| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.00018019370823635407, |
| "eval_steps": 3, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 6.006456941211803e-05, |
| "grad_norm": 0.18168316781520844, |
| "learning_rate": 2e-05, |
| "loss": 1.668, |
| "step": 1 |
| }, |
| { |
| "epoch": 6.006456941211803e-05, |
| "eval_loss": 1.6562931537628174, |
| "eval_runtime": 601.6426, |
| "eval_samples_per_second": 11.653, |
| "eval_steps_per_second": 5.827, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00012012913882423606, |
| "grad_norm": 0.15870024263858795, |
| "learning_rate": 4e-05, |
| "loss": 1.5504, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00018019370823635407, |
| "grad_norm": 0.19789431989192963, |
| "learning_rate": 6e-05, |
| "loss": 1.4139, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.00018019370823635407, |
| "eval_loss": 1.6558383703231812, |
| "eval_runtime": 600.9327, |
| "eval_samples_per_second": 11.667, |
| "eval_steps_per_second": 5.834, |
| "step": 3 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 369021899243520.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
