| { | |
| "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": 0.5270758122743683, | |
| "eval_loss": 0.07883936911821365, | |
| "eval_runtime": 4.3827, | |
| "eval_samples_per_second": 63.203, | |
| "eval_steps_per_second": 7.986, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.003893162393162393, | |
| "loss": 0.1715, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.2058744877576828, | |
| "eval_runtime": 4.4761, | |
| "eval_samples_per_second": 61.884, | |
| "eval_steps_per_second": 7.819, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.11342689394950867, | |
| "eval_runtime": 4.4913, | |
| "eval_samples_per_second": 61.675, | |
| "eval_steps_per_second": 7.793, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0037863247863247863, | |
| "loss": 0.1222, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.08309175819158554, | |
| "eval_runtime": 4.5034, | |
| "eval_samples_per_second": 61.509, | |
| "eval_steps_per_second": 7.772, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0036794871794871794, | |
| "loss": 0.1187, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5703971119133574, | |
| "eval_loss": 0.07322770357131958, | |
| "eval_runtime": 4.5054, | |
| "eval_samples_per_second": 61.482, | |
| "eval_steps_per_second": 7.769, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07959606498479843, | |
| "eval_runtime": 4.4974, | |
| "eval_samples_per_second": 61.591, | |
| "eval_steps_per_second": 7.782, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.003572649572649573, | |
| "loss": 0.0991, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0745367482304573, | |
| "eval_runtime": 4.4876, | |
| "eval_samples_per_second": 61.725, | |
| "eval_steps_per_second": 7.799, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 0.0715838074684143, | |
| "eval_runtime": 4.4817, | |
| "eval_samples_per_second": 61.807, | |
| "eval_steps_per_second": 7.81, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.003465811965811966, | |
| "loss": 0.0819, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.07054454833269119, | |
| "eval_runtime": 4.4827, | |
| "eval_samples_per_second": 61.793, | |
| "eval_steps_per_second": 7.808, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.003358974358974359, | |
| "loss": 0.0807, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07019203901290894, | |
| "eval_runtime": 4.4883, | |
| "eval_samples_per_second": 61.716, | |
| "eval_steps_per_second": 7.798, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07131501287221909, | |
| "eval_runtime": 4.4864, | |
| "eval_samples_per_second": 61.742, | |
| "eval_steps_per_second": 7.801, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.0032521367521367523, | |
| "loss": 0.0802, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07025401294231415, | |
| "eval_runtime": 4.4874, | |
| "eval_samples_per_second": 61.728, | |
| "eval_steps_per_second": 7.8, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.0031452991452991454, | |
| "loss": 0.0795, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07835417985916138, | |
| "eval_runtime": 4.4839, | |
| "eval_samples_per_second": 61.776, | |
| "eval_steps_per_second": 7.806, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.07064678519964218, | |
| "eval_runtime": 4.4919, | |
| "eval_samples_per_second": 61.666, | |
| "eval_steps_per_second": 7.792, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0030384615384615385, | |
| "loss": 0.0794, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07303398102521896, | |
| "eval_runtime": 4.4936, | |
| "eval_samples_per_second": 61.643, | |
| "eval_steps_per_second": 7.789, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.0706457644701004, | |
| "eval_runtime": 4.489, | |
| "eval_samples_per_second": 61.706, | |
| "eval_steps_per_second": 7.797, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0029316239316239316, | |
| "loss": 0.0806, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 0.07106263935565948, | |
| "eval_runtime": 4.4937, | |
| "eval_samples_per_second": 61.642, | |
| "eval_steps_per_second": 7.789, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.002824786324786325, | |
| "loss": 0.0811, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.0703640729188919, | |
| "eval_runtime": 4.4948, | |
| "eval_samples_per_second": 61.626, | |
| "eval_steps_per_second": 7.787, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.48736462093862815, | |
| "eval_loss": 0.07006794959306717, | |
| "eval_runtime": 4.4898, | |
| "eval_samples_per_second": 61.695, | |
| "eval_steps_per_second": 7.795, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5703971119133574, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0027179487179487182, | |
| "loss": 0.0798, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6101083032490975, | |
| "eval_loss": 0.07190611958503723, | |
| "eval_runtime": 4.493, | |
| "eval_samples_per_second": 61.651, | |
| "eval_steps_per_second": 7.79, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0026111111111111114, | |
| "loss": 0.0793, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.07052430510520935, | |
| "eval_runtime": 4.4908, | |
| "eval_samples_per_second": 61.682, | |
| "eval_steps_per_second": 7.794, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5884476534296029, | |
| "eval_loss": 0.07068859040737152, | |
| "eval_runtime": 4.4944, | |
| "eval_samples_per_second": 61.633, | |
| "eval_steps_per_second": 7.788, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0025042735042735045, | |
| "loss": 0.0795, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07123356312513351, | |
| "eval_runtime": 4.4895, | |
| "eval_samples_per_second": 61.7, | |
| "eval_steps_per_second": 7.796, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07049828767776489, | |
| "eval_runtime": 4.4902, | |
| "eval_samples_per_second": 61.69, | |
| "eval_steps_per_second": 7.795, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0023974358974358976, | |
| "loss": 0.0796, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.07892809063196182, | |
| "eval_runtime": 4.4907, | |
| "eval_samples_per_second": 61.682, | |
| "eval_steps_per_second": 7.794, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0022905982905982907, | |
| "loss": 0.0796, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.07052510976791382, | |
| "eval_runtime": 4.4886, | |
| "eval_samples_per_second": 61.712, | |
| "eval_steps_per_second": 7.798, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07029584050178528, | |
| "eval_runtime": 4.4833, | |
| "eval_samples_per_second": 61.785, | |
| "eval_steps_per_second": 7.807, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.002183760683760684, | |
| "loss": 0.0787, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.07033976167440414, | |
| "eval_runtime": 4.4877, | |
| "eval_samples_per_second": 61.725, | |
| "eval_steps_per_second": 7.799, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0020769230769230773, | |
| "loss": 0.079, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07161471992731094, | |
| "eval_runtime": 4.4853, | |
| "eval_samples_per_second": 61.758, | |
| "eval_steps_per_second": 7.803, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5703971119133574, | |
| "eval_loss": 0.07392293959856033, | |
| "eval_runtime": 4.4851, | |
| "eval_samples_per_second": 61.76, | |
| "eval_steps_per_second": 7.804, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0019700854700854704, | |
| "loss": 0.0788, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5631768953068592, | |
| "eval_loss": 0.07494190335273743, | |
| "eval_runtime": 4.4843, | |
| "eval_samples_per_second": 61.771, | |
| "eval_steps_per_second": 7.805, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0710810124874115, | |
| "eval_runtime": 4.4859, | |
| "eval_samples_per_second": 61.749, | |
| "eval_steps_per_second": 7.802, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0018632478632478633, | |
| "loss": 0.0789, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.07050064951181412, | |
| "eval_runtime": 4.4845, | |
| "eval_samples_per_second": 61.768, | |
| "eval_steps_per_second": 7.805, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0017564102564102564, | |
| "loss": 0.0786, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.06995219737291336, | |
| "eval_runtime": 4.476, | |
| "eval_samples_per_second": 61.886, | |
| "eval_steps_per_second": 7.82, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.06990911066532135, | |
| "eval_runtime": 4.4873, | |
| "eval_samples_per_second": 61.73, | |
| "eval_steps_per_second": 7.8, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0016495726495726495, | |
| "loss": 0.0785, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07145760208368301, | |
| "eval_runtime": 4.4889, | |
| "eval_samples_per_second": 61.707, | |
| "eval_steps_per_second": 7.797, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 19, | |
| "best_eval_accuracy": 0.6101083032490975, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0015427350427350429, | |
| "loss": 0.0784, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6353790613718412, | |
| "eval_loss": 0.07159464806318283, | |
| "eval_runtime": 4.4862, | |
| "eval_samples_per_second": 61.745, | |
| "eval_steps_per_second": 7.802, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07186750322580338, | |
| "eval_runtime": 4.4867, | |
| "eval_samples_per_second": 61.737, | |
| "eval_steps_per_second": 7.801, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.001435897435897436, | |
| "loss": 0.0781, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5487364620938628, | |
| "eval_loss": 0.07000464200973511, | |
| "eval_runtime": 4.4864, | |
| "eval_samples_per_second": 61.742, | |
| "eval_steps_per_second": 7.801, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5848375451263538, | |
| "eval_loss": 0.06997690349817276, | |
| "eval_runtime": 4.4896, | |
| "eval_samples_per_second": 61.699, | |
| "eval_steps_per_second": 7.796, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.001329059829059829, | |
| "loss": 0.0778, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6173285198555957, | |
| "eval_loss": 0.07039925456047058, | |
| "eval_runtime": 4.4877, | |
| "eval_samples_per_second": 61.725, | |
| "eval_steps_per_second": 7.799, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0012222222222222224, | |
| "loss": 0.0778, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5848375451263538, | |
| "eval_loss": 0.07050343602895737, | |
| "eval_runtime": 4.4896, | |
| "eval_samples_per_second": 61.699, | |
| "eval_steps_per_second": 7.796, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.07049660384654999, | |
| "eval_runtime": 4.487, | |
| "eval_samples_per_second": 61.734, | |
| "eval_steps_per_second": 7.8, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0011153846153846155, | |
| "loss": 0.078, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.07012051343917847, | |
| "eval_runtime": 4.4899, | |
| "eval_samples_per_second": 61.694, | |
| "eval_steps_per_second": 7.795, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0010085470085470086, | |
| "loss": 0.0776, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5956678700361011, | |
| "eval_loss": 0.07043617963790894, | |
| "eval_runtime": 4.4893, | |
| "eval_samples_per_second": 61.702, | |
| "eval_steps_per_second": 7.796, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5848375451263538, | |
| "eval_loss": 0.07017319649457932, | |
| "eval_runtime": 4.4885, | |
| "eval_samples_per_second": 61.714, | |
| "eval_steps_per_second": 7.798, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0009017094017094017, | |
| "loss": 0.0772, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07025384157896042, | |
| "eval_runtime": 4.4917, | |
| "eval_samples_per_second": 61.669, | |
| "eval_steps_per_second": 7.792, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.0697227343916893, | |
| "eval_runtime": 4.4921, | |
| "eval_samples_per_second": 61.664, | |
| "eval_steps_per_second": 7.791, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0007948717948717948, | |
| "loss": 0.0773, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 0.06964733451604843, | |
| "eval_runtime": 4.5022, | |
| "eval_samples_per_second": 61.526, | |
| "eval_steps_per_second": 7.774, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0006880341880341881, | |
| "loss": 0.0772, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07015614211559296, | |
| "eval_runtime": 4.4706, | |
| "eval_samples_per_second": 61.96, | |
| "eval_steps_per_second": 7.829, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.07005967199802399, | |
| "eval_runtime": 4.4652, | |
| "eval_samples_per_second": 62.036, | |
| "eval_steps_per_second": 7.838, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0005811965811965813, | |
| "loss": 0.0776, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.07058187574148178, | |
| "eval_runtime": 4.465, | |
| "eval_samples_per_second": 62.038, | |
| "eval_steps_per_second": 7.839, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00047435897435897434, | |
| "loss": 0.0772, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5054151624548736, | |
| "eval_loss": 0.06982703506946564, | |
| "eval_runtime": 4.4547, | |
| "eval_samples_per_second": 62.182, | |
| "eval_steps_per_second": 7.857, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.07056145370006561, | |
| "eval_runtime": 4.4549, | |
| "eval_samples_per_second": 62.179, | |
| "eval_steps_per_second": 7.857, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00036752136752136755, | |
| "loss": 0.0766, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.07077504694461823, | |
| "eval_runtime": 4.4385, | |
| "eval_samples_per_second": 62.409, | |
| "eval_steps_per_second": 7.886, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.07004080712795258, | |
| "eval_runtime": 4.4393, | |
| "eval_samples_per_second": 62.397, | |
| "eval_steps_per_second": 7.884, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.0002606837606837607, | |
| "loss": 0.0766, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.06971540302038193, | |
| "eval_runtime": 4.4341, | |
| "eval_samples_per_second": 62.47, | |
| "eval_steps_per_second": 7.893, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.0767, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.07002807408571243, | |
| "eval_runtime": 4.4375, | |
| "eval_samples_per_second": 62.422, | |
| "eval_steps_per_second": 7.887, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5234657039711191, | |
| "eval_loss": 0.06969156861305237, | |
| "eval_runtime": 4.4353, | |
| "eval_samples_per_second": 62.454, | |
| "eval_steps_per_second": 7.891, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 4.700854700854701e-05, | |
| "loss": 0.0767, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.06970320641994476, | |
| "eval_runtime": 4.4366, | |
| "eval_samples_per_second": 62.435, | |
| "eval_steps_per_second": 7.889, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 36, | |
| "best_eval_accuracy": 0.6353790613718412, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.0838659094949054, | |
| "train_runtime": 4072.213, | |
| "train_samples_per_second": 36.688, | |
| "train_steps_per_second": 4.597 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |