| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3258390355164549, |
| "eval_steps": 1000, |
| "global_step": 5000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06516780710329098, |
| "grad_norm": 37.454742431640625, |
| "learning_rate": 9.99e-05, |
| "loss": 14.6821181640625, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.13033561420658196, |
| "grad_norm": 25.51059913635254, |
| "learning_rate": 9.989747492530146e-05, |
| "loss": 1.97178173828125, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.19550342130987292, |
| "grad_norm": 21.06842613220215, |
| "learning_rate": 9.958991052592558e-05, |
| "loss": 1.7084659423828126, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.2606712284131639, |
| "grad_norm": 24.679216384887695, |
| "learning_rate": 9.907857054719624e-05, |
| "loss": 1.605206298828125, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.3258390355164549, |
| "grad_norm": 11.777310371398926, |
| "learning_rate": 9.836555619476811e-05, |
| "loss": 1.543937255859375, |
| "step": 5000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 50000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
