| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.4864, |
| "eval_steps": 500, |
| "global_step": 59, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.256, |
| "grad_norm": 1.1803180980453234, |
| "learning_rate": 4.859708325770919e-06, |
| "loss": 0.9781, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 0.816742635326828, |
| "learning_rate": 4.058724504646834e-06, |
| "loss": 0.8946, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 0.7341204234955602, |
| "learning_rate": 2.7799111902582697e-06, |
| "loss": 0.9071, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.1193099493754795, |
| "learning_rate": 1.415290652206105e-06, |
| "loss": 0.8928, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.256, |
| "grad_norm": 0.6894704982672077, |
| "learning_rate": 3.831895019292897e-07, |
| "loss": 0.8297, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 59, |
| "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": 15696899342336.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
