| { |
| "best_metric": 0.7571426630020142, |
| "best_model_checkpoint": "/nlp/scr/q1zhang/models/0.000005_0.9/checkpoint-360", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 360, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.75e-06, |
| "loss": 1.2776, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.5267532827482938, |
| "eval_loss": 1.0772708654403687, |
| "eval_runtime": 4.4932, |
| "eval_samples_per_second": 53.414, |
| "eval_steps_per_second": 6.677, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.5e-06, |
| "loss": 0.9278, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.6492870923619042, |
| "eval_loss": 0.9544086456298828, |
| "eval_runtime": 5.7802, |
| "eval_samples_per_second": 41.521, |
| "eval_steps_per_second": 5.19, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.25e-06, |
| "loss": 0.6202, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.7183160283344106, |
| "eval_loss": 0.7571426630020142, |
| "eval_runtime": 4.1535, |
| "eval_samples_per_second": 57.783, |
| "eval_steps_per_second": 7.223, |
| "step": 360 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2400, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "total_flos": 696142871187264.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
