| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 2600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1923631816870251, |
| "grad_norm": 70.2215347290039, |
| "learning_rate": 8.080769230769231e-06, |
| "loss": -100.6029, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3847263633740502, |
| "grad_norm": 1890.31591796875, |
| "learning_rate": 6.157692307692308e-06, |
| "loss": -151.516, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5770895450610753, |
| "grad_norm": 258.2842102050781, |
| "learning_rate": 4.234615384615385e-06, |
| "loss": -154.422, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.7694527267481004, |
| "grad_norm": 101.9043197631836, |
| "learning_rate": 2.3115384615384617e-06, |
| "loss": -157.1482, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.9618159084351255, |
| "grad_norm": 66.6363754272461, |
| "learning_rate": 3.8846153846153845e-07, |
| "loss": -158.2865, |
| "step": 2500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2600, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 0.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
