{ "best_metric": 0.0012785379076376557, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.2062780269058295, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02391629297458894, "grad_norm": 0.8342862725257874, "learning_rate": 5e-05, "loss": 0.151, "step": 1 }, { "epoch": 0.02391629297458894, "eval_loss": 0.3206508159637451, "eval_runtime": 5.0018, "eval_samples_per_second": 9.996, "eval_steps_per_second": 2.599, "step": 1 }, { "epoch": 0.04783258594917788, "grad_norm": 1.0358092784881592, "learning_rate": 0.0001, "loss": 0.1876, "step": 2 }, { "epoch": 0.07174887892376682, "grad_norm": 0.9988421201705933, "learning_rate": 9.990365154573717e-05, "loss": 0.1574, "step": 3 }, { "epoch": 0.09566517189835576, "grad_norm": 0.40356796979904175, "learning_rate": 9.961501876182148e-05, "loss": 0.0344, "step": 4 }, { "epoch": 0.11958146487294469, "grad_norm": 0.4616738557815552, "learning_rate": 9.913533761814537e-05, "loss": 0.0295, "step": 5 }, { "epoch": 0.14349775784753363, "grad_norm": 0.2594583034515381, "learning_rate": 9.846666218300807e-05, "loss": 0.017, "step": 6 }, { "epoch": 0.16741405082212257, "grad_norm": 0.20972101390361786, "learning_rate": 9.761185582727977e-05, "loss": 0.0138, "step": 7 }, { "epoch": 0.19133034379671152, "grad_norm": 0.23585247993469238, "learning_rate": 9.657457896300791e-05, "loss": 0.0162, "step": 8 }, { "epoch": 0.21524663677130046, "grad_norm": 0.2117353081703186, "learning_rate": 9.535927336897098e-05, "loss": 0.0104, "step": 9 }, { "epoch": 0.23916292974588937, "grad_norm": 0.2045036405324936, "learning_rate": 9.397114317029975e-05, "loss": 0.0143, "step": 10 }, { "epoch": 0.26307922272047835, "grad_norm": 0.14103253185749054, "learning_rate": 9.241613255361455e-05, "loss": 0.0282, "step": 11 }, { "epoch": 0.28699551569506726, "grad_norm": 0.11386289447546005, "learning_rate": 9.070090031310558e-05, "loss": 0.0074, "step": 12 }, { "epoch": 0.3109118086696562, "grad_norm": 0.11132951080799103, "learning_rate": 8.883279133655399e-05, "loss": 0.0082, "step": 13 }, { "epoch": 0.33482810164424515, "grad_norm": 0.0779055580496788, "learning_rate": 8.681980515339464e-05, "loss": 0.0056, "step": 14 }, { "epoch": 0.35874439461883406, "grad_norm": 0.08194252848625183, "learning_rate": 8.467056167950311e-05, "loss": 0.0044, "step": 15 }, { "epoch": 0.38266068759342303, "grad_norm": 0.09063728153705597, "learning_rate": 8.239426430539243e-05, "loss": 0.005, "step": 16 }, { "epoch": 0.40657698056801195, "grad_norm": 0.07385275512933731, "learning_rate": 8.000066048588211e-05, "loss": 0.0028, "step": 17 }, { "epoch": 0.4304932735426009, "grad_norm": 0.05866006389260292, "learning_rate": 7.75e-05, "loss": 0.0022, "step": 18 }, { "epoch": 0.45440956651718983, "grad_norm": 0.0739208534359932, "learning_rate": 7.490299105985507e-05, "loss": 0.0016, "step": 19 }, { "epoch": 0.47832585949177875, "grad_norm": 0.09625879675149918, "learning_rate": 7.222075445642904e-05, "loss": 0.0036, "step": 20 }, { "epoch": 0.5022421524663677, "grad_norm": 0.08272045105695724, "learning_rate": 6.946477593864228e-05, "loss": 0.0114, "step": 21 }, { "epoch": 0.5261584454409567, "grad_norm": 0.029296347871422768, "learning_rate": 6.664685702961344e-05, "loss": 0.0017, "step": 22 }, { "epoch": 0.5500747384155455, "grad_norm": 0.04417581856250763, "learning_rate": 6.377906449072578e-05, "loss": 0.0021, "step": 23 }, { "epoch": 0.5739910313901345, "grad_norm": 0.05239644646644592, "learning_rate": 6.087367864990233e-05, "loss": 0.0026, "step": 24 }, { "epoch": 0.5979073243647235, "grad_norm": 0.03702784329652786, "learning_rate": 5.794314081535644e-05, "loss": 0.0013, "step": 25 }, { "epoch": 0.5979073243647235, "eval_loss": 0.0019476765301078558, "eval_runtime": 5.0938, "eval_samples_per_second": 9.816, "eval_steps_per_second": 2.552, "step": 25 }, { "epoch": 0.6218236173393124, "grad_norm": 0.04498022794723511, "learning_rate": 5.500000000000001e-05, "loss": 0.0014, "step": 26 }, { "epoch": 0.6457399103139013, "grad_norm": 0.06719963252544403, "learning_rate": 5.205685918464356e-05, "loss": 0.0016, "step": 27 }, { "epoch": 0.6696562032884903, "grad_norm": 0.07147950679063797, "learning_rate": 4.912632135009769e-05, "loss": 0.0015, "step": 28 }, { "epoch": 0.6935724962630793, "grad_norm": 0.11482597142457962, "learning_rate": 4.6220935509274235e-05, "loss": 0.0013, "step": 29 }, { "epoch": 0.7174887892376681, "grad_norm": 0.05224405601620674, "learning_rate": 4.3353142970386564e-05, "loss": 0.0007, "step": 30 }, { "epoch": 0.7414050822122571, "grad_norm": 0.0664152279496193, "learning_rate": 4.053522406135775e-05, "loss": 0.01, "step": 31 }, { "epoch": 0.7653213751868461, "grad_norm": 0.038789551705121994, "learning_rate": 3.777924554357096e-05, "loss": 0.0021, "step": 32 }, { "epoch": 0.7892376681614349, "grad_norm": 0.03222445398569107, "learning_rate": 3.509700894014496e-05, "loss": 0.0019, "step": 33 }, { "epoch": 0.8131539611360239, "grad_norm": 0.04085226729512215, "learning_rate": 3.250000000000001e-05, "loss": 0.0016, "step": 34 }, { "epoch": 0.8370702541106129, "grad_norm": 0.041735582053661346, "learning_rate": 2.9999339514117912e-05, "loss": 0.0013, "step": 35 }, { "epoch": 0.8609865470852018, "grad_norm": 0.060009196400642395, "learning_rate": 2.760573569460757e-05, "loss": 0.0018, "step": 36 }, { "epoch": 0.8849028400597907, "grad_norm": 0.05532706901431084, "learning_rate": 2.53294383204969e-05, "loss": 0.0022, "step": 37 }, { "epoch": 0.9088191330343797, "grad_norm": 0.009391087107360363, "learning_rate": 2.3180194846605367e-05, "loss": 0.0001, "step": 38 }, { "epoch": 0.9327354260089686, "grad_norm": 0.10321075469255447, "learning_rate": 2.1167208663446025e-05, "loss": 0.0026, "step": 39 }, { "epoch": 0.9566517189835575, "grad_norm": 0.03513889014720917, "learning_rate": 1.9299099686894423e-05, "loss": 0.0003, "step": 40 }, { "epoch": 0.9805680119581465, "grad_norm": 0.047013089060783386, "learning_rate": 1.758386744638546e-05, "loss": 0.0008, "step": 41 }, { "epoch": 1.014947683109118, "grad_norm": 0.051135145127773285, "learning_rate": 1.602885682970026e-05, "loss": 0.0137, "step": 42 }, { "epoch": 1.038863976083707, "grad_norm": 0.025920534506440163, "learning_rate": 1.464072663102903e-05, "loss": 0.001, "step": 43 }, { "epoch": 1.062780269058296, "grad_norm": 0.02824629843235016, "learning_rate": 1.3425421036992098e-05, "loss": 0.0013, "step": 44 }, { "epoch": 1.086696562032885, "grad_norm": 0.0347956158220768, "learning_rate": 1.2388144172720251e-05, "loss": 0.0011, "step": 45 }, { "epoch": 1.1106128550074739, "grad_norm": 0.021422594785690308, "learning_rate": 1.1533337816991932e-05, "loss": 0.0007, "step": 46 }, { "epoch": 1.1345291479820627, "grad_norm": 0.020450716838240623, "learning_rate": 1.0864662381854632e-05, "loss": 0.0004, "step": 47 }, { "epoch": 1.1584454409566518, "grad_norm": 0.04902283474802971, "learning_rate": 1.0384981238178534e-05, "loss": 0.0012, "step": 48 }, { "epoch": 1.1823617339312407, "grad_norm": 0.03443044051527977, "learning_rate": 1.0096348454262845e-05, "loss": 0.0003, "step": 49 }, { "epoch": 1.2062780269058295, "grad_norm": 0.024215981364250183, "learning_rate": 1e-05, "loss": 0.0002, "step": 50 }, { "epoch": 1.2062780269058295, "eval_loss": 0.0012785379076376557, "eval_runtime": 4.7582, "eval_samples_per_second": 10.508, "eval_steps_per_second": 2.732, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 6.29218041065898e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }