{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 25.0, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.533333333333333, "grad_norm": 0.3359375, "learning_rate": 1.9811781768982392e-05, "loss": 0.7714, "step": 10 }, { "epoch": 5.0, "grad_norm": 0.197265625, "learning_rate": 1.8687117365181514e-05, "loss": 0.7636, "step": 20 }, { "epoch": 7.533333333333333, "grad_norm": 0.1806640625, "learning_rate": 1.665915225011681e-05, "loss": 0.7631, "step": 30 }, { "epoch": 10.0, "grad_norm": 0.18359375, "learning_rate": 1.3938757562492873e-05, "loss": 0.7629, "step": 40 }, { "epoch": 12.533333333333333, "grad_norm": 0.2373046875, "learning_rate": 1.0808804403614044e-05, "loss": 0.7609, "step": 50 }, { "epoch": 15.0, "grad_norm": 0.166015625, "learning_rate": 7.594750436337467e-06, "loss": 0.7628, "step": 60 }, { "epoch": 17.533333333333335, "grad_norm": 0.22265625, "learning_rate": 4.630798263510162e-06, "loss": 0.7615, "step": 70 }, { "epoch": 20.0, "grad_norm": 0.2294921875, "learning_rate": 2.2251444932035094e-06, "loss": 0.7618, "step": 80 }, { "epoch": 22.533333333333335, "grad_norm": 0.1982421875, "learning_rate": 6.279329499365649e-07, "loss": 0.7625, "step": 90 }, { "epoch": 25.0, "grad_norm": 0.2314453125, "learning_rate": 5.2443095448506674e-09, "loss": 0.761, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 25, "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": 1.2178044223488e+16, "train_batch_size": 3, "trial_name": null, "trial_params": null }