{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.2005513439007581, "eval_steps": 291, "global_step": 291, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.06891798759476224, "grad_norm": 5.37721586227417, "learning_rate": 9.88326321974139e-06, "loss": 0.6331, "step": 100 }, { "epoch": 0.13783597518952448, "grad_norm": 6.225131988525391, "learning_rate": 9.53850386931162e-06, "loss": 0.5923, "step": 200 }, { "epoch": 0.2005513439007581, "eval_accuracy": 0.6812963891076586, "eval_loss": 0.5887773036956787, "eval_runtime": 460.7553, "eval_samples_per_second": 181.88, "eval_steps_per_second": 5.684, "step": 291 } ], "logging_steps": 100, "max_steps": 1451, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 291, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }