| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500.0, |
| "global_step": 804, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0012437810945273632, |
| "grad_norm": 484.0, |
| "learning_rate": 1.4634146341463415e-07, |
| "loss": 12.134991645812988, |
| "step": 1, |
| "token_acc": 0.296875 |
| }, |
| { |
| "epoch": 0.6218905472636815, |
| "grad_norm": 8.4375, |
| "learning_rate": 2.05886314785724e-06, |
| "loss": 0.5664094913459732, |
| "step": 500, |
| "token_acc": 0.9448897795591182 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 804, |
| "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": 6.620963837417882e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
