| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.978021978021978, |
| "eval_steps": 500, |
| "global_step": 1800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5494505494505495, |
| "grad_norm": 1.1440719366073608, |
| "learning_rate": 2e-05, |
| "loss": 1.759, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.098901098901099, |
| "grad_norm": 0.9083975553512573, |
| "learning_rate": 1.5515695067264575e-05, |
| "loss": 1.5431, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.6483516483516483, |
| "grad_norm": 0.9180422425270081, |
| "learning_rate": 1.1031390134529149e-05, |
| "loss": 1.3968, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2730, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 90, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.335990692610048e+17, |
| "train_batch_size": 80, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
