| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.12572685840012573, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 8.996486892091073e-06, |
| "loss": 0.6543, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 8.985953053665263e-06, |
| "loss": 0.469, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 8.968414932060827e-06, |
| "loss": 0.2958, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 8.94389991097275e-06, |
| "loss": 0.2424, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 8.912446267696357e-06, |
| "loss": 0.2481, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 8.874103113361848e-06, |
| "loss": 0.251, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 8.828930316253112e-06, |
| "loss": 0.1803, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 8.7769984083305e-06, |
| "loss": 0.2148, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 8.718388475103545e-06, |
| "loss": 0.1926, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 8.653192029025561e-06, |
| "loss": 0.2202, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.13, |
| "eval_accuracy": 0.0, |
| "eval_loss": 0.07498380541801453, |
| "eval_runtime": 28.9719, |
| "eval_samples_per_second": 97.612, |
| "eval_steps_per_second": 24.403, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 795, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "total_flos": 0.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
