{ "best_metric": 0.0014751702547073364, "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": 0.8442800641059875, "learning_rate": 5e-05, "loss": 0.1508, "step": 1 }, { "epoch": 0.02391629297458894, "eval_loss": 0.31977328658103943, "eval_runtime": 2.8259, "eval_samples_per_second": 17.693, "eval_steps_per_second": 4.6, "step": 1 }, { "epoch": 0.04783258594917788, "grad_norm": 1.0565803050994873, "learning_rate": 0.0001, "loss": 0.1883, "step": 2 }, { "epoch": 0.07174887892376682, "grad_norm": 1.0159571170806885, "learning_rate": 9.990365154573717e-05, "loss": 0.1564, "step": 3 }, { "epoch": 0.09566517189835576, "grad_norm": 0.43976831436157227, "learning_rate": 9.961501876182148e-05, "loss": 0.0346, "step": 4 }, { "epoch": 0.11958146487294469, "grad_norm": 0.4568823575973511, "learning_rate": 9.913533761814537e-05, "loss": 0.0298, "step": 5 }, { "epoch": 0.14349775784753363, "grad_norm": 0.2651366591453552, "learning_rate": 9.846666218300807e-05, "loss": 0.0173, "step": 6 }, { "epoch": 0.16741405082212257, "grad_norm": 0.19742408394813538, "learning_rate": 9.761185582727977e-05, "loss": 0.0138, "step": 7 }, { "epoch": 0.19133034379671152, "grad_norm": 0.2404056191444397, "learning_rate": 9.657457896300791e-05, "loss": 0.016, "step": 8 }, { "epoch": 0.21524663677130046, "grad_norm": 0.22004278004169464, "learning_rate": 9.535927336897098e-05, "loss": 0.0108, "step": 9 }, { "epoch": 0.23916292974588937, "grad_norm": 0.21782603859901428, "learning_rate": 9.397114317029975e-05, "loss": 0.0155, "step": 10 }, { "epoch": 0.26307922272047835, "grad_norm": 0.15671923756599426, "learning_rate": 9.241613255361455e-05, "loss": 0.0288, "step": 11 }, { "epoch": 0.28699551569506726, "grad_norm": 0.12894146144390106, "learning_rate": 9.070090031310558e-05, "loss": 0.0077, "step": 12 }, { "epoch": 0.3109118086696562, "grad_norm": 0.1150781512260437, "learning_rate": 8.883279133655399e-05, "loss": 0.0086, "step": 13 }, { "epoch": 0.33482810164424515, "grad_norm": 0.0887535884976387, "learning_rate": 8.681980515339464e-05, "loss": 0.0056, "step": 14 }, { "epoch": 0.35874439461883406, "grad_norm": 0.08574005216360092, "learning_rate": 8.467056167950311e-05, "loss": 0.0049, "step": 15 }, { "epoch": 0.38266068759342303, "grad_norm": 0.08197639882564545, "learning_rate": 8.239426430539243e-05, "loss": 0.0049, "step": 16 }, { "epoch": 0.40657698056801195, "grad_norm": 0.07190021872520447, "learning_rate": 8.000066048588211e-05, "loss": 0.0023, "step": 17 }, { "epoch": 0.4304932735426009, "grad_norm": 0.06231943145394325, "learning_rate": 7.75e-05, "loss": 0.0027, "step": 18 }, { "epoch": 0.45440956651718983, "grad_norm": 0.08097774535417557, "learning_rate": 7.490299105985507e-05, "loss": 0.0019, "step": 19 }, { "epoch": 0.47832585949177875, "grad_norm": 0.1490212380886078, "learning_rate": 7.222075445642904e-05, "loss": 0.0044, "step": 20 }, { "epoch": 0.5022421524663677, "grad_norm": 0.0848916694521904, "learning_rate": 6.946477593864228e-05, "loss": 0.0119, "step": 21 }, { "epoch": 0.5261584454409567, "grad_norm": 0.032029468566179276, "learning_rate": 6.664685702961344e-05, "loss": 0.0017, "step": 22 }, { "epoch": 0.5500747384155455, "grad_norm": 0.05014993995428085, "learning_rate": 6.377906449072578e-05, "loss": 0.0022, "step": 23 }, { "epoch": 0.5739910313901345, "grad_norm": 0.05183505266904831, "learning_rate": 6.087367864990233e-05, "loss": 0.0026, "step": 24 }, { "epoch": 0.5979073243647235, "grad_norm": 0.0341709703207016, "learning_rate": 5.794314081535644e-05, "loss": 0.0013, "step": 25 }, { "epoch": 0.5979073243647235, "eval_loss": 0.0024434493388980627, "eval_runtime": 2.9148, "eval_samples_per_second": 17.154, "eval_steps_per_second": 4.46, "step": 25 }, { "epoch": 0.6218236173393124, "grad_norm": 0.06525561958551407, "learning_rate": 5.500000000000001e-05, "loss": 0.0014, "step": 26 }, { "epoch": 0.6457399103139013, "grad_norm": 0.056695058941841125, "learning_rate": 5.205685918464356e-05, "loss": 0.0013, "step": 27 }, { "epoch": 0.6696562032884903, "grad_norm": 0.08220528066158295, "learning_rate": 4.912632135009769e-05, "loss": 0.0016, "step": 28 }, { "epoch": 0.6935724962630793, "grad_norm": 0.02752971462905407, "learning_rate": 4.6220935509274235e-05, "loss": 0.0003, "step": 29 }, { "epoch": 0.7174887892376681, "grad_norm": 0.04567359760403633, "learning_rate": 4.3353142970386564e-05, "loss": 0.0006, "step": 30 }, { "epoch": 0.7414050822122571, "grad_norm": 0.06756115704774857, "learning_rate": 4.053522406135775e-05, "loss": 0.0099, "step": 31 }, { "epoch": 0.7653213751868461, "grad_norm": 0.040632255375385284, "learning_rate": 3.777924554357096e-05, "loss": 0.0023, "step": 32 }, { "epoch": 0.7892376681614349, "grad_norm": 0.03136821463704109, "learning_rate": 3.509700894014496e-05, "loss": 0.002, "step": 33 }, { "epoch": 0.8131539611360239, "grad_norm": 0.03969261422753334, "learning_rate": 3.250000000000001e-05, "loss": 0.0016, "step": 34 }, { "epoch": 0.8370702541106129, "grad_norm": 0.0348944216966629, "learning_rate": 2.9999339514117912e-05, "loss": 0.0012, "step": 35 }, { "epoch": 0.8609865470852018, "grad_norm": 0.05596629157662392, "learning_rate": 2.760573569460757e-05, "loss": 0.0017, "step": 36 }, { "epoch": 0.8849028400597907, "grad_norm": 0.05693504586815834, "learning_rate": 2.53294383204969e-05, "loss": 0.0019, "step": 37 }, { "epoch": 0.9088191330343797, "grad_norm": 0.028402505442500114, "learning_rate": 2.3180194846605367e-05, "loss": 0.0002, "step": 38 }, { "epoch": 0.9327354260089686, "grad_norm": 0.10989071428775787, "learning_rate": 2.1167208663446025e-05, "loss": 0.0024, "step": 39 }, { "epoch": 0.9566517189835575, "grad_norm": 0.02785768359899521, "learning_rate": 1.9299099686894423e-05, "loss": 0.0002, "step": 40 }, { "epoch": 0.9805680119581465, "grad_norm": 0.04585525766015053, "learning_rate": 1.758386744638546e-05, "loss": 0.0008, "step": 41 }, { "epoch": 1.014947683109118, "grad_norm": 0.05161361023783684, "learning_rate": 1.602885682970026e-05, "loss": 0.0135, "step": 42 }, { "epoch": 1.038863976083707, "grad_norm": 0.02895764261484146, "learning_rate": 1.464072663102903e-05, "loss": 0.0011, "step": 43 }, { "epoch": 1.062780269058296, "grad_norm": 0.027964701876044273, "learning_rate": 1.3425421036992098e-05, "loss": 0.0013, "step": 44 }, { "epoch": 1.086696562032885, "grad_norm": 0.03263154253363609, "learning_rate": 1.2388144172720251e-05, "loss": 0.0012, "step": 45 }, { "epoch": 1.1106128550074739, "grad_norm": 0.02236635610461235, "learning_rate": 1.1533337816991932e-05, "loss": 0.0007, "step": 46 }, { "epoch": 1.1345291479820627, "grad_norm": 0.021304232999682426, "learning_rate": 1.0864662381854632e-05, "loss": 0.0004, "step": 47 }, { "epoch": 1.1584454409566518, "grad_norm": 0.04713241755962372, "learning_rate": 1.0384981238178534e-05, "loss": 0.0011, "step": 48 }, { "epoch": 1.1823617339312407, "grad_norm": 0.031454771757125854, "learning_rate": 1.0096348454262845e-05, "loss": 0.0003, "step": 49 }, { "epoch": 1.2062780269058295, "grad_norm": 0.019992325454950333, "learning_rate": 1e-05, "loss": 0.0002, "step": 50 }, { "epoch": 1.2062780269058295, "eval_loss": 0.0014751702547073364, "eval_runtime": 2.7042, "eval_samples_per_second": 18.49, "eval_steps_per_second": 4.807, "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 }