{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006650732619765146, "eval_steps": 1.0, "global_step": 1, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 1.25e-06, "loss": 1.6498, "step": 1 }, { "epoch": 0.01, "eval_loss": 1.6147592067718506, "eval_runtime": 46.336, "eval_samples_per_second": 16.79, "eval_steps_per_second": 1.057, "step": 1 } ], "logging_steps": 1.0, "max_steps": 150, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1.0, "total_flos": 1280550895616.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }