{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 690, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 6.811136722564697, "learning_rate": 1.3333333333333333e-05, "loss": 0.5401, "step": 230 }, { "epoch": 1.0, "eval_accuracy": 0.8357843137254902, "eval_combined_score": 0.8583894925643437, "eval_f1": 0.8809946714031972, "eval_loss": 0.39578330516815186, "eval_runtime": 1.2728, "eval_samples_per_second": 320.554, "eval_steps_per_second": 40.069, "step": 230 }, { "epoch": 2.0, "grad_norm": 14.35599136352539, "learning_rate": 6.666666666666667e-06, "loss": 0.3312, "step": 460 }, { "epoch": 2.0, "eval_accuracy": 0.8431372549019608, "eval_combined_score": 0.8662053056516724, "eval_f1": 0.889273356401384, "eval_loss": 0.3634483516216278, "eval_runtime": 1.2981, "eval_samples_per_second": 314.298, "eval_steps_per_second": 39.287, "step": 460 }, { "epoch": 3.0, "grad_norm": 2.680626153945923, "learning_rate": 0.0, "loss": 0.1913, "step": 690 }, { "epoch": 3.0, "eval_accuracy": 0.8529411764705882, "eval_combined_score": 0.8743872549019608, "eval_f1": 0.8958333333333334, "eval_loss": 0.43215397000312805, "eval_runtime": 1.3921, "eval_samples_per_second": 293.088, "eval_steps_per_second": 36.636, "step": 690 }, { "epoch": 3.0, "step": 690, "total_flos": 2895274053181440.0, "train_loss": 0.0, "train_runtime": 0.0013, "train_samples_per_second": 8422284.893, "train_steps_per_second": 528114.92 } ], "logging_steps": 500, "max_steps": 690, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2895274053181440.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }