{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 939, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.32, "grad_norm": 0.8309588432312012, "learning_rate": 4.472843450479233e-05, "loss": 2.1268, "step": 100 }, { "epoch": 0.64, "grad_norm": 0.8111929893493652, "learning_rate": 3.940362087326944e-05, "loss": 1.9513, "step": 200 }, { "epoch": 0.96, "grad_norm": 0.7366995215415955, "learning_rate": 3.407880724174654e-05, "loss": 1.9131, "step": 300 }, { "epoch": 1.2784, "grad_norm": 0.7454879283905029, "learning_rate": 2.8753993610223644e-05, "loss": 1.8164, "step": 400 }, { "epoch": 1.5984, "grad_norm": 0.7343336939811707, "learning_rate": 2.3429179978700748e-05, "loss": 1.816, "step": 500 }, { "epoch": 1.9184, "grad_norm": 0.7088562250137329, "learning_rate": 1.8104366347177852e-05, "loss": 1.7918, "step": 600 }, { "epoch": 2.2368, "grad_norm": 0.7369393706321716, "learning_rate": 1.2779552715654951e-05, "loss": 1.7424, "step": 700 }, { "epoch": 2.5568, "grad_norm": 0.7260516285896301, "learning_rate": 7.4547390841320565e-06, "loss": 1.744, "step": 800 }, { "epoch": 2.8768000000000002, "grad_norm": 0.6936702728271484, "learning_rate": 2.1299254526091587e-06, "loss": 1.7355, "step": 900 } ], "logging_steps": 100, "max_steps": 939, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7838760960000000.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }