| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9952, |
| "eval_steps": 500, |
| "global_step": 468, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.28, |
| "grad_norm": 0.09104396402835846, |
| "learning_rate": 1e-05, |
| "loss": 0.3624, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.56, |
| "grad_norm": 0.1047985777258873, |
| "learning_rate": 1e-05, |
| "loss": 0.1875, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.9952, |
| "step": 468, |
| "total_flos": 64311364943872.0, |
| "train_loss": 0.2557532644679404, |
| "train_runtime": 6755.8147, |
| "train_samples_per_second": 8.881, |
| "train_steps_per_second": 0.069 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 468, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 64311364943872.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
