{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.2727272727272725, "eval_steps": 25, "global_step": 9, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.36363636363636365, "grad_norm": 0.0, "learning_rate": 9.698463103929542e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.36363636363636365, "eval_loss": NaN, "eval_runtime": 0.3006, "eval_samples_per_second": 63.197, "eval_steps_per_second": 9.979, "step": 1 }, { "epoch": 0.7272727272727273, "grad_norm": 0.0, "learning_rate": 8.83022221559489e-05, "loss": 0.0, "step": 2 }, { "epoch": 1.0909090909090908, "grad_norm": 0.0, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 3 }, { "epoch": 1.4545454545454546, "grad_norm": 0.0, "learning_rate": 5.868240888334653e-05, "loss": 0.0, "step": 4 }, { "epoch": 1.8181818181818183, "grad_norm": 0.0, "learning_rate": 4.131759111665349e-05, "loss": 0.0, "step": 5 }, { "epoch": 2.1818181818181817, "grad_norm": 0.0, "learning_rate": 2.500000000000001e-05, "loss": 0.0, "step": 6 }, { "epoch": 2.5454545454545454, "grad_norm": 0.0, "learning_rate": 1.1697777844051105e-05, "loss": 0.0, "step": 7 }, { "epoch": 2.909090909090909, "grad_norm": 0.0, "learning_rate": 3.0153689607045845e-06, "loss": 0.0, "step": 8 }, { "epoch": 3.2727272727272725, "grad_norm": 0.0, "learning_rate": 0.0, "loss": 0.0, "step": 9 } ], "logging_steps": 1, "max_steps": 9, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "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": 4457602675113984.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }