| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.9216244220733643, |
| "learning_rate": 1e-05, |
| "loss": 3.4328, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6963831782341003, |
| "eval_runtime": 0.307, |
| "eval_samples_per_second": 6.515, |
| "eval_steps_per_second": 3.257, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.9603631496429443, |
| "learning_rate": 2e-05, |
| "loss": 3.4328, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.205862045288086, |
| "learning_rate": 3e-05, |
| "loss": 3.385, |
| "step": 3 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 3, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7512739547185152.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
