| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9896907216494846, |
| "eval_steps": 500, |
| "global_step": 72, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13745704467353953, |
| "grad_norm": 2.4307763198718733, |
| "learning_rate": 4.996988640512931e-06, |
| "loss": 0.388, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.27491408934707906, |
| "grad_norm": 1.0906284673832232, |
| "learning_rate": 4.644321525000681e-06, |
| "loss": 0.2703, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.41237113402061853, |
| "grad_norm": 1.2566825629380436, |
| "learning_rate": 3.785256860483054e-06, |
| "loss": 0.2409, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5498281786941581, |
| "grad_norm": 1.028796931927551, |
| "learning_rate": 2.6226691858185454e-06, |
| "loss": 0.2431, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6872852233676976, |
| "grad_norm": 1.1617643684029584, |
| "learning_rate": 1.4311122664242955e-06, |
| "loss": 0.2394, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8247422680412371, |
| "grad_norm": 0.9873573640523043, |
| "learning_rate": 4.91981171298388e-07, |
| "loss": 0.234, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9621993127147767, |
| "grad_norm": 0.8050782530173689, |
| "learning_rate": 2.7058725088047466e-08, |
| "loss": 0.2185, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 72, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 15087599255552.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
