{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5333333333333333, "eval_steps": 60, "global_step": 180, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.18, "learning_rate": 0.0002, "loss": 1.293, "step": 60 }, { "epoch": 0.18, "eval_runtime": 313.4076, "eval_samples_per_second": 1.914, "eval_steps_per_second": 0.239, "step": 60 }, { "epoch": 0.36, "learning_rate": 0.0002, "loss": 0.6736, "step": 120 }, { "epoch": 0.36, "eval_runtime": 313.3616, "eval_samples_per_second": 1.915, "eval_steps_per_second": 0.239, "step": 120 }, { "epoch": 0.53, "learning_rate": 0.0002, "loss": 0.6332, "step": 180 }, { "epoch": 0.53, "eval_runtime": 313.7062, "eval_samples_per_second": 1.913, "eval_steps_per_second": 0.239, "step": 180 } ], "logging_steps": 60, "max_steps": 1011, "num_train_epochs": 3, "save_steps": 60, "total_flos": 2.989819479195648e+16, "trial_name": null, "trial_params": null }