| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 0, |
| "loss": 0.1021, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0, |
| "loss": 0.1014, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0, |
| "loss": 0.1023, |
| "step": 3 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 3, |
| "total_flos": 102082805760.0, |
| "train_loss": 0.10191151996453603, |
| "train_runtime": 74.8855, |
| "train_samples_per_second": 0.401, |
| "train_steps_per_second": 0.04 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 3, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "total_flos": 102082805760.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
