| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.5, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.9875268340110779, |
| "eval_runtime": 1093.1912, |
| "eval_samples_per_second": 3.444, |
| "eval_steps_per_second": 0.431, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 1.1666666666666668e-05, |
| "loss": 1.2354, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.861046552658081, |
| "eval_runtime": 1076.5303, |
| "eval_samples_per_second": 3.497, |
| "eval_steps_per_second": 0.438, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.9502, |
| "step": 1000 |
| } |
| ], |
| "max_steps": 1200, |
| "num_train_epochs": 3, |
| "total_flos": 1034294675238000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
