| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 822, |
| "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": 1.5075, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 73.09082429753994, |
| "eval_f1": 76.17143894328423, |
| "eval_runtime": 3.4493, |
| "eval_samples_per_second": 2486.605, |
| "eval_steps_per_second": 7.828, |
| "step": 274 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.8003, |
| "step": 548 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 71.88993820683223, |
| "eval_f1": 75.83965822675361, |
| "eval_runtime": 3.0978, |
| "eval_samples_per_second": 2768.718, |
| "eval_steps_per_second": 8.716, |
| "step": 548 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.6457, |
| "step": 822 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 72.63611985542731, |
| "eval_f1": 76.42306118368614, |
| "eval_runtime": 3.0559, |
| "eval_samples_per_second": 2806.714, |
| "eval_steps_per_second": 8.835, |
| "step": 822 |
| } |
| ], |
| "max_steps": 2740, |
| "num_train_epochs": 10, |
| "total_flos": 99175094026240.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
