| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 1100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8786, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 75.24124881740775, | |
| "eval_f1": 84.0188866665289, | |
| "eval_runtime": 4.7505, | |
| "eval_samples_per_second": 2237.455, | |
| "eval_steps_per_second": 7.157, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0114, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 79.11069063386944, | |
| "eval_f1": 86.79699558491163, | |
| "eval_runtime": 3.7638, | |
| "eval_samples_per_second": 2824.033, | |
| "eval_steps_per_second": 9.034, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8056, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 79.80132450331126, | |
| "eval_f1": 87.32321704064296, | |
| "eval_runtime": 3.7232, | |
| "eval_samples_per_second": 2854.773, | |
| "eval_steps_per_second": 9.132, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6596, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 80.10406811731315, | |
| "eval_f1": 87.6417993483592, | |
| "eval_runtime": 3.7333, | |
| "eval_samples_per_second": 2847.112, | |
| "eval_steps_per_second": 9.107, | |
| "step": 1100 | |
| } | |
| ], | |
| "max_steps": 5500, | |
| "num_train_epochs": 20, | |
| "total_flos": 132394520674304.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |