| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 1317, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9776005180432095, |
| "eval_f1": 0.8999339498018495, |
| "eval_loss": 0.07999955117702484, |
| "eval_precision": 0.8833063209076175, |
| "eval_recall": 0.9171995960955908, |
| "eval_runtime": 10.0174, |
| "eval_samples_per_second": 324.435, |
| "eval_steps_per_second": 10.182, |
| "step": 439 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 1.240698557327259e-05, |
| "loss": 0.1922, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9839730382056867, |
| "eval_f1": 0.9235748070699528, |
| "eval_loss": 0.05978856980800629, |
| "eval_precision": 0.910951055819283, |
| "eval_recall": 0.9365533490407271, |
| "eval_runtime": 9.9678, |
| "eval_samples_per_second": 326.05, |
| "eval_steps_per_second": 10.233, |
| "step": 878 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 4.8139711465451785e-06, |
| "loss": 0.0487, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.984650026490846, |
| "eval_f1": 0.9284351936313127, |
| "eval_loss": 0.05753041058778763, |
| "eval_precision": 0.9151544874938695, |
| "eval_recall": 0.9421070346684618, |
| "eval_runtime": 10.1359, |
| "eval_samples_per_second": 320.642, |
| "eval_steps_per_second": 10.063, |
| "step": 1317 |
| } |
| ], |
| "max_steps": 1317, |
| "num_train_epochs": 3, |
| "total_flos": 1166128434618210.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
