| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 324, |
| "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": 1.1736, |
| "step": 108 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 72.18141541331468, |
| "eval_f1": 75.71603809790038, |
| "eval_runtime": 3.5116, |
| "eval_samples_per_second": 2442.455, |
| "eval_steps_per_second": 7.689, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4685, |
| "step": 216 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 71.81998367727644, |
| "eval_f1": 75.98313809352322, |
| "eval_runtime": 3.055, |
| "eval_samples_per_second": 2807.539, |
| "eval_steps_per_second": 8.838, |
| "step": 216 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4254, |
| "step": 324 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 72.50786988457503, |
| "eval_f1": 76.0290331485552, |
| "eval_runtime": 3.0504, |
| "eval_samples_per_second": 2811.797, |
| "eval_steps_per_second": 8.851, |
| "step": 324 |
| } |
| ], |
| "max_steps": 1080, |
| "num_train_epochs": 10, |
| "total_flos": 38745933873152.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
