| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 18720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5234657039711191, | |
| "eval_loss": 0.5125718116760254, | |
| "eval_runtime": 8.8736, | |
| "eval_samples_per_second": 31.216, | |
| "eval_steps_per_second": 3.944, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.002919871794871795, | |
| "loss": 0.5126, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.38242238759994507, | |
| "eval_runtime": 8.7725, | |
| "eval_samples_per_second": 31.576, | |
| "eval_steps_per_second": 3.99, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.3692016005516052, | |
| "eval_runtime": 8.7845, | |
| "eval_samples_per_second": 31.533, | |
| "eval_steps_per_second": 3.984, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0028397435897435895, | |
| "loss": 0.4613, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.3940806984901428, | |
| "eval_runtime": 8.8274, | |
| "eval_samples_per_second": 31.38, | |
| "eval_steps_per_second": 3.965, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0027596153846153847, | |
| "loss": 0.446, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.6773150563240051, | |
| "eval_runtime": 8.9686, | |
| "eval_samples_per_second": 30.885, | |
| "eval_steps_per_second": 3.902, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.5515874028205872, | |
| "eval_runtime": 9.1762, | |
| "eval_samples_per_second": 30.187, | |
| "eval_steps_per_second": 3.814, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00267948717948718, | |
| "loss": 0.4477, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.3517453372478485, | |
| "eval_runtime": 9.1384, | |
| "eval_samples_per_second": 30.312, | |
| "eval_steps_per_second": 3.83, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.37720802426338196, | |
| "eval_runtime": 9.0573, | |
| "eval_samples_per_second": 30.583, | |
| "eval_steps_per_second": 3.864, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0025993589743589745, | |
| "loss": 0.4263, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.36901482939720154, | |
| "eval_runtime": 9.0499, | |
| "eval_samples_per_second": 30.608, | |
| "eval_steps_per_second": 3.867, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0025192307692307693, | |
| "loss": 0.4397, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.35119369626045227, | |
| "eval_runtime": 9.0328, | |
| "eval_samples_per_second": 30.666, | |
| "eval_steps_per_second": 3.875, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.47159671783447266, | |
| "eval_runtime": 9.0616, | |
| "eval_samples_per_second": 30.569, | |
| "eval_steps_per_second": 3.862, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.002439102564102564, | |
| "loss": 0.4425, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.36053842306137085, | |
| "eval_runtime": 9.0613, | |
| "eval_samples_per_second": 30.57, | |
| "eval_steps_per_second": 3.863, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.6570397111913358, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.002358974358974359, | |
| "loss": 0.4269, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.3570541739463806, | |
| "eval_runtime": 9.0666, | |
| "eval_samples_per_second": 30.552, | |
| "eval_steps_per_second": 3.86, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.6570397111913358, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.3544716238975525, | |
| "eval_runtime": 9.1496, | |
| "eval_samples_per_second": 30.274, | |
| "eval_steps_per_second": 3.825, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.6570397111913358, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.002278846153846154, | |
| "loss": 0.3975, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.37444454431533813, | |
| "eval_runtime": 9.0245, | |
| "eval_samples_per_second": 30.694, | |
| "eval_steps_per_second": 3.878, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.6570397111913358, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6606498194945848, | |
| "eval_loss": 0.35777392983436584, | |
| "eval_runtime": 9.0439, | |
| "eval_samples_per_second": 30.628, | |
| "eval_steps_per_second": 3.87, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.6606498194945848, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0021987179487179486, | |
| "loss": 0.3906, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.37044015526771545, | |
| "eval_runtime": 9.0352, | |
| "eval_samples_per_second": 30.658, | |
| "eval_steps_per_second": 3.874, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.0021185897435897437, | |
| "loss": 0.3633, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6064981949458483, | |
| "eval_loss": 0.3355711102485657, | |
| "eval_runtime": 9.076, | |
| "eval_samples_per_second": 30.52, | |
| "eval_steps_per_second": 3.856, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6064981949458483, | |
| "eval_loss": 0.3397271931171417, | |
| "eval_runtime": 9.0579, | |
| "eval_samples_per_second": 30.581, | |
| "eval_steps_per_second": 3.864, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 0.3604, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3809119760990143, | |
| "eval_runtime": 9.0061, | |
| "eval_samples_per_second": 30.757, | |
| "eval_steps_per_second": 3.886, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0019583333333333336, | |
| "loss": 0.3565, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.33565953373908997, | |
| "eval_runtime": 9.0589, | |
| "eval_samples_per_second": 30.578, | |
| "eval_steps_per_second": 3.864, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.38026997447013855, | |
| "eval_runtime": 9.0356, | |
| "eval_samples_per_second": 30.656, | |
| "eval_steps_per_second": 3.874, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0018782051282051281, | |
| "loss": 0.3533, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.37539029121398926, | |
| "eval_runtime": 9.0595, | |
| "eval_samples_per_second": 30.576, | |
| "eval_steps_per_second": 3.863, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6353790613718412, | |
| "eval_loss": 0.3304370641708374, | |
| "eval_runtime": 9.2561, | |
| "eval_samples_per_second": 29.926, | |
| "eval_steps_per_second": 3.781, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 16, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.001798076923076923, | |
| "loss": 0.3462, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.36999332904815674, | |
| "eval_runtime": 9.2621, | |
| "eval_samples_per_second": 29.907, | |
| "eval_steps_per_second": 3.779, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0017179487179487178, | |
| "loss": 0.3432, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.333748996257782, | |
| "eval_runtime": 9.203, | |
| "eval_samples_per_second": 30.099, | |
| "eval_steps_per_second": 3.803, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 25, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3289393484592438, | |
| "eval_runtime": 9.2259, | |
| "eval_samples_per_second": 30.024, | |
| "eval_steps_per_second": 3.794, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 25, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0016378205128205127, | |
| "loss": 0.3409, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3340049684047699, | |
| "eval_runtime": 9.2073, | |
| "eval_samples_per_second": 30.085, | |
| "eval_steps_per_second": 3.801, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 25, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0015576923076923079, | |
| "loss": 0.3381, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3466947674751282, | |
| "eval_runtime": 9.2066, | |
| "eval_samples_per_second": 30.087, | |
| "eval_steps_per_second": 3.802, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6823104693140795, | |
| "eval_loss": 0.3859948515892029, | |
| "eval_runtime": 9.1838, | |
| "eval_samples_per_second": 30.162, | |
| "eval_steps_per_second": 3.811, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0014775641025641026, | |
| "loss": 0.337, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3795461356639862, | |
| "eval_runtime": 9.2077, | |
| "eval_samples_per_second": 30.083, | |
| "eval_steps_per_second": 3.801, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.3755357563495636, | |
| "eval_runtime": 9.142, | |
| "eval_samples_per_second": 30.3, | |
| "eval_steps_per_second": 3.828, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0013974358974358976, | |
| "loss": 0.334, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.3529473543167114, | |
| "eval_runtime": 9.0973, | |
| "eval_samples_per_second": 30.449, | |
| "eval_steps_per_second": 3.847, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0013173076923076923, | |
| "loss": 0.3321, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.33890479803085327, | |
| "eval_runtime": 9.1599, | |
| "eval_samples_per_second": 30.24, | |
| "eval_steps_per_second": 3.821, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3260202407836914, | |
| "eval_runtime": 9.3959, | |
| "eval_samples_per_second": 29.481, | |
| "eval_steps_per_second": 3.725, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0012371794871794872, | |
| "loss": 0.3315, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.35185953974723816, | |
| "eval_runtime": 9.0108, | |
| "eval_samples_per_second": 30.741, | |
| "eval_steps_per_second": 3.884, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0011570512820512822, | |
| "loss": 0.3317, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3741394877433777, | |
| "eval_runtime": 8.9889, | |
| "eval_samples_per_second": 30.816, | |
| "eval_steps_per_second": 3.894, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.33644017577171326, | |
| "eval_runtime": 9.1679, | |
| "eval_samples_per_second": 30.214, | |
| "eval_steps_per_second": 3.818, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0010769230769230769, | |
| "loss": 0.325, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.34382882714271545, | |
| "eval_runtime": 9.0452, | |
| "eval_samples_per_second": 30.624, | |
| "eval_steps_per_second": 3.869, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3461564779281616, | |
| "eval_runtime": 8.9087, | |
| "eval_samples_per_second": 31.093, | |
| "eval_steps_per_second": 3.929, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0009967948717948718, | |
| "loss": 0.3282, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.33443841338157654, | |
| "eval_runtime": 9.0016, | |
| "eval_samples_per_second": 30.772, | |
| "eval_steps_per_second": 3.888, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0009166666666666668, | |
| "loss": 0.3251, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.328012079000473, | |
| "eval_runtime": 8.8448, | |
| "eval_samples_per_second": 31.318, | |
| "eval_steps_per_second": 3.957, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.35438141226768494, | |
| "eval_runtime": 8.8382, | |
| "eval_samples_per_second": 31.341, | |
| "eval_steps_per_second": 3.96, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0008365384615384616, | |
| "loss": 0.3223, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.34875577688217163, | |
| "eval_runtime": 8.7814, | |
| "eval_samples_per_second": 31.544, | |
| "eval_steps_per_second": 3.986, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0007564102564102564, | |
| "loss": 0.3215, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3436548113822937, | |
| "eval_runtime": 8.7944, | |
| "eval_samples_per_second": 31.497, | |
| "eval_steps_per_second": 3.98, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.34295418858528137, | |
| "eval_runtime": 8.7788, | |
| "eval_samples_per_second": 31.553, | |
| "eval_steps_per_second": 3.987, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0006762820512820514, | |
| "loss": 0.3205, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.33936554193496704, | |
| "eval_runtime": 8.8644, | |
| "eval_samples_per_second": 31.249, | |
| "eval_steps_per_second": 3.948, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.3676346242427826, | |
| "eval_runtime": 8.8385, | |
| "eval_samples_per_second": 31.34, | |
| "eval_steps_per_second": 3.96, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 35, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0005961538461538461, | |
| "loss": 0.3163, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3486822545528412, | |
| "eval_runtime": 8.8462, | |
| "eval_samples_per_second": 31.313, | |
| "eval_steps_per_second": 3.956, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.000516025641025641, | |
| "loss": 0.3154, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.33869412541389465, | |
| "eval_runtime": 8.9668, | |
| "eval_samples_per_second": 30.892, | |
| "eval_steps_per_second": 3.903, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.3448237478733063, | |
| "eval_runtime": 8.8551, | |
| "eval_samples_per_second": 31.281, | |
| "eval_steps_per_second": 3.953, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00043589743589743596, | |
| "loss": 0.3164, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.33612075448036194, | |
| "eval_runtime": 8.8349, | |
| "eval_samples_per_second": 31.353, | |
| "eval_steps_per_second": 3.962, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00035576923076923074, | |
| "loss": 0.3153, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.367554634809494, | |
| "eval_runtime": 8.8354, | |
| "eval_samples_per_second": 31.351, | |
| "eval_steps_per_second": 3.961, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3463309407234192, | |
| "eval_runtime": 8.8416, | |
| "eval_samples_per_second": 31.329, | |
| "eval_steps_per_second": 3.959, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0002756410256410257, | |
| "loss": 0.3145, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.34912317991256714, | |
| "eval_runtime": 8.8368, | |
| "eval_samples_per_second": 31.346, | |
| "eval_steps_per_second": 3.961, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3599321246147156, | |
| "eval_runtime": 8.8319, | |
| "eval_samples_per_second": 31.363, | |
| "eval_steps_per_second": 3.963, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00019551282051282054, | |
| "loss": 0.3151, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3457310199737549, | |
| "eval_runtime": 8.9008, | |
| "eval_samples_per_second": 31.121, | |
| "eval_steps_per_second": 3.932, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 0.3103, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.34887006878852844, | |
| "eval_runtime": 8.8994, | |
| "eval_samples_per_second": 31.126, | |
| "eval_steps_per_second": 3.933, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.348056823015213, | |
| "eval_runtime": 8.9031, | |
| "eval_samples_per_second": 31.113, | |
| "eval_steps_per_second": 3.931, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 3.5256410256410254e-05, | |
| "loss": 0.314, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.35035568475723267, | |
| "eval_runtime": 8.8809, | |
| "eval_samples_per_second": 31.191, | |
| "eval_steps_per_second": 3.941, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 48, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.3594475073692126, | |
| "train_runtime": 8160.6004, | |
| "train_samples_per_second": 18.307, | |
| "train_steps_per_second": 2.294 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |