| { | |
| "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": 0.516245487364621, | |
| "eval_loss": 30.45633316040039, | |
| "eval_runtime": 7.0533, | |
| "eval_samples_per_second": 39.273, | |
| "eval_steps_per_second": 4.962, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0009732905982905983, | |
| "loss": 31.8281, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 28.268251419067383, | |
| "eval_runtime": 7.0517, | |
| "eval_samples_per_second": 39.281, | |
| "eval_steps_per_second": 4.963, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 22.482925415039062, | |
| "eval_runtime": 7.0537, | |
| "eval_samples_per_second": 39.27, | |
| "eval_steps_per_second": 4.962, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0009465811965811966, | |
| "loss": 26.6026, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 17.250818252563477, | |
| "eval_runtime": 7.0937, | |
| "eval_samples_per_second": 39.049, | |
| "eval_steps_per_second": 4.934, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.516245487364621, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0009198717948717949, | |
| "loss": 20.7188, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 15.695619583129883, | |
| "eval_runtime": 7.1074, | |
| "eval_samples_per_second": 38.974, | |
| "eval_steps_per_second": 4.924, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 14.759888648986816, | |
| "eval_runtime": 6.9232, | |
| "eval_samples_per_second": 40.011, | |
| "eval_steps_per_second": 5.055, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.0008931623931623932, | |
| "loss": 18.7808, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 14.433088302612305, | |
| "eval_runtime": 7.0834, | |
| "eval_samples_per_second": 39.106, | |
| "eval_steps_per_second": 4.941, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 13.9365873336792, | |
| "eval_runtime": 7.0894, | |
| "eval_samples_per_second": 39.072, | |
| "eval_steps_per_second": 4.937, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0008664529914529915, | |
| "loss": 18.0838, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.634007453918457, | |
| "eval_runtime": 7.127, | |
| "eval_samples_per_second": 38.867, | |
| "eval_steps_per_second": 4.911, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0008397435897435898, | |
| "loss": 17.722, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.437921524047852, | |
| "eval_runtime": 7.1307, | |
| "eval_samples_per_second": 38.846, | |
| "eval_steps_per_second": 4.908, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.439308166503906, | |
| "eval_runtime": 7.0992, | |
| "eval_samples_per_second": 39.019, | |
| "eval_steps_per_second": 4.93, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.0008130341880341881, | |
| "loss": 17.4783, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 13.137593269348145, | |
| "eval_runtime": 7.1532, | |
| "eval_samples_per_second": 38.724, | |
| "eval_steps_per_second": 4.893, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.0007863247863247863, | |
| "loss": 17.2699, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.95992374420166, | |
| "eval_runtime": 7.0409, | |
| "eval_samples_per_second": 39.341, | |
| "eval_steps_per_second": 4.971, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.848048210144043, | |
| "eval_runtime": 7.0065, | |
| "eval_samples_per_second": 39.535, | |
| "eval_steps_per_second": 4.995, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0007596153846153846, | |
| "loss": 17.0966, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.781341552734375, | |
| "eval_runtime": 7.0694, | |
| "eval_samples_per_second": 39.183, | |
| "eval_steps_per_second": 4.951, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.691984176635742, | |
| "eval_runtime": 7.0798, | |
| "eval_samples_per_second": 39.125, | |
| "eval_steps_per_second": 4.944, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0007329059829059829, | |
| "loss": 16.9613, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.569376945495605, | |
| "eval_runtime": 6.9647, | |
| "eval_samples_per_second": 39.772, | |
| "eval_steps_per_second": 5.025, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.0007061965811965813, | |
| "loss": 16.848, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.51942253112793, | |
| "eval_runtime": 7.1195, | |
| "eval_samples_per_second": 38.907, | |
| "eval_steps_per_second": 4.916, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.459056854248047, | |
| "eval_runtime": 7.0039, | |
| "eval_samples_per_second": 39.55, | |
| "eval_steps_per_second": 4.997, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0006794871794871796, | |
| "loss": 16.7661, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.382737159729004, | |
| "eval_runtime": 7.1366, | |
| "eval_samples_per_second": 38.814, | |
| "eval_steps_per_second": 4.904, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0006527777777777778, | |
| "loss": 16.6825, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.341012001037598, | |
| "eval_runtime": 6.9768, | |
| "eval_samples_per_second": 39.703, | |
| "eval_steps_per_second": 5.017, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.324116706848145, | |
| "eval_runtime": 7.0623, | |
| "eval_samples_per_second": 39.223, | |
| "eval_steps_per_second": 4.956, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0006260683760683761, | |
| "loss": 16.5963, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.329614639282227, | |
| "eval_runtime": 6.9809, | |
| "eval_samples_per_second": 39.68, | |
| "eval_steps_per_second": 5.014, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.261089324951172, | |
| "eval_runtime": 7.0903, | |
| "eval_samples_per_second": 39.067, | |
| "eval_steps_per_second": 4.936, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0005993589743589744, | |
| "loss": 16.5513, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.151515007019043, | |
| "eval_runtime": 7.0185, | |
| "eval_samples_per_second": 39.467, | |
| "eval_steps_per_second": 4.987, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0005726495726495727, | |
| "loss": 16.4926, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.119367599487305, | |
| "eval_runtime": 7.1667, | |
| "eval_samples_per_second": 38.651, | |
| "eval_steps_per_second": 4.884, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.105155944824219, | |
| "eval_runtime": 6.9401, | |
| "eval_samples_per_second": 39.913, | |
| "eval_steps_per_second": 5.043, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.000545940170940171, | |
| "loss": 16.4398, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 12.051624298095703, | |
| "eval_runtime": 7.0895, | |
| "eval_samples_per_second": 39.072, | |
| "eval_steps_per_second": 4.937, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0005192307692307693, | |
| "loss": 16.399, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.49458483754512633, | |
| "eval_loss": 12.021004676818848, | |
| "eval_runtime": 7.1719, | |
| "eval_samples_per_second": 38.623, | |
| "eval_steps_per_second": 4.88, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 12.005374908447266, | |
| "eval_runtime": 7.026, | |
| "eval_samples_per_second": 39.425, | |
| "eval_steps_per_second": 4.981, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0004925213675213676, | |
| "loss": 16.3657, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.996041297912598, | |
| "eval_runtime": 7.1337, | |
| "eval_samples_per_second": 38.83, | |
| "eval_steps_per_second": 4.906, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.954824447631836, | |
| "eval_runtime": 7.0913, | |
| "eval_samples_per_second": 39.062, | |
| "eval_steps_per_second": 4.936, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.00046581196581196583, | |
| "loss": 16.3306, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.933246612548828, | |
| "eval_runtime": 7.0339, | |
| "eval_samples_per_second": 39.381, | |
| "eval_steps_per_second": 4.976, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0004391025641025641, | |
| "loss": 16.294, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.914789199829102, | |
| "eval_runtime": 7.1276, | |
| "eval_samples_per_second": 38.863, | |
| "eval_steps_per_second": 4.91, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.92249870300293, | |
| "eval_runtime": 7.0158, | |
| "eval_samples_per_second": 39.482, | |
| "eval_steps_per_second": 4.989, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0004123931623931624, | |
| "loss": 16.2657, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 11.87264633178711, | |
| "eval_runtime": 7.0946, | |
| "eval_samples_per_second": 39.044, | |
| "eval_steps_per_second": 4.933, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0003856837606837607, | |
| "loss": 16.2465, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.845185279846191, | |
| "eval_runtime": 3.3622, | |
| "eval_samples_per_second": 82.387, | |
| "eval_steps_per_second": 10.41, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.834094047546387, | |
| "eval_runtime": 3.3675, | |
| "eval_samples_per_second": 82.257, | |
| "eval_steps_per_second": 10.394, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.000358974358974359, | |
| "loss": 16.208, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.823224067687988, | |
| "eval_runtime": 3.3616, | |
| "eval_samples_per_second": 82.4, | |
| "eval_steps_per_second": 10.412, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.797883033752441, | |
| "eval_runtime": 3.372, | |
| "eval_samples_per_second": 82.146, | |
| "eval_steps_per_second": 10.379, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.00033226495726495727, | |
| "loss": 16.191, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.789505004882812, | |
| "eval_runtime": 3.3805, | |
| "eval_samples_per_second": 81.94, | |
| "eval_steps_per_second": 10.353, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0003055555555555556, | |
| "loss": 16.1729, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.839137077331543, | |
| "eval_runtime": 3.3622, | |
| "eval_samples_per_second": 82.387, | |
| "eval_steps_per_second": 10.41, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.761892318725586, | |
| "eval_runtime": 3.3566, | |
| "eval_samples_per_second": 82.525, | |
| "eval_steps_per_second": 10.427, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0002788461538461539, | |
| "loss": 16.1571, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.750166893005371, | |
| "eval_runtime": 3.3501, | |
| "eval_samples_per_second": 82.684, | |
| "eval_steps_per_second": 10.447, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.00025213675213675216, | |
| "loss": 16.1268, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.751955032348633, | |
| "eval_runtime": 3.3666, | |
| "eval_samples_per_second": 82.278, | |
| "eval_steps_per_second": 10.396, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.75387954711914, | |
| "eval_runtime": 3.3569, | |
| "eval_samples_per_second": 82.516, | |
| "eval_steps_per_second": 10.426, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.00022542735042735044, | |
| "loss": 16.1194, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.754090309143066, | |
| "eval_runtime": 3.359, | |
| "eval_samples_per_second": 82.465, | |
| "eval_steps_per_second": 10.42, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.712992668151855, | |
| "eval_runtime": 3.3491, | |
| "eval_samples_per_second": 82.708, | |
| "eval_steps_per_second": 10.451, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0001987179487179487, | |
| "loss": 16.11, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.701953887939453, | |
| "eval_runtime": 3.3622, | |
| "eval_samples_per_second": 82.386, | |
| "eval_steps_per_second": 10.41, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.00017200854700854702, | |
| "loss": 16.0989, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.694924354553223, | |
| "eval_runtime": 3.3584, | |
| "eval_samples_per_second": 82.481, | |
| "eval_steps_per_second": 10.422, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.702590942382812, | |
| "eval_runtime": 3.3669, | |
| "eval_samples_per_second": 82.272, | |
| "eval_steps_per_second": 10.395, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00014529914529914532, | |
| "loss": 16.0802, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.70562744140625, | |
| "eval_runtime": 3.3506, | |
| "eval_samples_per_second": 82.672, | |
| "eval_steps_per_second": 10.446, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00011858974358974358, | |
| "loss": 16.0765, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.679302215576172, | |
| "eval_runtime": 3.3699, | |
| "eval_samples_per_second": 82.199, | |
| "eval_steps_per_second": 10.386, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 11.675891876220703, | |
| "eval_runtime": 3.3612, | |
| "eval_samples_per_second": 82.41, | |
| "eval_steps_per_second": 10.413, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 9.188034188034189e-05, | |
| "loss": 16.0629, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.671220779418945, | |
| "eval_runtime": 3.359, | |
| "eval_samples_per_second": 82.464, | |
| "eval_steps_per_second": 10.42, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.49458483754512633, | |
| "eval_loss": 11.665974617004395, | |
| "eval_runtime": 3.3679, | |
| "eval_samples_per_second": 82.247, | |
| "eval_steps_per_second": 10.392, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 6.517094017094018e-05, | |
| "loss": 16.0619, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.666152000427246, | |
| "eval_runtime": 3.3732, | |
| "eval_samples_per_second": 82.117, | |
| "eval_steps_per_second": 10.376, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 16.0566, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.664301872253418, | |
| "eval_runtime": 3.3723, | |
| "eval_samples_per_second": 82.14, | |
| "eval_steps_per_second": 10.379, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.661619186401367, | |
| "eval_runtime": 3.3491, | |
| "eval_samples_per_second": 82.709, | |
| "eval_steps_per_second": 10.451, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 1.1752136752136752e-05, | |
| "loss": 16.0547, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 11.661417961120605, | |
| "eval_runtime": 3.3494, | |
| "eval_samples_per_second": 82.702, | |
| "eval_steps_per_second": 10.45, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 17.346778074085204, | |
| "train_runtime": 5173.7493, | |
| "train_samples_per_second": 28.877, | |
| "train_steps_per_second": 3.618 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |