| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 211, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47393364928909953, |
| "grad_norm": 0.0005387316341511905, |
| "learning_rate": 3.4458598726114654e-05, |
| "loss": 0.2021, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9478672985781991, |
| "grad_norm": 0.0011278997408226132, |
| "learning_rate": 2.8089171974522295e-05, |
| "loss": 0.1048, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.3743789196014404, |
| "eval_runtime": 508.0838, |
| "eval_samples_per_second": 0.49, |
| "eval_steps_per_second": 0.49, |
| "step": 211 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 633, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.478100644706386e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
