| "loss": 0.878, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 6.582857142857143, | |
| "grad_norm": 6.975459098815918, | |
| "learning_rate": 3.1090723751274206e-05, | |
| "loss": 0.928, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 6.628571428571428, | |
| "grad_norm": 6.6826372146606445, | |
| "learning_rate": 3.09208290859667e-05, | |
| "loss": 0.9126, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6.674285714285714, | |
| "grad_norm": 6.843193054199219, | |
| "learning_rate": 3.075093442065919e-05, | |
| "loss": 0.94, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "grad_norm": 9.00674819946289, | |
| "learning_rate": 3.0581039755351684e-05, | |
| "loss": 0.9406, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 6.765714285714286, | |
| "grad_norm": 7.362587928771973, | |
| "learning_rate": 3.0411145090044174e-05, | |
| "loss": 0.9414, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 6.811428571428571, | |
| "grad_norm": 10.040757179260254, | |
| "learning_rate": 3.0241250424736666e-05, | |
| "loss": 0.9372, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "grad_norm": 6.630922794342041, | |
| "learning_rate": 3.0071355759429153e-05, | |
| "loss": 0.918, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.902857142857143, | |
| "grad_norm": 6.996939182281494, | |
| "learning_rate": 2.9901461094121645e-05, | |
| "loss": 0.8634, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 6.948571428571428, | |
| "grad_norm": 6.364753723144531, | |
| "learning_rate": 2.9731566428814138e-05, | |
| "loss": 0.94, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 6.994285714285715, | |
| "grad_norm": 7.604902267456055, | |
| "learning_rate": 2.9561671763506628e-05, | |
| "loss": 0.8751, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 6.998857142857143, | |
| "eval_accuracy": 0.7639426076107299, | |
| "eval_loss": 0.7851645350456238, | |
| "eval_runtime": 71.3545, | |
| "eval_samples_per_second": 112.327, | |
| "eval_steps_per_second": 3.518, | |
| "step": 1531 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "grad_norm": 6.300110816955566, | |
| "learning_rate": 2.939177709819912e-05, | |
| "loss": 0.9023, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 7.085714285714285, | |
| "grad_norm": 6.873245716094971, | |
| "learning_rate": 2.9221882432891607e-05, | |
| "loss": 0.8445, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 7.131428571428572, | |
| "grad_norm": 6.225979328155518, | |
| "learning_rate": 2.90519877675841e-05, | |
| "loss": 0.8429, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 7.177142857142857, | |
| "grad_norm": 9.389466285705566, | |
| "learning_rate": 2.8882093102276592e-05, | |
| "loss": 0.8686, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 7.222857142857142, | |
| "grad_norm": 6.56587028503418, | |
| "learning_rate": 2.871219843696908e-05, | |
| "loss": 0.9168, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 7.268571428571429, | |
| "grad_norm": 7.2763447761535645, | |
| "learning_rate": 2.854230377166157e-05, | |
| "loss": 0.9107, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 7.314285714285714, | |
| "grad_norm": 10.647456169128418, | |
| "learning_rate": 2.8372409106354064e-05, | |
| "loss": 0.8785, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "grad_norm": 9.847870826721191, | |
| "learning_rate": 2.820251444104655e-05, | |
| "loss": 0.8282, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 7.405714285714286, | |
| "grad_norm": 6.836136341094971, | |
| "learning_rate": 2.8032619775739043e-05, | |
| "loss": 0.881, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 7.451428571428571, | |
| "grad_norm": 7.8010687828063965, | |
| "learning_rate": 2.7862725110431533e-05, | |
| "loss": 0.8969, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 7.497142857142857, | |
| "grad_norm": 8.551609992980957, | |
| "learning_rate": 2.7692830445124026e-05, | |
| "loss": 0.9146, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 7.542857142857143, | |
| "grad_norm": 6.829668998718262, | |
| "learning_rate": 2.7522935779816515e-05, | |
| "loss": 0.8377, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7.588571428571429, | |
| "grad_norm": 5.782020568847656, | |
| "learning_rate": 2.7353041114509004e-05, | |
| "loss": 0.8956, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 7.634285714285714, | |
| "grad_norm": 7.081970691680908, | |
| "learning_rate": 2.7183146449201497e-05, | |
| "loss": 0.8707, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "grad_norm": 7.2627739906311035, | |
| "learning_rate": 2.701325178389399e-05, | |
| "loss": 0.8865, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 7.725714285714286, | |
| "grad_norm": 6.740649700164795, | |
| "learning_rate": 2.6843357118586476e-05, | |
| "loss": 0.8183, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 7.771428571428571, | |
| "grad_norm": 6.93267822265625, | |
| "learning_rate": 2.667346245327897e-05, | |
| "loss": 0.8898, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.817142857142857, | |
| "grad_norm": 8.19253921508789, | |
| "learning_rate": 2.6503567787971462e-05, | |
| "loss": 0.8982, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 7.862857142857143, | |
| "grad_norm": 5.707729816436768, | |
| "learning_rate": 2.6333673122663948e-05, | |
| "loss": 0.888, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 7.908571428571428, | |
| "grad_norm": 6.924159049987793, | |
| "learning_rate": 2.616377845735644e-05, | |
| "loss": 0.8658, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 7.954285714285715, | |
| "grad_norm": 8.230816841125488, | |
| "learning_rate": 2.5993883792048927e-05, | |
| "loss": 0.8772, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 7.3947906494140625, | |
| "learning_rate": 2.582398912674142e-05, | |
| "loss": 0.9107, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7713038053649407, | |
| "eval_loss": 0.7643583416938782, | |
| "eval_runtime": 72.4816, | |
| "eval_samples_per_second": 110.58, | |
| "eval_steps_per_second": 3.463, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 8.045714285714286, | |
| "grad_norm": 6.424936294555664, | |
| "learning_rate": 2.5654094461433913e-05, | |
| "loss": 0.8515, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 8.09142857142857, | |
| "grad_norm": 7.372068881988525, | |
| "learning_rate": 2.5484199796126402e-05, | |
| "loss": 0.7997, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 8.137142857142857, | |
| "grad_norm": 6.683503150939941, | |
| "learning_rate": 2.5314305130818895e-05, | |
| "loss": 0.8021, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 8.182857142857143, | |
| "grad_norm": 7.226657390594482, | |
| "learning_rate": 2.5144410465511388e-05, | |
| "loss": 0.8367, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 8.228571428571428, | |
| "grad_norm": 6.432008743286133, | |
| "learning_rate": 2.4974515800203874e-05, | |
| "loss": 0.8582, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.274285714285714, | |
| "grad_norm": 6.051323890686035, | |
| "learning_rate": 2.4804621134896367e-05, | |
| "loss": 0.8166, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "grad_norm": 10.92369270324707, | |
| "learning_rate": 2.4634726469588856e-05, | |
| "loss": 0.8797, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 8.365714285714287, | |
| "grad_norm": 9.526762962341309, | |
| "learning_rate": 2.4464831804281346e-05, | |
| "loss": 0.8032, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 8.411428571428571, | |
| "grad_norm": 7.965165138244629, | |
| "learning_rate": 2.4294937138973835e-05, | |
| "loss": 0.8453, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 8.457142857142857, | |
| "grad_norm": 7.171777248382568, | |
| "learning_rate": 2.4125042473666328e-05, | |
| "loss": 0.8668, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 8.502857142857144, | |
| "grad_norm": 7.443463325500488, | |
| "learning_rate": 2.3955147808358818e-05, | |
| "loss": 0.8412, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 8.548571428571428, | |
| "grad_norm": 5.963488578796387, | |
| "learning_rate": 2.3785253143051307e-05, | |
| "loss": 0.8126, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 8.594285714285714, | |
| "grad_norm": 7.679189682006836, | |
| "learning_rate": 2.36153584777438e-05, | |
| "loss": 0.8548, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "grad_norm": 7.266505718231201, | |
| "learning_rate": 2.3445463812436293e-05, | |
| "loss": 0.8217, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 8.685714285714285, | |
| "grad_norm": 6.643305778503418, | |
| "learning_rate": 2.3275569147128782e-05, | |
| "loss": 0.8284, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.731428571428571, | |
| "grad_norm": 6.7400922775268555, | |
| "learning_rate": 2.3105674481821272e-05, | |
| "loss": 0.8595, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 8.777142857142858, | |
| "grad_norm": 9.218864440917969, | |
| "learning_rate": 2.2935779816513765e-05, | |
| "loss": 0.8636, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 8.822857142857142, | |
| "grad_norm": 6.2901434898376465, | |
| "learning_rate": 2.2765885151206254e-05, | |
| "loss": 0.8293, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 8.868571428571428, | |
| "grad_norm": 7.57029390335083, | |
| "learning_rate": 2.2595990485898744e-05, | |
| "loss": 0.8275, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 8.914285714285715, | |
| "grad_norm": 6.863813400268555, | |
| "learning_rate": 2.2426095820591233e-05, | |
| "loss": 0.7866, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "grad_norm": 7.338642597198486, | |
| "learning_rate": 2.2256201155283726e-05, | |
| "loss": 0.8464, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 8.996571428571428, | |
| "eval_accuracy": 0.7830318153462258, | |
| "eval_loss": 0.7322039604187012, | |
| "eval_runtime": 69.8506, | |
| "eval_samples_per_second": 114.745, | |
| "eval_steps_per_second": 3.593, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 9.005714285714285, | |
| "grad_norm": 5.92184591293335, | |
| "learning_rate": 2.2086306489976216e-05, | |
| "loss": 0.7986, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 9.051428571428572, | |
| "grad_norm": 8.04157829284668, | |
| "learning_rate": 2.1916411824668705e-05, | |
| "loss": 0.8227, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 9.097142857142858, | |
| "grad_norm": 6.019360065460205, | |
| "learning_rate": 2.1746517159361194e-05, | |
| "loss": 0.7563, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 9.142857142857142, | |
| "grad_norm": 7.545748233795166, | |
| "learning_rate": 2.1576622494053687e-05, | |
| "loss": 0.8087, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.188571428571429, | |
| "grad_norm": 7.692215442657471, | |
| "learning_rate": 2.140672782874618e-05, | |
| "loss": 0.7899, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 9.234285714285715, | |
| "grad_norm": 7.4185566902160645, | |
| "learning_rate": 2.123683316343867e-05, | |
| "loss": 0.7823, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "grad_norm": 8.05014705657959, | |
| "learning_rate": 2.106693849813116e-05, | |
| "loss": 0.767, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 9.325714285714286, | |
| "grad_norm": 7.103221893310547, | |
| "learning_rate": 2.0897043832823652e-05, | |
| "loss": 0.7722, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 9.371428571428572, | |
| "grad_norm": 6.289785861968994, | |
| "learning_rate": 2.072714916751614e-05, | |
| "loss": 0.7829, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 9.417142857142856, | |
| "grad_norm": 5.672107696533203, | |
| "learning_rate": 2.055725450220863e-05, | |
| "loss": 0.7582, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 9.462857142857143, | |
| "grad_norm": 7.584166049957275, | |
| "learning_rate": 2.038735983690112e-05, | |
| "loss": 0.8066, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 9.508571428571429, | |
| "grad_norm": 6.826247215270996, | |
| "learning_rate": 2.0217465171593613e-05, | |
| "loss": 0.8539, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 9.554285714285715, | |
| "grad_norm": 7.450297832489014, | |
| "learning_rate": 2.0047570506286103e-05, | |
| "loss": 0.8866, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 7.801323890686035, | |
| "learning_rate": 1.9877675840978592e-05, | |
| "loss": 0.7857, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9.645714285714286, | |
| "grad_norm": 5.812144756317139, | |
| "learning_rate": 1.9707781175671085e-05, | |
| "loss": 0.7891, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 9.691428571428572, | |
| "grad_norm": 6.948761940002441, | |
| "learning_rate": 1.9537886510363575e-05, | |
| "loss": 0.8282, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 9.737142857142857, | |
| "grad_norm": 7.478163719177246, | |
| "learning_rate": 1.9367991845056068e-05, | |
| "loss": 0.7716, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 9.782857142857143, | |
| "grad_norm": 7.083802700042725, | |
| "learning_rate": 1.9198097179748557e-05, | |
| "loss": 0.8072, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 9.82857142857143, | |
| "grad_norm": 8.924737930297852, | |
| "learning_rate": 1.902820251444105e-05, | |
| "loss": 0.795, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9.874285714285714, | |
| "grad_norm": 6.02655553817749, | |
| "learning_rate": 1.885830784913354e-05, | |
| "loss": 0.8785, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "grad_norm": 6.204999923706055, | |
| "learning_rate": 1.868841318382603e-05, | |
| "loss": 0.8836, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 9.965714285714286, | |
| "grad_norm": 9.425383567810059, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.8398, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 9.997714285714286, | |
| "eval_accuracy": 0.7797878976918278, | |
| "eval_loss": 0.7243014574050903, | |
| "eval_runtime": 70.1724, | |
| "eval_samples_per_second": 114.219, | |
| "eval_steps_per_second": 3.577, | |
| "step": 2187 | |
| }, | |
| { | |
| "epoch": 10.01142857142857, | |
| "grad_norm": 6.657647132873535, | |
| "learning_rate": 1.834862385321101e-05, | |
| "loss": 0.7659, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 10.057142857142857, | |
| "grad_norm": 6.205779075622559, | |
| "learning_rate": 1.81787291879035e-05, | |
| "loss": 0.7612, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 10.102857142857143, | |
| "grad_norm": 4.940152168273926, | |
| "learning_rate": 1.800883452259599e-05, | |
| "loss": 0.7277, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 10.14857142857143, | |
| "grad_norm": 6.750416278839111, | |
| "learning_rate": 1.783893985728848e-05, | |
| "loss": 0.7334, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 10.194285714285714, | |
| "grad_norm": 8.511019706726074, | |
| "learning_rate": 1.7669045191980972e-05, | |
| "loss": 0.846, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "grad_norm": 6.814949989318848, | |
| "learning_rate": 1.7499150526673462e-05, | |
| "loss": 0.7721, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 10.285714285714286, | |
| "grad_norm": 8.27193546295166, | |
| "learning_rate": 1.7329255861365955e-05, | |
| "loss": 0.7794, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 10.331428571428571, | |
| "grad_norm": 6.475657939910889, | |
| "learning_rate": 1.7159361196058444e-05, | |
| "loss": 0.7965, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 10.377142857142857, | |
| "grad_norm": 7.63599967956543, | |
| "learning_rate": 1.6989466530750937e-05, | |
| "loss": 0.768, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 10.422857142857143, | |
| "grad_norm": 6.7202043533325195, | |
| "learning_rate": 1.6819571865443427e-05, | |
| "loss": 0.7671, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 10.468571428571428, | |
| "grad_norm": 11.612401962280273, | |
| "learning_rate": 1.6649677200135916e-05, | |
| "loss": 0.7752, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 10.514285714285714, | |
| "grad_norm": 10.456415176391602, | |
| "learning_rate": 1.647978253482841e-05, | |
| "loss": 0.8036, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "grad_norm": 5.8782782554626465, | |
| "learning_rate": 1.63098878695209e-05, | |
| "loss": 0.7652, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 10.605714285714285, | |
| "grad_norm": 8.532390594482422, | |
| "learning_rate": 1.6139993204213388e-05, | |
| "loss": 0.8296, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 10.651428571428571, | |
| "grad_norm": 8.59847354888916, | |
| "learning_rate": 1.5970098538905877e-05, | |
| "loss": 0.8239, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 10.697142857142858, | |
| "grad_norm": 7.728725910186768, | |
| "learning_rate": 1.580020387359837e-05, | |
| "loss": 0.7657, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 10.742857142857144, | |
| "grad_norm": 7.599369049072266, | |
| "learning_rate": 1.563030920829086e-05, | |
| "loss": 0.734, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 10.788571428571428, | |
| "grad_norm": 7.236623287200928, | |
| "learning_rate": 1.546041454298335e-05, | |
| "loss": 0.7992, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 10.834285714285715, | |
| "grad_norm": 9.501078605651855, | |
| "learning_rate": 1.5290519877675842e-05, | |
| "loss": 0.7977, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "grad_norm": 7.179370403289795, | |
| "learning_rate": 1.5120625212368333e-05, | |
| "loss": 0.8284, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 10.925714285714285, | |
| "grad_norm": 6.750663757324219, | |
| "learning_rate": 1.4950730547060823e-05, | |
| "loss": 0.8197, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 10.971428571428572, | |
| "grad_norm": 8.519887924194336, | |
| "learning_rate": 1.4780835881753314e-05, | |
| "loss": 0.7534, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10.998857142857142, | |
| "eval_accuracy": 0.7845290081097941, | |
| "eval_loss": 0.708789050579071, | |
| "eval_runtime": 70.0816, | |
| "eval_samples_per_second": 114.367, | |
| "eval_steps_per_second": 3.582, | |
| "step": 2406 | |
| }, | |
| { | |
| "epoch": 11.017142857142858, | |
| "grad_norm": 8.514420509338379, | |
| "learning_rate": 1.4610941216445803e-05, | |
| "loss": 0.804, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 11.062857142857142, | |
| "grad_norm": 7.491757869720459, | |
| "learning_rate": 1.4441046551138296e-05, | |
| "loss": 0.8208, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 11.108571428571429, | |
| "grad_norm": 8.859854698181152, | |
| "learning_rate": 1.4271151885830786e-05, | |
| "loss": 0.7703, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 11.154285714285715, | |
| "grad_norm": 7.596364498138428, | |
| "learning_rate": 1.4101257220523275e-05, | |
| "loss": 0.7777, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 4.977694988250732, | |
| "learning_rate": 1.3931362555215766e-05, | |
| "loss": 0.7842, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 11.245714285714286, | |
| "grad_norm": 8.050721168518066, | |
| "learning_rate": 1.3761467889908258e-05, | |
| "loss": 0.7335, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 11.291428571428572, | |
| "grad_norm": 6.315252304077148, | |
| "learning_rate": 1.3591573224600749e-05, | |
| "loss": 0.7898, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 11.337142857142856, | |
| "grad_norm": 6.380728721618652, | |
| "learning_rate": 1.3421678559293238e-05, | |
| "loss": 0.7531, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 11.382857142857143, | |
| "grad_norm": 6.871670246124268, | |
| "learning_rate": 1.3251783893985731e-05, | |
| "loss": 0.7604, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 7.661756992340088, | |
| "learning_rate": 1.308188922867822e-05, | |
| "loss": 0.7772, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 11.474285714285715, | |
| "grad_norm": 8.346705436706543, | |
| "learning_rate": 1.291199456337071e-05, | |
| "loss": 0.7372, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "grad_norm": 5.545016288757324, | |
| "learning_rate": 1.2742099898063201e-05, | |
| "loss": 0.7428, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 11.565714285714286, | |
| "grad_norm": 8.73310661315918, | |
| "learning_rate": 1.2572205232755694e-05, | |
| "loss": 0.7566, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 11.611428571428572, | |
| "grad_norm": 7.3945794105529785, | |
| "learning_rate": 1.2402310567448183e-05, | |
| "loss": 0.7988, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 11.657142857142857, | |
| "grad_norm": 5.604186534881592, | |
| "learning_rate": 1.2232415902140673e-05, | |
| "loss": 0.6912, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 11.702857142857143, | |
| "grad_norm": 6.901523590087891, | |
| "learning_rate": 1.2062521236833164e-05, | |
| "loss": 0.7438, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 11.748571428571429, | |
| "grad_norm": 7.090272426605225, | |
| "learning_rate": 1.1892626571525654e-05, | |
| "loss": 0.7502, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 11.794285714285714, | |
| "grad_norm": 9.939922332763672, | |
| "learning_rate": 1.1722731906218146e-05, | |
| "loss": 0.7574, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "grad_norm": 7.832808017730713, | |
| "learning_rate": 1.1552837240910636e-05, | |
| "loss": 0.7763, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 11.885714285714286, | |
| "grad_norm": 7.921093940734863, | |
| "learning_rate": 1.1382942575603127e-05, | |
| "loss": 0.8136, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 11.93142857142857, | |
| "grad_norm": 8.13971996307373, | |
| "learning_rate": 1.1213047910295617e-05, | |
| "loss": 0.7735, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 11.977142857142857, | |
| "grad_norm": 5.870953559875488, | |
| "learning_rate": 1.1043153244988108e-05, | |
| "loss": 0.7051, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.793512164691204, | |
| "eval_loss": 0.6982392072677612, | |
| "eval_runtime": 74.4508, | |
| "eval_samples_per_second": 107.655, | |
| "eval_steps_per_second": 3.371, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 12.022857142857143, | |
| "grad_norm": 9.655831336975098, | |
| "learning_rate": 1.0873258579680597e-05, | |
| "loss": 0.7839, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 12.06857142857143, | |
| "grad_norm": 6.195824146270752, | |
| "learning_rate": 1.070336391437309e-05, | |
| "loss": 0.7916, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 12.114285714285714, | |
| "grad_norm": 7.92185115814209, | |
| "learning_rate": 1.053346924906558e-05, | |
| "loss": 0.7016, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "grad_norm": 5.990954875946045, | |
| "learning_rate": 1.036357458375807e-05, | |
| "loss": 0.6903, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 12.205714285714286, | |
| "grad_norm": 5.883810520172119, | |
| "learning_rate": 1.019367991845056e-05, | |
| "loss": 0.7879, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 12.251428571428571, | |
| "grad_norm": 6.014761447906494, | |
| "learning_rate": 1.0023785253143051e-05, | |
| "loss": 0.7569, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 12.297142857142857, | |
| "grad_norm": 6.2539191246032715, | |
| "learning_rate": 9.853890587835543e-06, | |
| "loss": 0.7547, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 12.342857142857143, | |
| "grad_norm": 8.04623031616211, | |
| "learning_rate": 9.683995922528034e-06, | |
| "loss": 0.7636, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 12.388571428571428, | |
| "grad_norm": 7.5707106590271, | |
| "learning_rate": 9.514101257220525e-06, | |
| "loss": 0.7976, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 12.434285714285714, | |
| "grad_norm": 7.271738529205322, | |
| "learning_rate": 9.344206591913014e-06, | |
| "loss": 0.6919, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "grad_norm": 6.238006591796875, | |
| "learning_rate": 9.174311926605506e-06, | |
| "loss": 0.7343, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 12.525714285714285, | |
| "grad_norm": 6.735348701477051, | |
| "learning_rate": 9.004417261297995e-06, | |
| "loss": 0.6853, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "grad_norm": 7.480915069580078, | |
| "learning_rate": 8.834522595990486e-06, | |
| "loss": 0.7797, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 12.617142857142857, | |
| "grad_norm": 7.131129741668701, | |
| "learning_rate": 8.664627930682977e-06, | |
| "loss": 0.7023, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 12.662857142857142, | |
| "grad_norm": 6.145063400268555, | |
| "learning_rate": 8.494733265375469e-06, | |
| "loss": 0.801, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 12.708571428571428, | |
| "grad_norm": 8.46693229675293, | |
| "learning_rate": 8.324838600067958e-06, | |
| "loss": 0.7693, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 12.754285714285714, | |
| "grad_norm": 6.422353744506836, | |
| "learning_rate": 8.15494393476045e-06, | |
| "loss": 0.7248, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "grad_norm": 10.295066833496094, | |
| "learning_rate": 7.985049269452939e-06, | |
| "loss": 0.8283, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 12.845714285714285, | |
| "grad_norm": 7.5840959548950195, | |
| "learning_rate": 7.81515460414543e-06, | |
| "loss": 0.7081, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 12.891428571428571, | |
| "grad_norm": 6.741255760192871, | |
| "learning_rate": 7.645259938837921e-06, | |
| "loss": 0.7079, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 12.937142857142858, | |
| "grad_norm": 7.525110721588135, | |
| "learning_rate": 7.475365273530411e-06, | |
| "loss": 0.7374, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 12.982857142857142, | |
| "grad_norm": 7.784526348114014, | |
| "learning_rate": 7.305470608222902e-06, | |
| "loss": 0.7359, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 12.996571428571428, | |
| "eval_accuracy": 0.7916406737367436, | |
| "eval_loss": 0.6984859704971313, | |
| "eval_runtime": 73.0055, | |
| "eval_samples_per_second": 109.786, | |
| "eval_steps_per_second": 3.438, | |
| "step": 2843 | |
| }, | |
| { | |
| "epoch": 13.028571428571428, | |
| "grad_norm": 7.309814929962158, | |
| "learning_rate": 7.135575942915393e-06, | |
| "loss": 0.709, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 13.074285714285715, | |
| "grad_norm": 10.355072021484375, | |
| "learning_rate": 6.965681277607883e-06, | |
| "loss": 0.7387, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "grad_norm": 7.303361415863037, | |
| "learning_rate": 6.795786612300374e-06, | |
| "loss": 0.6999, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 13.165714285714285, | |
| "grad_norm": 8.104413032531738, | |
| "learning_rate": 6.6258919469928655e-06, | |
| "loss": 0.7602, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 13.211428571428572, | |
| "grad_norm": 6.764256000518799, | |
| "learning_rate": 6.455997281685355e-06, | |
| "loss": 0.7195, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 13.257142857142856, | |
| "grad_norm": 6.039324760437012, | |
| "learning_rate": 6.286102616377847e-06, | |
| "loss": 0.6927, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 13.302857142857142, | |
| "grad_norm": 5.957076549530029, | |
| "learning_rate": 6.1162079510703365e-06, | |
| "loss": 0.7369, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 13.348571428571429, | |
| "grad_norm": 6.061888694763184, | |
| "learning_rate": 5.946313285762827e-06, | |
| "loss": 0.734, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 13.394285714285715, | |
| "grad_norm": 8.270124435424805, | |
| "learning_rate": 5.776418620455318e-06, | |
| "loss": 0.7389, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "grad_norm": 5.897438049316406, | |
| "learning_rate": 5.606523955147808e-06, | |
| "loss": 0.772, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 13.485714285714286, | |
| "grad_norm": 10.048014640808105, | |
| "learning_rate": 5.436629289840299e-06, | |
| "loss": 0.7129, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 13.531428571428572, | |
| "grad_norm": 6.532159805297852, | |
| "learning_rate": 5.26673462453279e-06, | |
| "loss": 0.7329, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 13.577142857142857, | |
| "grad_norm": 7.861076831817627, | |
| "learning_rate": 5.09683995922528e-06, | |
| "loss": 0.659, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 13.622857142857143, | |
| "grad_norm": 7.23004150390625, | |
| "learning_rate": 4.926945293917771e-06, | |
| "loss": 0.7383, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 13.668571428571429, | |
| "grad_norm": 7.737166881561279, | |
| "learning_rate": 4.7570506286102625e-06, | |
| "loss": 0.7243, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "grad_norm": 6.211805820465088, | |
| "learning_rate": 4.587155963302753e-06, | |
| "loss": 0.748, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "grad_norm": 6.718061447143555, | |
| "learning_rate": 4.417261297995243e-06, | |
| "loss": 0.7005, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 13.805714285714286, | |
| "grad_norm": 6.454185485839844, | |
| "learning_rate": 4.247366632687734e-06, | |
| "loss": 0.806, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 13.85142857142857, | |
| "grad_norm": 8.608590126037598, | |
| "learning_rate": 4.077471967380225e-06, | |
| "loss": 0.7342, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 13.897142857142857, | |
| "grad_norm": 6.505426406860352, | |
| "learning_rate": 3.907577302072715e-06, | |
| "loss": 0.7148, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 13.942857142857143, | |
| "grad_norm": 7.760762691497803, | |
| "learning_rate": 3.7376826367652057e-06, | |
| "loss": 0.7208, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 13.98857142857143, | |
| "grad_norm": 6.736624240875244, | |
| "learning_rate": 3.5677879714576964e-06, | |
| "loss": 0.7641, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 13.997714285714286, | |
| "eval_accuracy": 0.796756082345602, | |
| "eval_loss": 0.6838445663452148, | |
| "eval_runtime": 74.6047, | |
| "eval_samples_per_second": 107.433, | |
| "eval_steps_per_second": 3.364, | |
| "step": 3062 | |
| }, | |
| { | |
| "epoch": 14.034285714285714, | |
| "grad_norm": 6.665014266967773, | |
| "learning_rate": 3.397893306150187e-06, | |
| "loss": 0.6983, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "grad_norm": 6.425662994384766, | |
| "learning_rate": 3.2279986408426775e-06, | |
| "loss": 0.6563, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 14.125714285714286, | |
| "grad_norm": 6.079023838043213, | |
| "learning_rate": 3.0581039755351682e-06, | |
| "loss": 0.6838, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 14.17142857142857, | |
| "grad_norm": 6.835630416870117, | |
| "learning_rate": 2.888209310227659e-06, | |
| "loss": 0.6923, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 14.217142857142857, | |
| "grad_norm": 7.853431224822998, | |
| "learning_rate": 2.7183146449201493e-06, | |
| "loss": 0.7237, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 14.262857142857143, | |
| "grad_norm": 6.308788299560547, | |
| "learning_rate": 2.54841997961264e-06, | |
| "loss": 0.7469, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 14.308571428571428, | |
| "grad_norm": 7.8088202476501465, | |
| "learning_rate": 2.3785253143051312e-06, | |
| "loss": 0.73, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 14.354285714285714, | |
| "grad_norm": 6.700632095336914, | |
| "learning_rate": 2.2086306489976216e-06, | |
| "loss": 0.7349, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "grad_norm": 7.2199320793151855, | |
| "learning_rate": 2.0387359836901123e-06, | |
| "loss": 0.7093, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 14.445714285714285, | |
| "grad_norm": 5.401243686676025, | |
| "learning_rate": 1.8688413183826028e-06, | |
| "loss": 0.6662, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 14.491428571428571, | |
| "grad_norm": 6.991000652313232, | |
| "learning_rate": 1.6989466530750936e-06, | |
| "loss": 0.6859, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 14.537142857142857, | |
| "grad_norm": 5.750977993011475, | |
| "learning_rate": 1.5290519877675841e-06, | |
| "loss": 0.6917, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 14.582857142857144, | |
| "grad_norm": 8.291132926940918, | |
| "learning_rate": 1.3591573224600747e-06, | |
| "loss": 0.7237, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 14.628571428571428, | |
| "grad_norm": 8.148652076721191, | |
| "learning_rate": 1.1892626571525656e-06, | |
| "loss": 0.795, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 14.674285714285714, | |
| "grad_norm": 8.365762710571289, | |
| "learning_rate": 1.0193679918450562e-06, | |
| "loss": 0.7038, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "grad_norm": 8.118247032165527, | |
| "learning_rate": 8.494733265375468e-07, | |
| "loss": 0.7334, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 14.765714285714285, | |
| "grad_norm": 7.585115432739258, | |
| "learning_rate": 6.795786612300373e-07, | |
| "loss": 0.7761, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 14.811428571428571, | |
| "grad_norm": 7.77222204208374, | |
| "learning_rate": 5.096839959225281e-07, | |
| "loss": 0.6876, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "grad_norm": 7.689059734344482, | |
| "learning_rate": 3.3978933061501866e-07, | |
| "loss": 0.6827, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 14.902857142857142, | |
| "grad_norm": 7.31766414642334, | |
| "learning_rate": 1.6989466530750933e-07, | |
| "loss": 0.7361, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 14.948571428571428, | |
| "grad_norm": 6.6061015129089355, | |
| "learning_rate": 0.0, | |
| "loss": 0.7372, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 14.948571428571428, | |
| "eval_accuracy": 0.796756082345602, | |
| "eval_loss": 0.6781123280525208, | |
| "eval_runtime": 74.4538, | |
| "eval_samples_per_second": 107.651, | |
| "eval_steps_per_second": 3.371, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 14.948571428571428, | |
| "step": 3270, | |
| "total_flos": 1.0403963301155365e+19, | |
| "train_loss": 0.9863547705729073, | |
| "train_runtime": 7901.2254, | |
| "train_samples_per_second": 53.135, | |
| "train_steps_per_second": 0.414 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0403963301155365e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |