| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1575, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3365079365079365e-05, | |
| "loss": 0.2578, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.8262704515233855, | |
| "eval_loss": 0.16420972347259521, | |
| "eval_runtime": 6.7346, | |
| "eval_samples_per_second": 933.984, | |
| "eval_steps_per_second": 39.052, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.673015873015873e-05, | |
| "loss": 0.1289, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.8419785636499112, | |
| "eval_loss": 0.1397038847208023, | |
| "eval_runtime": 6.9657, | |
| "eval_samples_per_second": 902.999, | |
| "eval_steps_per_second": 37.757, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.523809523809524e-08, | |
| "loss": 0.0819, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.863220155832338, | |
| "eval_loss": 0.13522900640964508, | |
| "eval_runtime": 8.7357, | |
| "eval_samples_per_second": 720.032, | |
| "eval_steps_per_second": 30.106, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1575, | |
| "total_flos": 863012377186080.0, | |
| "train_loss": 0.15611859495677646, | |
| "train_runtime": 183.2111, | |
| "train_samples_per_second": 205.992, | |
| "train_steps_per_second": 8.597 | |
| } | |
| ], | |
| "max_steps": 1575, | |
| "num_train_epochs": 3, | |
| "total_flos": 863012377186080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |