| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 366, |
| "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": 1.2544, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 69.76384448798598, |
| "eval_f1": 72.56296217275572, |
| "eval_runtime": 3.902, |
| "eval_samples_per_second": 2485.109, |
| "eval_steps_per_second": 7.945, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5427, |
| "step": 244 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 70.0938434567392, |
| "eval_f1": 73.08162643840086, |
| "eval_runtime": 3.4556, |
| "eval_samples_per_second": 2806.134, |
| "eval_steps_per_second": 8.971, |
| "step": 244 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4796, |
| "step": 366 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 70.35165515107765, |
| "eval_f1": 73.28225906709206, |
| "eval_runtime": 3.4869, |
| "eval_samples_per_second": 2781.009, |
| "eval_steps_per_second": 8.891, |
| "step": 366 |
| } |
| ], |
| "max_steps": 1220, |
| "num_train_epochs": 10, |
| "total_flos": 43819446829056.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
