{ "best_metric": 10.365694999694824, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.29136400322841, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0258272800645682, "grad_norm": 0.14098317921161652, "learning_rate": 5e-05, "loss": 10.3967, "step": 1 }, { "epoch": 0.0258272800645682, "eval_loss": 10.38502311706543, "eval_runtime": 0.1487, "eval_samples_per_second": 336.184, "eval_steps_per_second": 87.408, "step": 1 }, { "epoch": 0.0516545601291364, "grad_norm": 0.18610599637031555, "learning_rate": 0.0001, "loss": 10.4055, "step": 2 }, { "epoch": 0.0774818401937046, "grad_norm": 0.13623014092445374, "learning_rate": 9.990365154573717e-05, "loss": 10.3946, "step": 3 }, { "epoch": 0.1033091202582728, "grad_norm": 0.12775151431560516, "learning_rate": 9.961501876182148e-05, "loss": 10.3897, "step": 4 }, { "epoch": 0.129136400322841, "grad_norm": 0.12215748429298401, "learning_rate": 9.913533761814537e-05, "loss": 10.3825, "step": 5 }, { "epoch": 0.1549636803874092, "grad_norm": 0.1178908571600914, "learning_rate": 9.846666218300807e-05, "loss": 10.3808, "step": 6 }, { "epoch": 0.1807909604519774, "grad_norm": 0.11641621589660645, "learning_rate": 9.761185582727977e-05, "loss": 10.3719, "step": 7 }, { "epoch": 0.2066182405165456, "grad_norm": 0.12131758779287338, "learning_rate": 9.657457896300791e-05, "loss": 10.3558, "step": 8 }, { "epoch": 0.2324455205811138, "grad_norm": 0.1481916755437851, "learning_rate": 9.535927336897098e-05, "loss": 10.3811, "step": 9 }, { "epoch": 0.258272800645682, "grad_norm": 0.10828401893377304, "learning_rate": 9.397114317029975e-05, "loss": 10.3774, "step": 10 }, { "epoch": 0.2841000807102502, "grad_norm": 0.2061031460762024, "learning_rate": 9.241613255361455e-05, "loss": 10.401, "step": 11 }, { "epoch": 0.3099273607748184, "grad_norm": 0.13002578914165497, "learning_rate": 9.070090031310558e-05, "loss": 10.3834, "step": 12 }, { "epoch": 0.3357546408393866, "grad_norm": 0.13271000981330872, "learning_rate": 8.883279133655399e-05, "loss": 10.3845, "step": 13 }, { "epoch": 0.3615819209039548, "grad_norm": 0.1344863474369049, "learning_rate": 8.681980515339464e-05, "loss": 10.382, "step": 14 }, { "epoch": 0.387409200968523, "grad_norm": 0.13007676601409912, "learning_rate": 8.467056167950311e-05, "loss": 10.3781, "step": 15 }, { "epoch": 0.4132364810330912, "grad_norm": 0.11889684945344925, "learning_rate": 8.239426430539243e-05, "loss": 10.3715, "step": 16 }, { "epoch": 0.4390637610976594, "grad_norm": 0.12730330228805542, "learning_rate": 8.000066048588211e-05, "loss": 10.3568, "step": 17 }, { "epoch": 0.4648910411622276, "grad_norm": 0.13269534707069397, "learning_rate": 7.75e-05, "loss": 10.3728, "step": 18 }, { "epoch": 0.4907183212267958, "grad_norm": 0.15930141508579254, "learning_rate": 7.490299105985507e-05, "loss": 10.3779, "step": 19 }, { "epoch": 0.516545601291364, "grad_norm": 0.1472412794828415, "learning_rate": 7.222075445642904e-05, "loss": 10.3798, "step": 20 }, { "epoch": 0.5423728813559322, "grad_norm": 0.20682215690612793, "learning_rate": 6.946477593864228e-05, "loss": 10.3987, "step": 21 }, { "epoch": 0.5682001614205004, "grad_norm": 0.14111225306987762, "learning_rate": 6.664685702961344e-05, "loss": 10.3825, "step": 22 }, { "epoch": 0.5940274414850686, "grad_norm": 0.14322906732559204, "learning_rate": 6.377906449072578e-05, "loss": 10.3769, "step": 23 }, { "epoch": 0.6198547215496368, "grad_norm": 0.14116321504116058, "learning_rate": 6.087367864990233e-05, "loss": 10.3719, "step": 24 }, { "epoch": 0.645682001614205, "grad_norm": 0.13819648325443268, "learning_rate": 5.794314081535644e-05, "loss": 10.3705, "step": 25 }, { "epoch": 0.645682001614205, "eval_loss": 10.371728897094727, "eval_runtime": 0.1433, "eval_samples_per_second": 348.971, "eval_steps_per_second": 90.732, "step": 25 }, { "epoch": 0.6715092816787732, "grad_norm": 0.13307611644268036, "learning_rate": 5.500000000000001e-05, "loss": 10.3589, "step": 26 }, { "epoch": 0.6973365617433414, "grad_norm": 0.12787942588329315, "learning_rate": 5.205685918464356e-05, "loss": 10.3505, "step": 27 }, { "epoch": 0.7231638418079096, "grad_norm": 0.17840470373630524, "learning_rate": 4.912632135009769e-05, "loss": 10.3771, "step": 28 }, { "epoch": 0.7489911218724778, "grad_norm": 0.12635862827301025, "learning_rate": 4.6220935509274235e-05, "loss": 10.3656, "step": 29 }, { "epoch": 0.774818401937046, "grad_norm": 0.23654264211654663, "learning_rate": 4.3353142970386564e-05, "loss": 10.397, "step": 30 }, { "epoch": 0.8006456820016142, "grad_norm": 0.17520985007286072, "learning_rate": 4.053522406135775e-05, "loss": 10.3823, "step": 31 }, { "epoch": 0.8264729620661824, "grad_norm": 0.16809497773647308, "learning_rate": 3.777924554357096e-05, "loss": 10.3763, "step": 32 }, { "epoch": 0.8523002421307506, "grad_norm": 0.16317372024059296, "learning_rate": 3.509700894014496e-05, "loss": 10.3719, "step": 33 }, { "epoch": 0.8781275221953188, "grad_norm": 0.1540750414133072, "learning_rate": 3.250000000000001e-05, "loss": 10.3655, "step": 34 }, { "epoch": 0.903954802259887, "grad_norm": 0.15551811456680298, "learning_rate": 2.9999339514117912e-05, "loss": 10.361, "step": 35 }, { "epoch": 0.9297820823244553, "grad_norm": 0.14692772924900055, "learning_rate": 2.760573569460757e-05, "loss": 10.3512, "step": 36 }, { "epoch": 0.9556093623890234, "grad_norm": 0.12654046714305878, "learning_rate": 2.53294383204969e-05, "loss": 10.3606, "step": 37 }, { "epoch": 0.9814366424535916, "grad_norm": 0.17960292100906372, "learning_rate": 2.3180194846605367e-05, "loss": 10.3658, "step": 38 }, { "epoch": 1.0072639225181599, "grad_norm": 0.19845052063465118, "learning_rate": 2.1167208663446025e-05, "loss": 14.0463, "step": 39 }, { "epoch": 1.033091202582728, "grad_norm": 0.2014998197555542, "learning_rate": 1.9299099686894423e-05, "loss": 8.8616, "step": 40 }, { "epoch": 1.0589184826472962, "grad_norm": 0.20529989898204803, "learning_rate": 1.758386744638546e-05, "loss": 11.0625, "step": 41 }, { "epoch": 1.0847457627118644, "grad_norm": 0.19758163392543793, "learning_rate": 1.602885682970026e-05, "loss": 10.6261, "step": 42 }, { "epoch": 1.1105730427764327, "grad_norm": 0.17450495064258575, "learning_rate": 1.464072663102903e-05, "loss": 10.2504, "step": 43 }, { "epoch": 1.136400322841001, "grad_norm": 0.16295291483402252, "learning_rate": 1.3425421036992098e-05, "loss": 10.2684, "step": 44 }, { "epoch": 1.162227602905569, "grad_norm": 0.16200117766857147, "learning_rate": 1.2388144172720251e-05, "loss": 10.3569, "step": 45 }, { "epoch": 1.1880548829701372, "grad_norm": 0.15267767012119293, "learning_rate": 1.1533337816991932e-05, "loss": 10.3028, "step": 46 }, { "epoch": 1.2138821630347054, "grad_norm": 0.13210907578468323, "learning_rate": 1.0864662381854632e-05, "loss": 10.4081, "step": 47 }, { "epoch": 1.2397094430992737, "grad_norm": 0.18460141122341156, "learning_rate": 1.0384981238178534e-05, "loss": 10.6767, "step": 48 }, { "epoch": 1.2655367231638417, "grad_norm": 0.1711810678243637, "learning_rate": 1.0096348454262845e-05, "loss": 11.0648, "step": 49 }, { "epoch": 1.29136400322841, "grad_norm": 0.23405061662197113, "learning_rate": 1e-05, "loss": 9.1647, "step": 50 }, { "epoch": 1.29136400322841, "eval_loss": 10.365694999694824, "eval_runtime": 0.1505, "eval_samples_per_second": 332.175, "eval_steps_per_second": 86.365, "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": 50807118495744.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }