| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.92, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.6966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.4002748727798462, | |
| "eval_runtime": 5.8667, | |
| "eval_samples_per_second": 17.045, | |
| "eval_steps_per_second": 2.216, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.3419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.3410404324531555, | |
| "eval_runtime": 7.4319, | |
| "eval_samples_per_second": 13.456, | |
| "eval_steps_per_second": 1.749, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "step": 18, | |
| "total_flos": 27578625622016.0, | |
| "train_loss": 0.8035296764638689, | |
| "train_runtime": 289.9665, | |
| "train_samples_per_second": 2.069, | |
| "train_steps_per_second": 0.062 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 27578625622016.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |