{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 313, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "step": 313, "total_flos": 4.216512416894157e+16, "train_loss": 0.4463165575703874, "train_runtime": 453.3701, "train_samples_per_second": 352.913, "train_steps_per_second": 0.69, "train_tokens_per_second": 22622.54 } ], "logging_steps": 500, "max_steps": 313, "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": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4.216512416894157e+16, "train_batch_size": 64, "trial_name": null, "trial_params": null }