| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 2950, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.85, |
| "learning_rate": 8.305084745762712e-05, |
| "loss": 0.0907, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.05301688611507416, |
| "eval_runtime": 22.0022, |
| "eval_samples_per_second": 6.727, |
| "eval_steps_per_second": 3.363, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 6.610169491525424e-05, |
| "loss": 0.044, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.05314206704497337, |
| "eval_runtime": 22.0246, |
| "eval_samples_per_second": 6.72, |
| "eval_steps_per_second": 3.36, |
| "step": 1180 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 4.915254237288136e-05, |
| "loss": 0.0324, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.0601324662566185, |
| "eval_runtime": 22.0071, |
| "eval_samples_per_second": 6.725, |
| "eval_steps_per_second": 3.363, |
| "step": 1770 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 3.2203389830508473e-05, |
| "loss": 0.0215, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.07468509674072266, |
| "eval_runtime": 22.0212, |
| "eval_samples_per_second": 6.721, |
| "eval_steps_per_second": 3.36, |
| "step": 2360 |
| }, |
| { |
| "epoch": 4.24, |
| "learning_rate": 1.5254237288135596e-05, |
| "loss": 0.0133, |
| "step": 2500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.08810325711965561, |
| "eval_runtime": 22.015, |
| "eval_samples_per_second": 6.723, |
| "eval_steps_per_second": 3.361, |
| "step": 2950 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2950, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 2.567886864384e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
