{ "best_metric": 0.5116, "best_model_checkpoint": "outputs/checkpoint-29586", "epoch": 1.0, "global_step": 29586, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 0.00027307465111127524, "loss": 3.6072, "step": 29586 }, { "epoch": 1.0, "eval_gen_len": 15.1014, "eval_loss": 2.7608768939971924, "eval_runtime": 362.214, "eval_sacrebleu": 0.5116, "eval_samples_per_second": 6.286, "eval_steps_per_second": 3.145, "step": 29586 } ], "max_steps": 59172, "num_train_epochs": 2, "total_flos": 4.0141178675030016e+17, "trial_name": null, "trial_params": null }