| { |
| "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": 1.1011, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 70.11446839228627, |
| "eval_f1": 72.9083060123436, |
| "eval_runtime": 9.547, |
| "eval_samples_per_second": 1015.715, |
| "eval_steps_per_second": 3.247, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5108, |
| "step": 244 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 71.35196452511086, |
| "eval_f1": 73.86206623465694, |
| "eval_runtime": 8.5377, |
| "eval_samples_per_second": 1135.78, |
| "eval_steps_per_second": 3.631, |
| "step": 244 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4496, |
| "step": 366 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 70.69196658760441, |
| "eval_f1": 74.27826709419496, |
| "eval_runtime": 8.5607, |
| "eval_samples_per_second": 1132.734, |
| "eval_steps_per_second": 3.621, |
| "step": 366 |
| } |
| ], |
| "max_steps": 1220, |
| "num_train_epochs": 10, |
| "total_flos": 115390042603520.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
