{ "best_metric": 10.363144874572754, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 3.0569105691056913, "eval_steps": 25, "global_step": 47, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.06504065040650407, "grad_norm": 0.20289339125156403, "learning_rate": 5e-05, "loss": 10.3736, "step": 1 }, { "epoch": 0.06504065040650407, "eval_loss": 10.376363754272461, "eval_runtime": 0.1413, "eval_samples_per_second": 736.244, "eval_steps_per_second": 92.03, "step": 1 }, { "epoch": 0.13008130081300814, "grad_norm": 0.1323336660861969, "learning_rate": 0.0001, "loss": 10.3719, "step": 2 }, { "epoch": 0.1951219512195122, "grad_norm": 0.17840038239955902, "learning_rate": 9.987820251299122e-05, "loss": 10.3803, "step": 3 }, { "epoch": 0.2601626016260163, "grad_norm": 0.17275120317935944, "learning_rate": 9.951340343707852e-05, "loss": 10.3763, "step": 4 }, { "epoch": 0.3252032520325203, "grad_norm": 0.1751108169555664, "learning_rate": 9.890738003669029e-05, "loss": 10.3712, "step": 5 }, { "epoch": 0.3902439024390244, "grad_norm": 0.13938479125499725, "learning_rate": 9.806308479691595e-05, "loss": 10.373, "step": 6 }, { "epoch": 0.45528455284552843, "grad_norm": 0.17337481677532196, "learning_rate": 9.698463103929542e-05, "loss": 10.3757, "step": 7 }, { "epoch": 0.5203252032520326, "grad_norm": 0.22474798560142517, "learning_rate": 9.567727288213005e-05, "loss": 10.3718, "step": 8 }, { "epoch": 0.5853658536585366, "grad_norm": 0.13538026809692383, "learning_rate": 9.414737964294636e-05, "loss": 10.3692, "step": 9 }, { "epoch": 0.6504065040650406, "grad_norm": 0.17122657597064972, "learning_rate": 9.24024048078213e-05, "loss": 10.3734, "step": 10 }, { "epoch": 0.7154471544715447, "grad_norm": 0.17080749571323395, "learning_rate": 9.045084971874738e-05, "loss": 10.3726, "step": 11 }, { "epoch": 0.7804878048780488, "grad_norm": 0.22811958193778992, "learning_rate": 8.83022221559489e-05, "loss": 10.3704, "step": 12 }, { "epoch": 0.8455284552845529, "grad_norm": 0.14899323880672455, "learning_rate": 8.596699001693255e-05, "loss": 10.367, "step": 13 }, { "epoch": 0.9105691056910569, "grad_norm": 0.2465336173772812, "learning_rate": 8.345653031794292e-05, "loss": 10.3744, "step": 14 }, { "epoch": 0.975609756097561, "grad_norm": 0.17647525668144226, "learning_rate": 8.07830737662829e-05, "loss": 10.3707, "step": 15 }, { "epoch": 1.040650406504065, "grad_norm": 0.3739725649356842, "learning_rate": 7.795964517353735e-05, "loss": 18.1444, "step": 16 }, { "epoch": 1.1056910569105691, "grad_norm": 0.14059346914291382, "learning_rate": 7.500000000000001e-05, "loss": 10.2548, "step": 17 }, { "epoch": 1.170731707317073, "grad_norm": 0.25436219573020935, "learning_rate": 7.191855733945387e-05, "loss": 9.4334, "step": 18 }, { "epoch": 1.2357723577235773, "grad_norm": 0.09833599627017975, "learning_rate": 6.873032967079561e-05, "loss": 5.198, "step": 19 }, { "epoch": 1.3008130081300813, "grad_norm": 0.3984502851963043, "learning_rate": 6.545084971874738e-05, "loss": 16.4165, "step": 20 }, { "epoch": 1.3658536585365852, "grad_norm": 0.183476984500885, "learning_rate": 6.209609477998338e-05, "loss": 10.9875, "step": 21 }, { "epoch": 1.4308943089430894, "grad_norm": 0.21129857003688812, "learning_rate": 5.868240888334653e-05, "loss": 9.0419, "step": 22 }, { "epoch": 1.4959349593495934, "grad_norm": 0.11231347918510437, "learning_rate": 5.522642316338268e-05, "loss": 7.1111, "step": 23 }, { "epoch": 1.5609756097560976, "grad_norm": 0.3311237394809723, "learning_rate": 5.174497483512506e-05, "loss": 13.8825, "step": 24 }, { "epoch": 1.6260162601626016, "grad_norm": 0.19978109002113342, "learning_rate": 4.825502516487497e-05, "loss": 10.5704, "step": 25 }, { "epoch": 1.6260162601626016, "eval_loss": 10.363144874572754, "eval_runtime": 0.1376, "eval_samples_per_second": 755.6, "eval_steps_per_second": 94.45, "step": 25 }, { "epoch": 1.6910569105691056, "grad_norm": 0.20653556287288666, "learning_rate": 4.477357683661734e-05, "loss": 10.0741, "step": 26 }, { "epoch": 1.7560975609756098, "grad_norm": 0.2042083591222763, "learning_rate": 4.131759111665349e-05, "loss": 9.9069, "step": 27 }, { "epoch": 1.821138211382114, "grad_norm": 0.17668259143829346, "learning_rate": 3.790390522001662e-05, "loss": 11.2898, "step": 28 }, { "epoch": 1.886178861788618, "grad_norm": 0.30113402009010315, "learning_rate": 3.4549150281252636e-05, "loss": 9.5075, "step": 29 }, { "epoch": 1.951219512195122, "grad_norm": 0.2606578469276428, "learning_rate": 3.12696703292044e-05, "loss": 11.0706, "step": 30 }, { "epoch": 2.016260162601626, "grad_norm": 0.29925504326820374, "learning_rate": 2.8081442660546125e-05, "loss": 17.1891, "step": 31 }, { "epoch": 2.08130081300813, "grad_norm": 0.18933387100696564, "learning_rate": 2.500000000000001e-05, "loss": 10.4637, "step": 32 }, { "epoch": 2.1463414634146343, "grad_norm": 0.20285484194755554, "learning_rate": 2.2040354826462668e-05, "loss": 9.0417, "step": 33 }, { "epoch": 2.2113821138211383, "grad_norm": 0.18055562674999237, "learning_rate": 1.9216926233717085e-05, "loss": 8.3783, "step": 34 }, { "epoch": 2.2764227642276422, "grad_norm": 0.3930016756057739, "learning_rate": 1.6543469682057106e-05, "loss": 13.4143, "step": 35 }, { "epoch": 2.341463414634146, "grad_norm": 0.18804241716861725, "learning_rate": 1.4033009983067452e-05, "loss": 11.0764, "step": 36 }, { "epoch": 2.40650406504065, "grad_norm": 0.20714622735977173, "learning_rate": 1.1697777844051105e-05, "loss": 8.692, "step": 37 }, { "epoch": 2.4715447154471546, "grad_norm": 0.16578172147274017, "learning_rate": 9.549150281252633e-06, "loss": 7.9278, "step": 38 }, { "epoch": 2.5365853658536586, "grad_norm": 0.38254594802856445, "learning_rate": 7.597595192178702e-06, "loss": 13.5877, "step": 39 }, { "epoch": 2.6016260162601625, "grad_norm": 0.19641678035259247, "learning_rate": 5.852620357053651e-06, "loss": 11.453, "step": 40 }, { "epoch": 2.6666666666666665, "grad_norm": 0.2300872653722763, "learning_rate": 4.322727117869951e-06, "loss": 8.5011, "step": 41 }, { "epoch": 2.7317073170731705, "grad_norm": 0.1619451344013214, "learning_rate": 3.0153689607045845e-06, "loss": 7.7501, "step": 42 }, { "epoch": 2.796747967479675, "grad_norm": 0.3057861328125, "learning_rate": 1.9369152030840556e-06, "loss": 13.4289, "step": 43 }, { "epoch": 2.861788617886179, "grad_norm": 0.19348877668380737, "learning_rate": 1.0926199633097157e-06, "loss": 10.0297, "step": 44 }, { "epoch": 2.926829268292683, "grad_norm": 0.27544501423835754, "learning_rate": 4.865965629214819e-07, "loss": 10.6125, "step": 45 }, { "epoch": 2.991869918699187, "grad_norm": 0.38650020956993103, "learning_rate": 1.2179748700879012e-07, "loss": 15.4729, "step": 46 }, { "epoch": 3.0569105691056913, "grad_norm": 0.31395643949508667, "learning_rate": 0.0, "loss": 11.6441, "step": 47 } ], "logging_steps": 1, "max_steps": 47, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "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": true }, "attributes": {} } }, "total_flos": 47285435891712.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }