| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9852216748768474, |
| "eval_steps": 500, |
| "global_step": 303, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9852216748768473, |
| "grad_norm": 8.44809627532959, |
| "learning_rate": 3.731617647058824e-05, |
| "loss": 7.4543, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.9704433497536946, |
| "grad_norm": 7.080057144165039, |
| "learning_rate": 1.8933823529411765e-05, |
| "loss": 5.9576, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.955665024630542, |
| "grad_norm": 10.340251922607422, |
| "learning_rate": 5.514705882352942e-07, |
| "loss": 5.8759, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 303, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 184144394832384.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
