{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 345, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.0, "step": 345, "total_flos": 235624315556256.0, "train_loss": 0.4036261074784873, "train_runtime": 3078.6117, "train_samples_per_second": 3.574, "train_steps_per_second": 0.112 } ], "logging_steps": 500, "max_steps": 345, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 235624315556256.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }