{ "best_metric": 10.9188814163208, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.4209591474245116, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.028419182948490232, "grad_norm": 11.931985855102539, "learning_rate": 5e-05, "loss": 177.2983, "step": 1 }, { "epoch": 0.028419182948490232, "eval_loss": 11.077445983886719, "eval_runtime": 0.6057, "eval_samples_per_second": 82.549, "eval_steps_per_second": 21.463, "step": 1 }, { "epoch": 0.056838365896980464, "grad_norm": 12.072855949401855, "learning_rate": 0.0001, "loss": 177.2958, "step": 2 }, { "epoch": 0.0852575488454707, "grad_norm": 12.328163146972656, "learning_rate": 9.990365154573717e-05, "loss": 177.1981, "step": 3 }, { "epoch": 0.11367673179396093, "grad_norm": 12.601313591003418, "learning_rate": 9.961501876182148e-05, "loss": 177.1795, "step": 4 }, { "epoch": 0.14209591474245115, "grad_norm": 12.67906379699707, "learning_rate": 9.913533761814537e-05, "loss": 177.1172, "step": 5 }, { "epoch": 0.1705150976909414, "grad_norm": 13.034372329711914, "learning_rate": 9.846666218300807e-05, "loss": 176.964, "step": 6 }, { "epoch": 0.1989342806394316, "grad_norm": 13.431110382080078, "learning_rate": 9.761185582727977e-05, "loss": 176.7757, "step": 7 }, { "epoch": 0.22735346358792186, "grad_norm": 13.137831687927246, "learning_rate": 9.657457896300791e-05, "loss": 176.6702, "step": 8 }, { "epoch": 0.2557726465364121, "grad_norm": 13.190668106079102, "learning_rate": 9.535927336897098e-05, "loss": 176.6166, "step": 9 }, { "epoch": 0.2841918294849023, "grad_norm": 11.381518363952637, "learning_rate": 9.397114317029975e-05, "loss": 176.687, "step": 10 }, { "epoch": 0.31261101243339257, "grad_norm": 11.36163330078125, "learning_rate": 9.241613255361455e-05, "loss": 176.5332, "step": 11 }, { "epoch": 0.3410301953818828, "grad_norm": 11.728120803833008, "learning_rate": 9.070090031310558e-05, "loss": 176.3918, "step": 12 }, { "epoch": 0.369449378330373, "grad_norm": 10.89070987701416, "learning_rate": 8.883279133655399e-05, "loss": 176.3627, "step": 13 }, { "epoch": 0.3978685612788632, "grad_norm": 11.923406600952148, "learning_rate": 8.681980515339464e-05, "loss": 176.1445, "step": 14 }, { "epoch": 0.42628774422735344, "grad_norm": 11.664999961853027, "learning_rate": 8.467056167950311e-05, "loss": 176.0671, "step": 15 }, { "epoch": 0.4547069271758437, "grad_norm": 11.967464447021484, "learning_rate": 8.239426430539243e-05, "loss": 175.9094, "step": 16 }, { "epoch": 0.48312611012433393, "grad_norm": 11.525784492492676, "learning_rate": 8.000066048588211e-05, "loss": 175.9118, "step": 17 }, { "epoch": 0.5115452930728241, "grad_norm": 10.081451416015625, "learning_rate": 7.75e-05, "loss": 176.0716, "step": 18 }, { "epoch": 0.5399644760213144, "grad_norm": 9.321731567382812, "learning_rate": 7.490299105985507e-05, "loss": 176.1517, "step": 19 }, { "epoch": 0.5683836589698046, "grad_norm": 9.908023834228516, "learning_rate": 7.222075445642904e-05, "loss": 175.9415, "step": 20 }, { "epoch": 0.5968028419182948, "grad_norm": 10.024669647216797, "learning_rate": 6.946477593864228e-05, "loss": 175.7933, "step": 21 }, { "epoch": 0.6252220248667851, "grad_norm": 10.28567886352539, "learning_rate": 6.664685702961344e-05, "loss": 175.6552, "step": 22 }, { "epoch": 0.6536412078152753, "grad_norm": 10.22734546661377, "learning_rate": 6.377906449072578e-05, "loss": 175.5912, "step": 23 }, { "epoch": 0.6820603907637656, "grad_norm": 10.401936531066895, "learning_rate": 6.087367864990233e-05, "loss": 175.4432, "step": 24 }, { "epoch": 0.7104795737122558, "grad_norm": 10.381370544433594, "learning_rate": 5.794314081535644e-05, "loss": 175.3753, "step": 25 }, { "epoch": 0.7104795737122558, "eval_loss": 10.95850944519043, "eval_runtime": 0.0749, "eval_samples_per_second": 667.989, "eval_steps_per_second": 173.677, "step": 25 }, { "epoch": 0.738898756660746, "grad_norm": 10.467306137084961, "learning_rate": 5.500000000000001e-05, "loss": 175.286, "step": 26 }, { "epoch": 0.7673179396092362, "grad_norm": 9.422204971313477, "learning_rate": 5.205685918464356e-05, "loss": 175.5984, "step": 27 }, { "epoch": 0.7957371225577264, "grad_norm": 9.05484390258789, "learning_rate": 4.912632135009769e-05, "loss": 175.5301, "step": 28 }, { "epoch": 0.8241563055062167, "grad_norm": 9.462740898132324, "learning_rate": 4.6220935509274235e-05, "loss": 175.319, "step": 29 }, { "epoch": 0.8525754884547069, "grad_norm": 9.432267189025879, "learning_rate": 4.3353142970386564e-05, "loss": 175.2917, "step": 30 }, { "epoch": 0.8809946714031972, "grad_norm": 9.702966690063477, "learning_rate": 4.053522406135775e-05, "loss": 175.1519, "step": 31 }, { "epoch": 0.9094138543516874, "grad_norm": 9.353253364562988, "learning_rate": 3.777924554357096e-05, "loss": 175.1685, "step": 32 }, { "epoch": 0.9378330373001776, "grad_norm": 9.841263771057129, "learning_rate": 3.509700894014496e-05, "loss": 174.9627, "step": 33 }, { "epoch": 0.9662522202486679, "grad_norm": 9.773153305053711, "learning_rate": 3.250000000000001e-05, "loss": 174.9566, "step": 34 }, { "epoch": 0.9946714031971581, "grad_norm": 10.038649559020996, "learning_rate": 2.9999339514117912e-05, "loss": 174.906, "step": 35 }, { "epoch": 1.0230905861456483, "grad_norm": 8.701342582702637, "learning_rate": 2.760573569460757e-05, "loss": 175.3199, "step": 36 }, { "epoch": 1.0515097690941386, "grad_norm": 8.372360229492188, "learning_rate": 2.53294383204969e-05, "loss": 175.2856, "step": 37 }, { "epoch": 1.0799289520426287, "grad_norm": 8.60970687866211, "learning_rate": 2.3180194846605367e-05, "loss": 175.1147, "step": 38 }, { "epoch": 1.108348134991119, "grad_norm": 8.56649112701416, "learning_rate": 2.1167208663446025e-05, "loss": 175.1148, "step": 39 }, { "epoch": 1.1367673179396092, "grad_norm": 9.035955429077148, "learning_rate": 1.9299099686894423e-05, "loss": 175.0417, "step": 40 }, { "epoch": 1.1651865008880995, "grad_norm": 8.987525939941406, "learning_rate": 1.758386744638546e-05, "loss": 174.9268, "step": 41 }, { "epoch": 1.1936056838365896, "grad_norm": 9.520977020263672, "learning_rate": 1.602885682970026e-05, "loss": 174.7916, "step": 42 }, { "epoch": 1.22202486678508, "grad_norm": 9.228601455688477, "learning_rate": 1.464072663102903e-05, "loss": 174.876, "step": 43 }, { "epoch": 1.25044404973357, "grad_norm": 9.710033416748047, "learning_rate": 1.3425421036992098e-05, "loss": 174.6947, "step": 44 }, { "epoch": 1.2788632326820604, "grad_norm": 8.159988403320312, "learning_rate": 1.2388144172720251e-05, "loss": 175.2761, "step": 45 }, { "epoch": 1.3072824156305507, "grad_norm": 8.44509506225586, "learning_rate": 1.1533337816991932e-05, "loss": 175.0658, "step": 46 }, { "epoch": 1.3357015985790408, "grad_norm": 8.655789375305176, "learning_rate": 1.0864662381854632e-05, "loss": 174.9807, "step": 47 }, { "epoch": 1.3641207815275311, "grad_norm": 8.57877254486084, "learning_rate": 1.0384981238178534e-05, "loss": 174.9439, "step": 48 }, { "epoch": 1.3925399644760212, "grad_norm": 9.241225242614746, "learning_rate": 1.0096348454262845e-05, "loss": 174.7962, "step": 49 }, { "epoch": 1.4209591474245116, "grad_norm": 8.72666072845459, "learning_rate": 1e-05, "loss": 174.8377, "step": 50 }, { "epoch": 1.4209591474245116, "eval_loss": 10.9188814163208, "eval_runtime": 0.0743, "eval_samples_per_second": 672.861, "eval_steps_per_second": 174.944, "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": 4202692608000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }