{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 68223, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 2.555318593978882, "learning_rate": 1.3333333333333333e-05, "loss": 0.2948, "step": 22741 }, { "epoch": 1.0, "eval_accuracy": 0.9004946821667079, "eval_combined_score": 0.8834400741532002, "eval_f1": 0.8663854661396925, "eval_loss": 0.24696190655231476, "eval_runtime": 173.6065, "eval_samples_per_second": 232.883, "eval_steps_per_second": 29.112, "step": 22741 }, { "epoch": 2.0, "grad_norm": 6.593389987945557, "learning_rate": 6.666666666666667e-06, "loss": 0.1923, "step": 45482 }, { "epoch": 2.0, "eval_accuracy": 0.9049220875587435, "eval_combined_score": 0.8884498534776333, "eval_f1": 0.871977619396523, "eval_loss": 0.27233684062957764, "eval_runtime": 173.8289, "eval_samples_per_second": 232.585, "eval_steps_per_second": 29.075, "step": 45482 }, { "epoch": 3.0, "grad_norm": 0.5991644263267517, "learning_rate": 0.0, "loss": 0.1339, "step": 68223 }, { "epoch": 3.0, "eval_accuracy": 0.9109077417759089, "eval_combined_score": 0.8953925089190357, "eval_f1": 0.8798772760621624, "eval_loss": 0.35853680968284607, "eval_runtime": 174.2036, "eval_samples_per_second": 232.085, "eval_steps_per_second": 29.012, "step": 68223 }, { "epoch": 3.0, "step": 68223, "total_flos": 2.8719571514554368e+17, "train_loss": 0.0, "train_runtime": 0.002, "train_samples_per_second": 559413758.499, "train_steps_per_second": 34964320.845 } ], "logging_steps": 500, "max_steps": 68223, "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": 2.8719571514554368e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }