| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.939043965723035e-05, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.646347988574345e-05, |
| "grad_norm": 59.34721755981445, |
| "learning_rate": 1.647386284781828e-05, |
| "loss": 1.388497543334961, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.29269597714869e-05, |
| "grad_norm": 13.218413352966309, |
| "learning_rate": 6.298618446600856e-06, |
| "loss": 0.3699343204498291, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.939043965723035e-05, |
| "grad_norm": 3.9521124362945557, |
| "learning_rate": 5.862042845640403e-08, |
| "loss": 0.3119973182678223, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9891102718951424.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
