| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 29.864864864864863, |
| "eval_steps": 1000, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 24.864864864864863, |
| "grad_norm": 0.41308847069740295, |
| "learning_rate": 6e-06, |
| "loss": 3.8386, |
| "step": 100 |
| }, |
| { |
| "epoch": 29.864864864864863, |
| "step": 120, |
| "total_flos": 8754328240128000.0, |
| "train_loss": 3.8146740595499673, |
| "train_runtime": 2143.757, |
| "train_samples_per_second": 4.072, |
| "train_steps_per_second": 0.056 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 120, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 30, |
| "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": 8754328240128000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
