{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 148, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.6756756756756757, "grad_norm": 0.17686977982521057, "learning_rate": 6.666666666666667e-06, "loss": 2.3132, "step": 100 }, { "epoch": 1.0, "step": 148, "total_flos": 2689637233459200.0, "train_loss": 2.312007646302919, "train_runtime": 46.3579, "train_samples_per_second": 6.385, "train_steps_per_second": 3.193 } ], "logging_steps": 100, "max_steps": 148, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2689637233459200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }