{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "num_input_tokens_seen": 65536, "step": 1, "total_flos": 3174119881310208.0, "train_loss": 0.4201101064682007, "train_runtime": 27.3689, "train_samples_per_second": 0.292, "train_steps_per_second": 0.037 } ], "logging_steps": 5, "max_steps": 1, "num_input_tokens_seen": 65536, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3174119881310208.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }