{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0004749277714014327, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001583092571338109, "grad_norm": 1.5863964557647705, "learning_rate": 2e-05, "loss": 1.3986, "step": 1 }, { "epoch": 0.0001583092571338109, "eval_loss": 1.323094129562378, "eval_runtime": 79.7487, "eval_samples_per_second": 33.355, "eval_steps_per_second": 16.677, "step": 1 }, { "epoch": 0.0003166185142676218, "grad_norm": 1.0940614938735962, "learning_rate": 4e-05, "loss": 1.1118, "step": 2 }, { "epoch": 0.0004749277714014327, "grad_norm": 1.3260576725006104, "learning_rate": 6e-05, "loss": 1.2353, "step": 3 }, { "epoch": 0.0004749277714014327, "eval_loss": 1.2929919958114624, "eval_runtime": 79.0791, "eval_samples_per_second": 33.637, "eval_steps_per_second": 16.819, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 524868391010304.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }