| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3988863229751587, | |
| "eval_runtime": 1.1028, | |
| "eval_samples_per_second": 452.481, | |
| "eval_steps_per_second": 14.508, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.38775110244750977, | |
| "eval_runtime": 1.1024, | |
| "eval_samples_per_second": 452.63, | |
| "eval_steps_per_second": 14.513, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.727272727272727e-05, | |
| "loss": 0.4642, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.377765029668808, | |
| "eval_runtime": 1.1044, | |
| "eval_samples_per_second": 451.847, | |
| "eval_steps_per_second": 14.488, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.3701080083847046, | |
| "eval_runtime": 1.1029, | |
| "eval_samples_per_second": 452.461, | |
| "eval_steps_per_second": 14.508, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.4438, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.3616144061088562, | |
| "eval_runtime": 1.1041, | |
| "eval_samples_per_second": 451.939, | |
| "eval_steps_per_second": 14.491, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.35696589946746826, | |
| "eval_runtime": 1.3299, | |
| "eval_samples_per_second": 375.212, | |
| "eval_steps_per_second": 12.031, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.4262, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.3518909513950348, | |
| "eval_runtime": 1.5297, | |
| "eval_samples_per_second": 326.21, | |
| "eval_steps_per_second": 10.46, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.34925374388694763, | |
| "eval_runtime": 1.3276, | |
| "eval_samples_per_second": 375.855, | |
| "eval_steps_per_second": 12.051, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.34774351119995117, | |
| "eval_runtime": 1.3242, | |
| "eval_samples_per_second": 376.83, | |
| "eval_steps_per_second": 12.083, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.4197, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2200, | |
| "num_train_epochs": 10, | |
| "save_steps": 10, | |
| "total_flos": 2380323933388800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |