| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 130, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7797270955165692, |
| "grad_norm": 0.2537297010421753, |
| "learning_rate": 0.00014338837391175582, |
| "loss": 0.9497, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.5458089668615984, |
| "grad_norm": 0.08683182299137115, |
| "learning_rate": 2.8413315074028158e-05, |
| "loss": 0.7947, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 130, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1.7138672716690227e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
