| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 240, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.20833333333333334, |
| "grad_norm": 2.1875, |
| "learning_rate": 4.4212962962962966e-05, |
| "loss": 1.1163, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 2.0625, |
| "learning_rate": 3.263888888888889e-05, |
| "loss": 0.6972, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 2.140625, |
| "learning_rate": 2.1064814814814816e-05, |
| "loss": 0.6743, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 2.15625, |
| "learning_rate": 9.490740740740741e-06, |
| "loss": 0.6641, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 240, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
