{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.28439388553146105, "eval_steps": 100, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.14, "learning_rate": 0.0001, "loss": 1.2192, "step": 100 }, { "epoch": 0.14, "eval_runtime": 1408.0486, "eval_samples_per_second": 1.776, "eval_steps_per_second": 0.222, "step": 100 }, { "epoch": 0.28, "learning_rate": 0.0001, "loss": 0.6611, "step": 200 }, { "epoch": 0.28, "eval_runtime": 1407.4105, "eval_samples_per_second": 1.776, "eval_steps_per_second": 0.222, "step": 200 } ], "logging_steps": 100, "max_steps": 2109, "num_train_epochs": 3, "save_steps": 100, "total_flos": 6.64404328710144e+16, "trial_name": null, "trial_params": null }