| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 18525, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 4.44373083114624, | |
| "learning_rate": 4.354613174982253e-06, | |
| "loss": 0.6027, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 18525, | |
| "total_flos": 1.551734292653998e+18, | |
| "train_loss": 0.5984262187921727, | |
| "train_runtime": 34063.0741, | |
| "train_samples_per_second": 2.175, | |
| "train_steps_per_second": 0.544 | |
| } | |
| ], | |
| "logging_steps": 15000, | |
| "max_steps": 18525, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15000, | |
| "total_flos": 1.551734292653998e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |