| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500.0, |
| "global_step": 1397, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0007160759040458289, |
| "grad_norm": 528.0, |
| "learning_rate": 8.571428571428572e-08, |
| "loss": 12.75621223449707, |
| "step": 1, |
| "token_acc": 0.2962962962962963 |
| }, |
| { |
| "epoch": 0.35803795202291444, |
| "grad_norm": 5.15625, |
| "learning_rate": 4.575209588141909e-06, |
| "loss": 0.7769320379039328, |
| "step": 500, |
| "token_acc": 0.9363021928507059 |
| }, |
| { |
| "epoch": 0.7160759040458289, |
| "grad_norm": 0.2373046875, |
| "learning_rate": 1.230329742720808e-06, |
| "loss": 0.024479978561401366, |
| "step": 1000, |
| "token_acc": 0.9934866588806037 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1397, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.798510572387369e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
