{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.013029315960912053, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004343105320304018, "grad_norm": 1.5055750608444214, "learning_rate": 2e-05, "loss": 2.9357, "step": 1 }, { "epoch": 0.004343105320304018, "eval_loss": 0.9203988909721375, "eval_runtime": 16.8799, "eval_samples_per_second": 5.746, "eval_steps_per_second": 2.903, "step": 1 }, { "epoch": 0.008686210640608035, "grad_norm": 0.6354552507400513, "learning_rate": 4e-05, "loss": 3.224, "step": 2 }, { "epoch": 0.013029315960912053, "grad_norm": 0.8828385472297668, "learning_rate": 6e-05, "loss": 3.2607, "step": 3 }, { "epoch": 0.013029315960912053, "eval_loss": 0.9197360873222351, "eval_runtime": 16.9119, "eval_samples_per_second": 5.736, "eval_steps_per_second": 2.897, "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": 1820567399301120.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }