{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0256, "eval_steps": 1000, "global_step": 400, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00064, "grad_norm": 1.6144306659698486, "learning_rate": 1.1520000000000002e-08, "loss": 0.729, "step": 10 }, { "epoch": 0.00128, "grad_norm": 2.0952296257019043, "learning_rate": 2.4320000000000002e-08, "loss": 0.7295, "step": 20 }, { "epoch": 0.00192, "grad_norm": 1.3587689399719238, "learning_rate": 3.7120000000000004e-08, "loss": 0.73, "step": 30 }, { "epoch": 0.00256, "grad_norm": 1.2531732320785522, "learning_rate": 4.9920000000000006e-08, "loss": 0.7221, "step": 40 }, { "epoch": 0.0032, "grad_norm": 1.437932014465332, "learning_rate": 6.272000000000001e-08, "loss": 0.7209, "step": 50 }, { "epoch": 0.00384, "grad_norm": 1.418426752090454, "learning_rate": 7.552e-08, "loss": 0.729, "step": 60 }, { "epoch": 0.00448, "grad_norm": 1.9476298093795776, "learning_rate": 8.832e-08, "loss": 0.7242, "step": 70 }, { "epoch": 0.00512, "grad_norm": 1.7948051691055298, "learning_rate": 1.0112000000000001e-07, "loss": 0.7227, "step": 80 }, { "epoch": 0.00576, "grad_norm": 1.6534360647201538, "learning_rate": 1.1392e-07, "loss": 0.7234, "step": 90 }, { "epoch": 0.0064, "grad_norm": 1.0920158624649048, "learning_rate": 1.2672e-07, "loss": 0.7328, "step": 100 }, { "epoch": 0.00704, "grad_norm": 1.977837085723877, "learning_rate": 1.3952000000000002e-07, "loss": 0.7263, "step": 110 }, { "epoch": 0.00768, "grad_norm": 1.388983130455017, "learning_rate": 1.5232000000000003e-07, "loss": 0.7286, "step": 120 }, { "epoch": 0.00832, "grad_norm": 1.2956682443618774, "learning_rate": 1.6512e-07, "loss": 0.7251, "step": 130 }, { "epoch": 0.00896, "grad_norm": 1.8125052452087402, "learning_rate": 1.7792e-07, "loss": 0.7251, "step": 140 }, { "epoch": 0.0096, "grad_norm": 1.626846194267273, "learning_rate": 1.9072e-07, "loss": 0.727, "step": 150 }, { "epoch": 0.01024, "grad_norm": 2.3243086338043213, "learning_rate": 2.0352e-07, "loss": 0.726, "step": 160 }, { "epoch": 0.01088, "grad_norm": 1.4734737873077393, "learning_rate": 2.1632e-07, "loss": 0.7252, "step": 170 }, { "epoch": 0.01152, "grad_norm": 2.090498685836792, "learning_rate": 2.2912e-07, "loss": 0.7273, "step": 180 }, { "epoch": 0.01216, "grad_norm": 1.7563093900680542, "learning_rate": 2.4192000000000004e-07, "loss": 0.719, "step": 190 }, { "epoch": 0.0128, "grad_norm": 1.449843168258667, "learning_rate": 2.5472000000000005e-07, "loss": 0.7237, "step": 200 }, { "epoch": 0.01344, "grad_norm": 144219.625, "learning_rate": 5.350742447516642e-07, "loss": 0.7218, "step": 210 }, { "epoch": 0.01408, "grad_norm": 105046.0234375, "learning_rate": 5.606758832565284e-07, "loss": 0.718, "step": 220 }, { "epoch": 0.01472, "grad_norm": 126142.4296875, "learning_rate": 5.862775217613928e-07, "loss": 0.7107, "step": 230 }, { "epoch": 0.01536, "grad_norm": 92423.2265625, "learning_rate": 6.118791602662571e-07, "loss": 0.7271, "step": 240 }, { "epoch": 0.016, "grad_norm": 98091.828125, "learning_rate": 6.374807987711214e-07, "loss": 0.7123, "step": 250 }, { "epoch": 0.01664, "grad_norm": 131949.578125, "learning_rate": 6.630824372759858e-07, "loss": 0.7204, "step": 260 }, { "epoch": 0.01728, "grad_norm": 112228.5625, "learning_rate": 6.8868407578085e-07, "loss": 0.722, "step": 270 }, { "epoch": 0.01792, "grad_norm": 64587.734375, "learning_rate": 7.142857142857143e-07, "loss": 0.7263, "step": 280 }, { "epoch": 0.01856, "grad_norm": 99893.203125, "learning_rate": 7.398873527905787e-07, "loss": 0.7169, "step": 290 }, { "epoch": 0.0192, "grad_norm": 135749.875, "learning_rate": 7.65488991295443e-07, "loss": 0.7122, "step": 300 }, { "epoch": 0.01984, "grad_norm": 103292.5703125, "learning_rate": 7.910906298003073e-07, "loss": 0.7183, "step": 310 }, { "epoch": 0.02048, "grad_norm": 86927.28125, "learning_rate": 8.166922683051716e-07, "loss": 0.7192, "step": 320 }, { "epoch": 0.02112, "grad_norm": 153738.390625, "learning_rate": 8.422939068100359e-07, "loss": 0.711, "step": 330 }, { "epoch": 0.02176, "grad_norm": 69994.7734375, "learning_rate": 8.678955453149002e-07, "loss": 0.7176, "step": 340 }, { "epoch": 0.0224, "grad_norm": 141370.6875, "learning_rate": 8.934971838197646e-07, "loss": 0.7105, "step": 350 }, { "epoch": 0.02304, "grad_norm": 71139.453125, "learning_rate": 9.190988223246289e-07, "loss": 0.7126, "step": 360 }, { "epoch": 0.02368, "grad_norm": 82039.1953125, "learning_rate": 9.447004608294931e-07, "loss": 0.7078, "step": 370 }, { "epoch": 0.02432, "grad_norm": 71275.7890625, "learning_rate": 9.703020993343575e-07, "loss": 0.7145, "step": 380 }, { "epoch": 0.02496, "grad_norm": 145801.21875, "learning_rate": 9.959037378392218e-07, "loss": 0.7102, "step": 390 }, { "epoch": 0.0256, "grad_norm": 171507.0, "learning_rate": 1.021505376344086e-06, "loss": 0.7123, "step": 400 } ], "logging_steps": 10, "max_steps": 78125, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 200, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3367295286497280.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }