| { | |
| "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": 0.4729241877256318, | |
| "eval_loss": 0.15293638408184052, | |
| "eval_runtime": 4.3856, | |
| "eval_samples_per_second": 63.161, | |
| "eval_steps_per_second": 7.981, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.004866452991452991, | |
| "loss": 0.2201, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.10219389200210571, | |
| "eval_runtime": 4.4747, | |
| "eval_samples_per_second": 61.904, | |
| "eval_steps_per_second": 7.822, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.26191186904907227, | |
| "eval_runtime": 4.4885, | |
| "eval_samples_per_second": 61.714, | |
| "eval_steps_per_second": 7.798, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.004732905982905983, | |
| "loss": 0.1563, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.07380817085504532, | |
| "eval_runtime": 4.4993, | |
| "eval_samples_per_second": 61.565, | |
| "eval_steps_per_second": 7.779, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.004599358974358974, | |
| "loss": 0.0889, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 0.07089700549840927, | |
| "eval_runtime": 4.4954, | |
| "eval_samples_per_second": 61.619, | |
| "eval_steps_per_second": 7.786, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07577553391456604, | |
| "eval_runtime": 4.4933, | |
| "eval_samples_per_second": 61.647, | |
| "eval_steps_per_second": 7.789, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.004465811965811966, | |
| "loss": 0.0808, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07322199642658234, | |
| "eval_runtime": 4.4858, | |
| "eval_samples_per_second": 61.751, | |
| "eval_steps_per_second": 7.802, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 0.07163483649492264, | |
| "eval_runtime": 4.4829, | |
| "eval_samples_per_second": 61.79, | |
| "eval_steps_per_second": 7.807, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.004332264957264957, | |
| "loss": 0.0802, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.07071372121572495, | |
| "eval_runtime": 4.4841, | |
| "eval_samples_per_second": 61.774, | |
| "eval_steps_per_second": 7.805, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.004198717948717949, | |
| "loss": 0.0819, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07121473550796509, | |
| "eval_runtime": 4.4844, | |
| "eval_samples_per_second": 61.77, | |
| "eval_steps_per_second": 7.805, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07059402763843536, | |
| "eval_runtime": 4.4875, | |
| "eval_samples_per_second": 61.727, | |
| "eval_steps_per_second": 7.799, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00406517094017094, | |
| "loss": 0.0818, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4620938628158845, | |
| "eval_loss": 0.07027973979711533, | |
| "eval_runtime": 4.4847, | |
| "eval_samples_per_second": 61.766, | |
| "eval_steps_per_second": 7.804, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.003931623931623931, | |
| "loss": 0.08, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07372691482305527, | |
| "eval_runtime": 4.4841, | |
| "eval_samples_per_second": 61.774, | |
| "eval_steps_per_second": 7.805, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.07121168822050095, | |
| "eval_runtime": 4.4841, | |
| "eval_samples_per_second": 61.774, | |
| "eval_steps_per_second": 7.805, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.003798076923076923, | |
| "loss": 0.0803, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07377327233552933, | |
| "eval_runtime": 4.4908, | |
| "eval_samples_per_second": 61.682, | |
| "eval_steps_per_second": 7.794, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07084672898054123, | |
| "eval_runtime": 4.4838, | |
| "eval_samples_per_second": 61.778, | |
| "eval_steps_per_second": 7.806, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.003664529914529914, | |
| "loss": 0.0807, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 0.0708812028169632, | |
| "eval_runtime": 4.485, | |
| "eval_samples_per_second": 61.761, | |
| "eval_steps_per_second": 7.804, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.003530982905982906, | |
| "loss": 0.082, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5523465703971119, | |
| "eval_loss": 0.0720214918255806, | |
| "eval_runtime": 4.4868, | |
| "eval_samples_per_second": 61.736, | |
| "eval_steps_per_second": 7.801, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07122407853603363, | |
| "eval_runtime": 4.49, | |
| "eval_samples_per_second": 61.693, | |
| "eval_steps_per_second": 7.795, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0033974358974358976, | |
| "loss": 0.0806, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5090252707581228, | |
| "eval_loss": 0.07032328844070435, | |
| "eval_runtime": 4.4893, | |
| "eval_samples_per_second": 61.703, | |
| "eval_steps_per_second": 7.796, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.003263888888888889, | |
| "loss": 0.0801, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07104188203811646, | |
| "eval_runtime": 4.488, | |
| "eval_samples_per_second": 61.72, | |
| "eval_steps_per_second": 7.799, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.07005982100963593, | |
| "eval_runtime": 4.4962, | |
| "eval_samples_per_second": 61.608, | |
| "eval_steps_per_second": 7.784, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0031303418803418806, | |
| "loss": 0.0798, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.07032880932092667, | |
| "eval_runtime": 4.4887, | |
| "eval_samples_per_second": 61.711, | |
| "eval_steps_per_second": 7.797, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07051917910575867, | |
| "eval_runtime": 4.4932, | |
| "eval_samples_per_second": 61.649, | |
| "eval_steps_per_second": 7.79, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0029967948717948716, | |
| "loss": 0.0854, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5523465703971119, | |
| "eval_loss": 0.07042864710092545, | |
| "eval_runtime": 4.4874, | |
| "eval_samples_per_second": 61.728, | |
| "eval_steps_per_second": 7.8, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.002863247863247863, | |
| "loss": 0.0793, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.07020144909620285, | |
| "eval_runtime": 4.4906, | |
| "eval_samples_per_second": 61.684, | |
| "eval_steps_per_second": 7.794, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07208646833896637, | |
| "eval_runtime": 4.4856, | |
| "eval_samples_per_second": 61.753, | |
| "eval_steps_per_second": 7.803, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0027297008547008546, | |
| "loss": 0.0792, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07201223820447922, | |
| "eval_runtime": 4.4887, | |
| "eval_samples_per_second": 61.711, | |
| "eval_steps_per_second": 7.797, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0025961538461538466, | |
| "loss": 0.0794, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.0713350772857666, | |
| "eval_runtime": 4.4877, | |
| "eval_samples_per_second": 61.724, | |
| "eval_steps_per_second": 7.799, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5595667870036101, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5631768953068592, | |
| "eval_loss": 0.07010631263256073, | |
| "eval_runtime": 4.4831, | |
| "eval_samples_per_second": 61.787, | |
| "eval_steps_per_second": 7.807, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 29, | |
| "best_eval_accuracy": 0.5631768953068592, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0024626068376068376, | |
| "loss": 0.0785, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6101083032490975, | |
| "eval_loss": 0.07099565863609314, | |
| "eval_runtime": 4.4893, | |
| "eval_samples_per_second": 61.703, | |
| "eval_steps_per_second": 7.796, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.07032310217618942, | |
| "eval_runtime": 4.4879, | |
| "eval_samples_per_second": 61.721, | |
| "eval_steps_per_second": 7.799, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.002329059829059829, | |
| "loss": 0.0786, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07281779497861862, | |
| "eval_runtime": 4.4847, | |
| "eval_samples_per_second": 61.766, | |
| "eval_steps_per_second": 7.804, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0021955128205128206, | |
| "loss": 0.0791, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.5054151624548736, | |
| "eval_loss": 0.07028384506702423, | |
| "eval_runtime": 4.4824, | |
| "eval_samples_per_second": 61.798, | |
| "eval_steps_per_second": 7.808, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6173285198555957, | |
| "eval_loss": 0.07163991034030914, | |
| "eval_runtime": 4.4867, | |
| "eval_samples_per_second": 61.738, | |
| "eval_steps_per_second": 7.801, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.002061965811965812, | |
| "loss": 0.0789, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07081528007984161, | |
| "eval_runtime": 4.4866, | |
| "eval_samples_per_second": 61.739, | |
| "eval_steps_per_second": 7.801, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0019284188034188036, | |
| "loss": 0.0786, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07695722579956055, | |
| "eval_runtime": 4.4827, | |
| "eval_samples_per_second": 61.793, | |
| "eval_steps_per_second": 7.808, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07178593426942825, | |
| "eval_runtime": 4.4814, | |
| "eval_samples_per_second": 61.811, | |
| "eval_steps_per_second": 7.81, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0017948717948717949, | |
| "loss": 0.0784, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.06998021900653839, | |
| "eval_runtime": 4.4856, | |
| "eval_samples_per_second": 61.753, | |
| "eval_steps_per_second": 7.803, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5234657039711191, | |
| "eval_loss": 0.06990227848291397, | |
| "eval_runtime": 4.4914, | |
| "eval_samples_per_second": 61.673, | |
| "eval_steps_per_second": 7.793, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0016613247863247864, | |
| "loss": 0.0775, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6137184115523465, | |
| "eval_loss": 0.06979037076234818, | |
| "eval_runtime": 4.4875, | |
| "eval_samples_per_second": 61.727, | |
| "eval_steps_per_second": 7.799, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0015277777777777779, | |
| "loss": 0.0779, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.06967325508594513, | |
| "eval_runtime": 4.4905, | |
| "eval_samples_per_second": 61.686, | |
| "eval_steps_per_second": 7.794, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.6173285198555957, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.06980358064174652, | |
| "eval_runtime": 4.4879, | |
| "eval_samples_per_second": 61.721, | |
| "eval_steps_per_second": 7.799, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0013942307692307694, | |
| "loss": 0.0777, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5848375451263538, | |
| "eval_loss": 0.06972871720790863, | |
| "eval_runtime": 4.5198, | |
| "eval_samples_per_second": 61.286, | |
| "eval_steps_per_second": 7.744, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0012606837606837606, | |
| "loss": 0.0776, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.06987190246582031, | |
| "eval_runtime": 4.501, | |
| "eval_samples_per_second": 61.542, | |
| "eval_steps_per_second": 7.776, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6028880866425993, | |
| "eval_loss": 0.06966899335384369, | |
| "eval_runtime": 4.4681, | |
| "eval_samples_per_second": 61.995, | |
| "eval_steps_per_second": 7.833, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0011271367521367521, | |
| "loss": 0.0769, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.07046782970428467, | |
| "eval_runtime": 4.4607, | |
| "eval_samples_per_second": 62.098, | |
| "eval_steps_per_second": 7.846, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.06947591155767441, | |
| "eval_runtime": 4.4615, | |
| "eval_samples_per_second": 62.087, | |
| "eval_steps_per_second": 7.845, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0009935897435897436, | |
| "loss": 0.077, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5667870036101083, | |
| "eval_loss": 0.06946070492267609, | |
| "eval_runtime": 4.4574, | |
| "eval_samples_per_second": 62.144, | |
| "eval_steps_per_second": 7.852, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0008600427350427351, | |
| "loss": 0.077, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5018050541516246, | |
| "eval_loss": 0.06961851567029953, | |
| "eval_runtime": 4.4447, | |
| "eval_samples_per_second": 62.321, | |
| "eval_steps_per_second": 7.874, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.49458483754512633, | |
| "eval_loss": 0.07000398635864258, | |
| "eval_runtime": 4.4397, | |
| "eval_samples_per_second": 62.391, | |
| "eval_steps_per_second": 7.883, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0007264957264957266, | |
| "loss": 0.0774, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 0.0700514167547226, | |
| "eval_runtime": 4.4359, | |
| "eval_samples_per_second": 62.445, | |
| "eval_steps_per_second": 7.89, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.000592948717948718, | |
| "loss": 0.0767, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5812274368231047, | |
| "eval_loss": 0.06938585638999939, | |
| "eval_runtime": 4.4418, | |
| "eval_samples_per_second": 62.363, | |
| "eval_steps_per_second": 7.88, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.07005595415830612, | |
| "eval_runtime": 4.4342, | |
| "eval_samples_per_second": 62.469, | |
| "eval_steps_per_second": 7.893, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00045940170940170943, | |
| "loss": 0.0761, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.07062944769859314, | |
| "eval_runtime": 4.4382, | |
| "eval_samples_per_second": 62.412, | |
| "eval_steps_per_second": 7.886, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 42, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.06952185928821564, | |
| "eval_runtime": 4.4379, | |
| "eval_samples_per_second": 62.417, | |
| "eval_steps_per_second": 7.887, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 55, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00032585470085470087, | |
| "loss": 0.0762, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.6028880866425993, | |
| "eval_loss": 0.0693010687828064, | |
| "eval_runtime": 4.4361, | |
| "eval_samples_per_second": 62.442, | |
| "eval_steps_per_second": 7.89, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 55, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 0.0763, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.06962151825428009, | |
| "eval_runtime": 4.4368, | |
| "eval_samples_per_second": 62.432, | |
| "eval_steps_per_second": 7.889, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 55, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5740072202166066, | |
| "eval_loss": 0.06931070238351822, | |
| "eval_runtime": 4.4366, | |
| "eval_samples_per_second": 62.435, | |
| "eval_steps_per_second": 7.889, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 55, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-05, | |
| "loss": 0.0763, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5812274368231047, | |
| "eval_loss": 0.06930926442146301, | |
| "eval_runtime": 4.4417, | |
| "eval_samples_per_second": 62.364, | |
| "eval_steps_per_second": 7.88, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 55, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.08502325043719039, | |
| "train_runtime": 4069.7527, | |
| "train_samples_per_second": 36.71, | |
| "train_steps_per_second": 4.6 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |