| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 339, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4424778761061947, |
| "grad_norm": 19.375, |
| "learning_rate": 1.7109144542772864e-05, |
| "loss": 1.4660652160644532, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8849557522123894, |
| "grad_norm": 10.8125, |
| "learning_rate": 1.4159292035398232e-05, |
| "loss": 0.729761962890625, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.3274336283185841, |
| "grad_norm": 21.25, |
| "learning_rate": 1.12094395280236e-05, |
| "loss": 0.7059085845947266, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7699115044247788, |
| "grad_norm": 12.0625, |
| "learning_rate": 8.259587020648968e-06, |
| "loss": 0.6798995971679688, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.2123893805309733, |
| "grad_norm": 24.0, |
| "learning_rate": 5.309734513274337e-06, |
| "loss": 0.6704206085205078, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.6548672566371683, |
| "grad_norm": 19.125, |
| "learning_rate": 2.359882005899705e-06, |
| "loss": 0.6608395385742187, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 339, |
| "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": 5788629113241600.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
