{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 102, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.29906542056074764, "learning_rate": 0.00019871817834144504, "loss": 0.9407, "mean_token_accuracy": 0.35524434726685283, "num_tokens": 241264.0, "step": 10 }, { "epoch": 0.5981308411214953, "learning_rate": 0.00018865993063730004, "loss": 0.9849, "mean_token_accuracy": 0.33938964605331423, "num_tokens": 473645.0, "step": 20 }, { "epoch": 0.897196261682243, "learning_rate": 0.00016956825506034867, "loss": 0.9593, "mean_token_accuracy": 0.34235219554975627, "num_tokens": 712343.0, "step": 30 }, { "epoch": 1.1794392523364485, "learning_rate": 0.00014338837391175582, "loss": 0.9381, "mean_token_accuracy": 0.33994899512521476, "num_tokens": 936009.0, "step": 40 }, { "epoch": 1.4785046728971962, "learning_rate": 0.00011278771616845061, "loss": 0.9865, "mean_token_accuracy": 0.33825155487284064, "num_tokens": 1170415.0, "step": 50 }, { "epoch": 1.777570093457944, "learning_rate": 8.08841371298628e-05, "loss": 0.9682, "mean_token_accuracy": 0.3465846974402666, "num_tokens": 1407415.0, "step": 60 }, { "epoch": 2.0598130841121494, "learning_rate": 5.092824479960625e-05, "loss": 0.947, "mean_token_accuracy": 0.34771046032574005, "num_tokens": 1636448.0, "step": 70 }, { "epoch": 2.358878504672897, "learning_rate": 2.5972200292468464e-05, "loss": 0.9417, "mean_token_accuracy": 0.34379080319777133, "num_tokens": 1875647.0, "step": 80 }, { "epoch": 2.6579439252336448, "learning_rate": 8.558737698418761e-06, "loss": 0.9681, "mean_token_accuracy": 0.3381199288181961, "num_tokens": 2112937.0, "step": 90 }, { "epoch": 2.9570093457943925, "learning_rate": 4.62088705080177e-07, "loss": 0.9956, "mean_token_accuracy": 0.34778707958757876, "num_tokens": 2342803.0, "step": 100 } ], "logging_steps": 10, "max_steps": 102, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.1773315846476595e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }