| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.736842105263158, |
| "eval_steps": 500, |
| "global_step": 27, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5263157894736842, |
| "grad_norm": 21.34374237060547, |
| "learning_rate": 0.0001, |
| "loss": 20.0853, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.8480261564254761, |
| "learning_rate": 0.0001, |
| "loss": 0.4974, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.526315789473684, |
| "grad_norm": 1.0094432830810547, |
| "learning_rate": 0.0001, |
| "loss": 0.2344, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.9557652473449707, |
| "learning_rate": 0.0001, |
| "loss": 0.1812, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.526315789473684, |
| "grad_norm": 1.8617483377456665, |
| "learning_rate": 0.0001, |
| "loss": 0.0935, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.736842105263158, |
| "step": 27, |
| "total_flos": 0.0, |
| "train_loss": 3.9162730640835233, |
| "train_runtime": 200.1748, |
| "train_samples_per_second": 4.496, |
| "train_steps_per_second": 0.135 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 27, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
