{ "best_metric": 0.5986165404319763, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.034809851187886175, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006961970237577234, "grad_norm": 4.59558629989624, "learning_rate": 5e-05, "loss": 2.8264, "step": 1 }, { "epoch": 0.0006961970237577234, "eval_loss": 5.053422451019287, "eval_runtime": 3.2961, "eval_samples_per_second": 15.169, "eval_steps_per_second": 3.944, "step": 1 }, { "epoch": 0.0013923940475154468, "grad_norm": 6.345708847045898, "learning_rate": 0.0001, "loss": 3.6521, "step": 2 }, { "epoch": 0.0020885910712731704, "grad_norm": 5.618392467498779, "learning_rate": 9.990365154573717e-05, "loss": 3.2998, "step": 3 }, { "epoch": 0.0027847880950308936, "grad_norm": 5.514031887054443, "learning_rate": 9.961501876182148e-05, "loss": 2.304, "step": 4 }, { "epoch": 0.003480985118788617, "grad_norm": 3.9541125297546387, "learning_rate": 9.913533761814537e-05, "loss": 1.5882, "step": 5 }, { "epoch": 0.004177182142546341, "grad_norm": 3.096938133239746, "learning_rate": 9.846666218300807e-05, "loss": 1.2982, "step": 6 }, { "epoch": 0.004873379166304064, "grad_norm": 2.73142409324646, "learning_rate": 9.761185582727977e-05, "loss": 1.0909, "step": 7 }, { "epoch": 0.005569576190061787, "grad_norm": 2.2758121490478516, "learning_rate": 9.657457896300791e-05, "loss": 0.9526, "step": 8 }, { "epoch": 0.006265773213819511, "grad_norm": 2.1884617805480957, "learning_rate": 9.535927336897098e-05, "loss": 0.9004, "step": 9 }, { "epoch": 0.006961970237577234, "grad_norm": 1.905522108078003, "learning_rate": 9.397114317029975e-05, "loss": 0.8348, "step": 10 }, { "epoch": 0.007658167261334958, "grad_norm": 1.953636646270752, "learning_rate": 9.241613255361455e-05, "loss": 0.8431, "step": 11 }, { "epoch": 0.008354364285092682, "grad_norm": 2.07503342628479, "learning_rate": 9.070090031310558e-05, "loss": 0.8399, "step": 12 }, { "epoch": 0.009050561308850404, "grad_norm": 2.3713271617889404, "learning_rate": 8.883279133655399e-05, "loss": 1.0231, "step": 13 }, { "epoch": 0.009746758332608128, "grad_norm": 1.4214296340942383, "learning_rate": 8.681980515339464e-05, "loss": 0.8436, "step": 14 }, { "epoch": 0.010442955356365852, "grad_norm": 1.3992135524749756, "learning_rate": 8.467056167950311e-05, "loss": 0.7956, "step": 15 }, { "epoch": 0.011139152380123574, "grad_norm": 1.2084200382232666, "learning_rate": 8.239426430539243e-05, "loss": 0.6528, "step": 16 }, { "epoch": 0.011835349403881298, "grad_norm": 1.291199803352356, "learning_rate": 8.000066048588211e-05, "loss": 0.7458, "step": 17 }, { "epoch": 0.012531546427639022, "grad_norm": 1.2058777809143066, "learning_rate": 7.75e-05, "loss": 0.6487, "step": 18 }, { "epoch": 0.013227743451396745, "grad_norm": 1.1101080179214478, "learning_rate": 7.490299105985507e-05, "loss": 0.6245, "step": 19 }, { "epoch": 0.013923940475154469, "grad_norm": 1.1463162899017334, "learning_rate": 7.222075445642904e-05, "loss": 0.6225, "step": 20 }, { "epoch": 0.014620137498912193, "grad_norm": 1.246386170387268, "learning_rate": 6.946477593864228e-05, "loss": 0.7079, "step": 21 }, { "epoch": 0.015316334522669915, "grad_norm": 1.2304069995880127, "learning_rate": 6.664685702961344e-05, "loss": 0.6294, "step": 22 }, { "epoch": 0.01601253154642764, "grad_norm": 1.3009647130966187, "learning_rate": 6.377906449072578e-05, "loss": 0.6165, "step": 23 }, { "epoch": 0.016708728570185363, "grad_norm": 1.384681224822998, "learning_rate": 6.087367864990233e-05, "loss": 0.6018, "step": 24 }, { "epoch": 0.017404925593943087, "grad_norm": 1.7515813112258911, "learning_rate": 5.794314081535644e-05, "loss": 0.6501, "step": 25 }, { "epoch": 0.017404925593943087, "eval_loss": 0.7062661051750183, "eval_runtime": 3.3907, "eval_samples_per_second": 14.746, "eval_steps_per_second": 3.834, "step": 25 }, { "epoch": 0.018101122617700808, "grad_norm": 1.3576762676239014, "learning_rate": 5.500000000000001e-05, "loss": 0.7465, "step": 26 }, { "epoch": 0.018797319641458532, "grad_norm": 1.313129186630249, "learning_rate": 5.205685918464356e-05, "loss": 0.6395, "step": 27 }, { "epoch": 0.019493516665216256, "grad_norm": 1.188519835472107, "learning_rate": 4.912632135009769e-05, "loss": 0.7079, "step": 28 }, { "epoch": 0.02018971368897398, "grad_norm": 1.1454977989196777, "learning_rate": 4.6220935509274235e-05, "loss": 0.6928, "step": 29 }, { "epoch": 0.020885910712731704, "grad_norm": 1.0681382417678833, "learning_rate": 4.3353142970386564e-05, "loss": 0.6142, "step": 30 }, { "epoch": 0.021582107736489428, "grad_norm": 1.1505845785140991, "learning_rate": 4.053522406135775e-05, "loss": 0.5769, "step": 31 }, { "epoch": 0.02227830476024715, "grad_norm": 1.2340224981307983, "learning_rate": 3.777924554357096e-05, "loss": 0.5512, "step": 32 }, { "epoch": 0.022974501784004873, "grad_norm": 1.0733771324157715, "learning_rate": 3.509700894014496e-05, "loss": 0.5667, "step": 33 }, { "epoch": 0.023670698807762597, "grad_norm": 1.0927112102508545, "learning_rate": 3.250000000000001e-05, "loss": 0.5102, "step": 34 }, { "epoch": 0.02436689583152032, "grad_norm": 1.3149555921554565, "learning_rate": 2.9999339514117912e-05, "loss": 0.5898, "step": 35 }, { "epoch": 0.025063092855278045, "grad_norm": 1.3991199731826782, "learning_rate": 2.760573569460757e-05, "loss": 0.6337, "step": 36 }, { "epoch": 0.025759289879035766, "grad_norm": 1.4893077611923218, "learning_rate": 2.53294383204969e-05, "loss": 0.6278, "step": 37 }, { "epoch": 0.02645548690279349, "grad_norm": 1.150443434715271, "learning_rate": 2.3180194846605367e-05, "loss": 0.8092, "step": 38 }, { "epoch": 0.027151683926551214, "grad_norm": 0.8582993745803833, "learning_rate": 2.1167208663446025e-05, "loss": 0.6176, "step": 39 }, { "epoch": 0.027847880950308938, "grad_norm": 1.009572148323059, "learning_rate": 1.9299099686894423e-05, "loss": 0.5971, "step": 40 }, { "epoch": 0.02854407797406666, "grad_norm": 1.0766137838363647, "learning_rate": 1.758386744638546e-05, "loss": 0.5786, "step": 41 }, { "epoch": 0.029240274997824386, "grad_norm": 0.9323824644088745, "learning_rate": 1.602885682970026e-05, "loss": 0.555, "step": 42 }, { "epoch": 0.029936472021582106, "grad_norm": 1.1088814735412598, "learning_rate": 1.464072663102903e-05, "loss": 0.5825, "step": 43 }, { "epoch": 0.03063266904533983, "grad_norm": 0.9386204481124878, "learning_rate": 1.3425421036992098e-05, "loss": 0.5434, "step": 44 }, { "epoch": 0.03132886606909756, "grad_norm": 0.8790339827537537, "learning_rate": 1.2388144172720251e-05, "loss": 0.4153, "step": 45 }, { "epoch": 0.03202506309285528, "grad_norm": 1.0394346714019775, "learning_rate": 1.1533337816991932e-05, "loss": 0.4865, "step": 46 }, { "epoch": 0.032721260116613, "grad_norm": 1.093427062034607, "learning_rate": 1.0864662381854632e-05, "loss": 0.5469, "step": 47 }, { "epoch": 0.03341745714037073, "grad_norm": 1.174867033958435, "learning_rate": 1.0384981238178534e-05, "loss": 0.5534, "step": 48 }, { "epoch": 0.03411365416412845, "grad_norm": 1.370957851409912, "learning_rate": 1.0096348454262845e-05, "loss": 0.5735, "step": 49 }, { "epoch": 0.034809851187886175, "grad_norm": 1.5540739297866821, "learning_rate": 1e-05, "loss": 0.6185, "step": 50 }, { "epoch": 0.034809851187886175, "eval_loss": 0.5986165404319763, "eval_runtime": 3.3935, "eval_samples_per_second": 14.734, "eval_steps_per_second": 3.831, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 6.631381723512832e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }