| { | |
| "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": 6.9248, | |
| "eval_samples_per_second": 40.001, | |
| "eval_steps_per_second": 5.054, | |
| "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": 6.8798, | |
| "eval_samples_per_second": 40.263, | |
| "eval_steps_per_second": 5.087, | |
| "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": 6.8633, | |
| "eval_samples_per_second": 40.36, | |
| "eval_steps_per_second": 5.1, | |
| "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": 6.8768, | |
| "eval_samples_per_second": 40.281, | |
| "eval_steps_per_second": 5.09, | |
| "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": 6.9281, | |
| "eval_samples_per_second": 39.982, | |
| "eval_steps_per_second": 5.052, | |
| "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": 6.832, | |
| "eval_samples_per_second": 40.545, | |
| "eval_steps_per_second": 5.123, | |
| "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": 6.8638, | |
| "eval_samples_per_second": 40.356, | |
| "eval_steps_per_second": 5.099, | |
| "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": 6.8545, | |
| "eval_samples_per_second": 40.411, | |
| "eval_steps_per_second": 5.106, | |
| "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": 6.7394, | |
| "eval_samples_per_second": 41.102, | |
| "eval_steps_per_second": 5.193, | |
| "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": 6.8897, | |
| "eval_samples_per_second": 40.205, | |
| "eval_steps_per_second": 5.08, | |
| "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": 6.8739, | |
| "eval_samples_per_second": 40.297, | |
| "eval_steps_per_second": 5.092, | |
| "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": 6.874, | |
| "eval_samples_per_second": 40.297, | |
| "eval_steps_per_second": 5.092, | |
| "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": 6.8727, | |
| "eval_samples_per_second": 40.304, | |
| "eval_steps_per_second": 5.093, | |
| "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": 6.8528, | |
| "eval_samples_per_second": 40.421, | |
| "eval_steps_per_second": 5.107, | |
| "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": 6.8525, | |
| "eval_samples_per_second": 40.423, | |
| "eval_steps_per_second": 5.108, | |
| "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": 6.9197, | |
| "eval_samples_per_second": 40.03, | |
| "eval_steps_per_second": 5.058, | |
| "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": 6.837, | |
| "eval_samples_per_second": 40.515, | |
| "eval_steps_per_second": 5.119, | |
| "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": 6.9126, | |
| "eval_samples_per_second": 40.072, | |
| "eval_steps_per_second": 5.063, | |
| "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": 6.8379, | |
| "eval_samples_per_second": 40.509, | |
| "eval_steps_per_second": 5.119, | |
| "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": 6.8814, | |
| "eval_samples_per_second": 40.253, | |
| "eval_steps_per_second": 5.086, | |
| "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": 6.8719, | |
| "eval_samples_per_second": 40.309, | |
| "eval_steps_per_second": 5.093, | |
| "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": 6.8995, | |
| "eval_samples_per_second": 40.148, | |
| "eval_steps_per_second": 5.073, | |
| "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": 6.8549, | |
| "eval_samples_per_second": 40.409, | |
| "eval_steps_per_second": 5.106, | |
| "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": 6.8822, | |
| "eval_samples_per_second": 40.249, | |
| "eval_steps_per_second": 5.086, | |
| "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": 6.8798, | |
| "eval_samples_per_second": 40.263, | |
| "eval_steps_per_second": 5.087, | |
| "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": 6.8242, | |
| "eval_samples_per_second": 40.591, | |
| "eval_steps_per_second": 5.129, | |
| "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": 6.9189, | |
| "eval_samples_per_second": 40.035, | |
| "eval_steps_per_second": 5.059, | |
| "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": 6.8467, | |
| "eval_samples_per_second": 40.457, | |
| "eval_steps_per_second": 5.112, | |
| "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": 6.9157, | |
| "eval_samples_per_second": 40.054, | |
| "eval_steps_per_second": 5.061, | |
| "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": 6.9233, | |
| "eval_samples_per_second": 40.01, | |
| "eval_steps_per_second": 5.055, | |
| "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": 6.8696, | |
| "eval_samples_per_second": 40.323, | |
| "eval_steps_per_second": 5.095, | |
| "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": 6.8336, | |
| "eval_samples_per_second": 40.535, | |
| "eval_steps_per_second": 5.122, | |
| "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": 6.8702, | |
| "eval_samples_per_second": 40.319, | |
| "eval_steps_per_second": 5.094, | |
| "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": 6.8807, | |
| "eval_samples_per_second": 40.258, | |
| "eval_steps_per_second": 5.087, | |
| "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": 6.8751, | |
| "eval_samples_per_second": 40.29, | |
| "eval_steps_per_second": 5.091, | |
| "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": 6.849, | |
| "eval_samples_per_second": 40.444, | |
| "eval_steps_per_second": 5.11, | |
| "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": 6.8882, | |
| "eval_samples_per_second": 40.214, | |
| "eval_steps_per_second": 5.081, | |
| "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": 6.8409, | |
| "eval_samples_per_second": 40.492, | |
| "eval_steps_per_second": 5.116, | |
| "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": 6.842, | |
| "eval_samples_per_second": 40.485, | |
| "eval_steps_per_second": 5.115, | |
| "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": 6.8695, | |
| "eval_samples_per_second": 40.323, | |
| "eval_steps_per_second": 5.095, | |
| "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": 6.908, | |
| "eval_samples_per_second": 40.098, | |
| "eval_steps_per_second": 5.067, | |
| "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": 6.9254, | |
| "eval_samples_per_second": 39.998, | |
| "eval_steps_per_second": 5.054, | |
| "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": 3.298, | |
| "eval_samples_per_second": 83.991, | |
| "eval_steps_per_second": 10.613, | |
| "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": 3.2851, | |
| "eval_samples_per_second": 84.319, | |
| "eval_steps_per_second": 10.654, | |
| "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": 3.2892, | |
| "eval_samples_per_second": 84.215, | |
| "eval_steps_per_second": 10.641, | |
| "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": 3.3027, | |
| "eval_samples_per_second": 83.87, | |
| "eval_steps_per_second": 10.597, | |
| "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": 3.2928, | |
| "eval_samples_per_second": 84.122, | |
| "eval_steps_per_second": 10.629, | |
| "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": 3.2869, | |
| "eval_samples_per_second": 84.274, | |
| "eval_steps_per_second": 10.648, | |
| "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": 3.2907, | |
| "eval_samples_per_second": 84.176, | |
| "eval_steps_per_second": 10.636, | |
| "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": 3.2959, | |
| "eval_samples_per_second": 84.044, | |
| "eval_steps_per_second": 10.619, | |
| "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": 3.3086, | |
| "eval_samples_per_second": 83.721, | |
| "eval_steps_per_second": 10.579, | |
| "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": 3.3021, | |
| "eval_samples_per_second": 83.885, | |
| "eval_steps_per_second": 10.599, | |
| "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": 3.3016, | |
| "eval_samples_per_second": 83.899, | |
| "eval_steps_per_second": 10.601, | |
| "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": 3.3127, | |
| "eval_samples_per_second": 83.618, | |
| "eval_steps_per_second": 10.566, | |
| "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": 3.2982, | |
| "eval_samples_per_second": 83.984, | |
| "eval_steps_per_second": 10.612, | |
| "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": 3.3072, | |
| "eval_samples_per_second": 83.758, | |
| "eval_steps_per_second": 10.583, | |
| "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": 3.2973, | |
| "eval_samples_per_second": 84.009, | |
| "eval_steps_per_second": 10.615, | |
| "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": 3.2855, | |
| "eval_samples_per_second": 84.311, | |
| "eval_steps_per_second": 10.653, | |
| "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": 3.3182, | |
| "eval_samples_per_second": 83.479, | |
| "eval_steps_per_second": 10.548, | |
| "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": 3.2798, | |
| "eval_samples_per_second": 84.456, | |
| "eval_steps_per_second": 10.671, | |
| "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": 5573.2397, | |
| "train_samples_per_second": 26.807, | |
| "train_steps_per_second": 3.359 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |