| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "global_step": 432, |
| "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": 1.2271, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 71.10877929345925, |
| "eval_f1": 74.5767906345225, |
| "eval_runtime": 3.8608, |
| "eval_samples_per_second": 2221.574, |
| "eval_steps_per_second": 6.993, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4925, |
| "step": 216 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 72.54284714935292, |
| "eval_f1": 75.50877362273009, |
| "eval_runtime": 3.0305, |
| "eval_samples_per_second": 2830.193, |
| "eval_steps_per_second": 8.909, |
| "step": 216 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.436, |
| "step": 324 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 72.54284714935292, |
| "eval_f1": 75.91301756720118, |
| "eval_runtime": 3.0491, |
| "eval_samples_per_second": 2812.975, |
| "eval_steps_per_second": 8.855, |
| "step": 324 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4098, |
| "step": 432 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_exact_match": 72.7293925615017, |
| "eval_f1": 75.95169013343053, |
| "eval_runtime": 3.0343, |
| "eval_samples_per_second": 2826.718, |
| "eval_steps_per_second": 8.898, |
| "step": 432 |
| } |
| ], |
| "max_steps": 1080, |
| "num_train_epochs": 10, |
| "total_flos": 51701511880704.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
